Provider & model performance

First-token latency, completion rate and effective throughput from real requests across TrustedRouter providers and models.

Last updated 2026-09-16T04:17:28.551Z

68 providers 5994 availability samples 156 sustained throughput samples Video leaderboard
Measurement details

Continuously sampled from TrustedRouter's monitor regions using a rolling benchmark set of up to 10,000 samples. Ranked by p50 time-to-first-token across all of a provider's models. Provider-attributed availability breaks latency ties. Different model mixes are not a controlled speed comparison.

Completion rate shows the end-user result. Provider availability excludes failures owned by TrustedRouter, customers, or route configuration, while still reporting those failures under their actual owner. Capacity acceptance measures requests not rejected for provider overload. Effective throughput is provider-reported output tokens divided by complete request time, so buffered delivery cannot inflate the result.

Models need 10 availability samples and providers need 30, each with at least 3 measured first tokens, to receive a rank. Thin availability and throughput measurements stay visible below the ranked set as warming. Unsupported route and probe-configuration rows are reported separately and do not count as provider downtime. No prompt or output content is ever stored.

Providers

#ProviderCompletionp50 TTFTEffective throughputSamplesDetails
1 google-ai-studio 6 models 100.00% 804 ms Not measured 0 samples, warming 50010 with TTFT
More
Provider availability
100.00% (500 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3948 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
2 mistral 5 models 100.00% 1276 ms 78 tok/s 2 samples, warming 4228 with TTFT
More
Provider availability
100.00% (42 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3074 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
3 friendli 7 models 100.00% 1283 ms 56 tok/s 1 samples, warming 3636 with TTFT
More
Provider availability
100.00% (36 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
13512 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
4 scaledown 4 models 3 excluded 100.00% 1303 ms Not measured 0 samples, warming 3534 with TTFT
More
Provider availability
100.00% (35 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
7732 ms
Failure owner
None
Errors
None
Excluded from provider availability
provider_error: 3
5 cerebras 4 models 100.00% 1403 ms 263 tok/s 2 samples, warming 3434 with TTFT
More
Provider availability
100.00% (34 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4228 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
6 digitalocean 13 models 96.67% 1413 ms 17 tok/s 5 samples 3029 with TTFT
More
Provider availability
96.67% (30 samples)
Within deadline
96.67%
Capacity accepted
100.00%
p95 TTFT
4122 ms
Failure owner
provider: 1
Errors
TimeoutError: 1
Excluded from provider availability
None
7 mancer 6 models 97.06% 1450 ms 122 tok/s 2 samples, warming 3433 with TTFT
More
Provider availability
97.06% (34 samples)
Within deadline
97.06%
Capacity accepted
100.00%
p95 TTFT
6329 ms
Failure owner
provider: 1
Errors
TimeoutError: 1
Excluded from provider availability
None
8 parasail 20 models 87.50% 1617 ms 138 tok/s 4 samples 3228 with TTFT
More
Provider availability
87.50% (32 samples)
Within deadline
87.50%
Capacity accepted
90.62%
p95 TTFT
5711 ms
Failure owner
provider: 4
Errors
TimeoutError: 1, provider_error: 3
Excluded from provider availability
None
9 scaleway 10 models 100.00% 1683 ms 77 tok/s 1 samples, warming 3232 with TTFT
More
Provider availability
100.00% (32 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4250 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
10 siliconflow 18 models 100.00% 1704 ms 69 tok/s 9 samples 48625 with TTFT
More
Provider availability
100.00% (486 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
6170 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
11 google-vertex 10 models 100.00% 1795 ms 58 tok/s 5 samples 3431 with TTFT
More
Provider availability
100.00% (34 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
5269 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
12 engy 8 models 100.00% 1813 ms 72 tok/s 2 samples, warming 3333 with TTFT
More
Provider availability
100.00% (33 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4413 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
13 fireworks 18 models 100.00% 1979 ms 82 tok/s 9 samples 28632 with TTFT
More
Provider availability
100.00% (286 samples)
Within deadline
96.88%
Capacity accepted
100.00%
p95 TTFT
5415 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
14 morph 8 models 67.65% 1994 ms 52 tok/s 4 samples 3423 with TTFT
More
Provider availability
67.65% (34 samples)
Within deadline
64.71%
Capacity accepted
79.41%
p95 TTFT
10027 ms
Failure owner
provider: 11
Errors
TimeoutError: 4, provider_error: 7
Excluded from provider availability
None
15 anthropic 9 models 2 excluded 99.56% 2005 ms 74 tok/s 1 samples, warming 225108 with TTFT
More
Provider availability
99.56% (225 samples)
Within deadline
97.25%
Capacity accepted
100.00%
p95 TTFT
4011 ms
Failure owner
provider: 1
Errors
empty_stream: 1
Excluded from provider availability
provider_error: 2
16 sail-research 9 models 99.80% 2059 ms 114 tok/s 2 samples, warming 49529 with TTFT
More
Provider availability
99.80% (495 samples)
Within deadline
96.67%
Capacity accepted
100.00%
p95 TTFT
4139 ms
Failure owner
provider: 1
Errors
TimeoutError: 1
Excluded from provider availability
None
17 deepinfra 41 models 97.76% 2117 ms 44 tok/s 9 samples 13440 with TTFT
More
Provider availability
97.76% (134 samples)
Within deadline
93.02%
Capacity accepted
100.00%
p95 TTFT
8086 ms
Failure owner
provider: 3
Errors
TimeoutError: 1, empty_stream: 2
Excluded from provider availability
None
18 baseten 11 models 100.00% 2118 ms 356 tok/s 1 samples, warming 497452 with TTFT
More
Provider availability
100.00% (497 samples)
Within deadline
99.78%
Capacity accepted
100.00%
p95 TTFT
4944 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
19 deepseek 4 models 100.00% 2172 ms 146 tok/s 1 samples, warming 7267 with TTFT
More
Provider availability
100.00% (72 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4643 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
20 lightning 19 models 87.10% 2198 ms 47 tok/s 4 samples 3127 with TTFT
More
Provider availability
87.10% (31 samples)
Within deadline
87.10%
Capacity accepted
100.00%
p95 TTFT
5240 ms
Failure owner
provider: 4
Errors
provider_error: 4
Excluded from provider availability
None
21 alibaba 31 models 100.00% 2212 ms 61 tok/s 3 samples 3838 with TTFT
More
Provider availability
100.00% (38 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4338 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
22 upstage 3 models 100.00% 2273 ms 87 tok/s 2 samples, warming 3232 with TTFT
More
Provider availability
100.00% (32 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4354 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
23 openai 20 models 100.00% 2288 ms Not measured 0 samples, warming 19929 with TTFT
More
Provider availability
100.00% (199 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
5573 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
24 pearl 5 models 100.00% 2461 ms 152 tok/s 2 samples, warming 3232 with TTFT
More
Provider availability
100.00% (32 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
5014 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
25 together 10 models 100.00% 2667 ms 95 tok/s 5 samples 11828 with TTFT
More
Provider availability
100.00% (118 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
6338 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
26 perplexity 1 models 100.00% 2678 ms Not measured 0 samples, warming 3232 with TTFT
More
Provider availability
100.00% (32 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
5233 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
27 nvidia-nim 13 models 40.62% 3056 ms Not measured 0 samples, warming 3213 with TTFT
More
Provider availability
40.62% (32 samples)
Within deadline
40.62%
Capacity accepted
100.00%
p95 TTFT
18949 ms
Failure owner
provider: 19
Errors
TimeoutError: 15, empty_stream: 4
Excluded from provider availability
None
28 tinfoil 8 models 82.44% 3379 ms 156 tok/s 3 samples 262200 with TTFT
More
Provider availability
82.44% (262 samples)
Within deadline
80.89%
Capacity accepted
83.97%
p95 TTFT
5760 ms
Failure owner
provider: 46
Errors
provider_error: 46
Excluded from provider availability
None
29 zai 11 models 100.00% 3569 ms 50 tok/s 2 samples, warming 4828 with TTFT
More
Provider availability
100.00% (48 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
12203 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
30 nebius 11 models 99.40% 4185 ms 103 tok/s 1 samples, warming 498495 with TTFT
More
Provider availability
99.40% (498 samples)
Within deadline
99.40%
Capacity accepted
100.00%
p95 TTFT
8166 ms
Failure owner
provider: 3
Errors
TimeoutError: 1, provider_error: 2
Excluded from provider availability
None
31 kimi 4 models 100.00% 7274 ms 41 tok/s 2 samples, warming 25243 with TTFT
More
Provider availability
100.00% (252 samples)
Within deadline
97.67%
Capacity accepted
100.00%
p95 TTFT
18624 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
32 chutes 10 models 77.78% 7680 ms 29 tok/s 1 samples, warming 3627 with TTFT
More
Provider availability
77.78% (36 samples)
Within deadline
71.43%
Capacity accepted
100.00%
p95 TTFT
20287 ms
Failure owner
provider: 8
Errors
TimeoutError: 5, provider_error: 3
Excluded from provider availability
None
grok 6 models warming 100.00% 1351 ms 48 tok/s 3 samples 2828 with TTFT
More
Provider availability
100.00% (28 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3553 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
inception 1 models warming 100.00% 1526 ms 180 tok/s 2 samples, warming 2626 with TTFT
More
Provider availability
100.00% (26 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3463 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
wafer 7 models warming 93.10% 1539 ms 110 tok/s 1 samples, warming 2927 with TTFT
More
Provider availability
93.10% (29 samples)
Within deadline
89.66%
Capacity accepted
100.00%
p95 TTFT
4061 ms
Failure owner
provider: 2
Errors
TimeoutError: 2
Excluded from provider availability
None
telnyx 14 models warming 100.00% 1612 ms 121 tok/s 4 samples 2220 with TTFT
More
Provider availability
100.00% (22 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3626 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
cloudflare-workers-ai 16 models warming 100.00% 1680 ms Not measured 0 samples, warming 2525 with TTFT
More
Provider availability
100.00% (25 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3456 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
atlas-cloud 29 models warming 100.00% 1755 ms 42 tok/s 9 samples 2626 with TTFT
More
Provider availability
100.00% (26 samples)
Within deadline
96.15%
Capacity accepted
100.00%
p95 TTFT
4438 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
azure 8 models warming 100.00% 1762 ms 99 tok/s 1 samples, warming 2626 with TTFT
More
Provider availability
100.00% (26 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4966 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
reka 1 models warming 100.00% 1850 ms Not measured 0 samples, warming 2626 with TTFT
More
Provider availability
100.00% (26 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3721 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
nextbit 8 models warming 95.83% 1868 ms 124 tok/s 1 samples, warming 2423 with TTFT
More
Provider availability
95.83% (24 samples)
Within deadline
95.83%
Capacity accepted
95.83%
p95 TTFT
4146 ms
Failure owner
provider: 1
Errors
provider_error: 1
Excluded from provider availability
None
makora 5 models warming 1 excluded 85.00% 1882 ms 13 tok/s 1 samples, warming 2017 with TTFT
More
Provider availability
85.00% (20 samples)
Within deadline
85.00%
Capacity accepted
100.00%
p95 TTFT
6562 ms
Failure owner
provider: 3
Errors
TimeoutError: 3
Excluded from provider availability
unsupported_route: 1
relace 2 models warming 96.43% 1940 ms Not measured 0 samples, warming 2827 with TTFT
More
Provider availability
96.43% (28 samples)
Within deadline
96.43%
Capacity accepted
100.00%
p95 TTFT
7630 ms
Failure owner
provider: 1
Errors
provider_error: 1
Excluded from provider availability
None
regolo 10 models warming 100.00% 1965 ms 99 tok/s 2 samples, warming 2525 with TTFT
More
Provider availability
100.00% (25 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3554 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
aion-labs 2 models warming 11 excluded 100.00% 1968 ms 56 tok/s 1 samples, warming 44 with TTFT
More
Provider availability
100.00% (4 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3263 ms
Failure owner
None
Errors
None
Excluded from provider availability
probe_config_error: 11
minimax 6 models warming 100.00% 2010 ms 153 tok/s 2 samples, warming 2929 with TTFT
More
Provider availability
100.00% (29 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4396 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
databricks 7 models warming 100.00% 2052 ms Not measured 0 samples, warming 2525 with TTFT
More
Provider availability
100.00% (25 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3917 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
novita 22 models warming 86.36% 2096 ms 63 tok/s 9 samples 2218 with TTFT
More
Provider availability
86.36% (22 samples)
Within deadline
80.95%
Capacity accepted
100.00%
p95 TTFT
22809 ms
Failure owner
provider: 3
Errors
TimeoutError: 2, empty_stream: 1
Excluded from provider availability
None
thinkingmachines 3 models warming 100.00% 2117 ms 79 tok/s 1 samples, warming 2020 with TTFT
More
Provider availability
100.00% (20 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4968 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
io-net 24 models warming 100.00% 2147 ms 140 tok/s 7 samples 2424 with TTFT
More
Provider availability
100.00% (24 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4255 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
akashml 6 models warming 100.00% 2265 ms Not measured 0 samples, warming 2323 with TTFT
More
Provider availability
100.00% (23 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
5033 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
wandb 17 models warming 100.00% 2298 ms 116 tok/s 3 samples 2626 with TTFT
More
Provider availability
100.00% (26 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
9033 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
venice 22 models warming 100.00% 2382 ms 79 tok/s 6 samples 2323 with TTFT
More
Provider availability
100.00% (23 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
16644 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
featherless 14 models warming 1 excluded 100.00% 2424 ms 172 tok/s 3 samples 2626 with TTFT
More
Provider availability
100.00% (26 samples)
Within deadline
96.15%
Capacity accepted
100.00%
p95 TTFT
22661 ms
Failure owner
None
Errors
None
Excluded from provider availability
probe_config_error: 1
nscale 10 models warming 100.00% 2528 ms Not measured 0 samples, warming 2924 with TTFT
More
Provider availability
100.00% (29 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4002 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
inceptron 6 models warming 88.89% 2618 ms 58 tok/s 1 samples, warming 2724 with TTFT
More
Provider availability
88.89% (27 samples)
Within deadline
88.89%
Capacity accepted
100.00%
p95 TTFT
17441 ms
Failure owner
provider: 3
Errors
provider_error: 3
Excluded from provider availability
None
zero-g 3 models warming 100.00% 2721 ms 93 tok/s 2 samples, warming 2323 with TTFT
More
Provider availability
100.00% (23 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
5078 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
stepfun 3 models warming 100.00% 2819 ms 129 tok/s 2 samples, warming 2525 with TTFT
More
Provider availability
100.00% (25 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
8265 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
gmi 6 models warming 100.00% 2878 ms 33 tok/s 2 samples, warming 2828 with TTFT
More
Provider availability
100.00% (28 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
11064 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
phala 5 models warming 56.00% 3003 ms 46 tok/s 3 samples 2514 with TTFT
More
Provider availability
56.00% (25 samples)
Within deadline
56.00%
Capacity accepted
100.00%
p95 TTFT
16011 ms
Failure owner
provider: 11
Errors
TimeoutError: 2, provider_error: 9
Excluded from provider availability
None
sambanova 6 models warming 88.24% 3015 ms Not measured 0 samples, warming 1715 with TTFT
More
Provider availability
88.24% (17 samples)
Within deadline
88.24%
Capacity accepted
100.00%
p95 TTFT
19308 ms
Failure owner
provider: 2
Errors
provider_error: 2
Excluded from provider availability
None
near-ai 1 models warming 3.85% 3555 ms Not measured 0 samples, warming 261 with TTFT
More
Provider availability
3.85% (26 samples)
Within deadline
3.85%
Capacity accepted
100.00%
p95 TTFT
3555 ms
Failure owner
provider: 25
Errors
TimeoutError: 1, provider_error: 24
Excluded from provider availability
None
confidential-ai 1 models warming 100.00% 3641 ms 244 tok/s 2 samples, warming 1414 with TTFT
More
Provider availability
100.00% (14 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4564 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
arcee 8 models warming 100.00% 4066 ms 57 tok/s 2 samples, warming 2929 with TTFT
More
Provider availability
100.00% (29 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
6524 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
xiaomi 2 models warming 100.00% 5113 ms 127 tok/s 1 samples, warming 1818 with TTFT
More
Provider availability
100.00% (18 samples)
Within deadline
88.89%
Capacity accepted
100.00%
p95 TTFT
24823 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
sakana 1 models warming 17 excluded 58.54% 7213 ms Not measured 0 samples, warming 2424 with TTFT
More
Provider availability
100.00% (24 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
8658 ms
Failure owner
trustedrouter: 17
Errors
None
Excluded from provider availability
router_error: 17
neurometric 1 models warming 100.00% Not measured Not measured 0 samples, warming 5000 with TTFT
More
Provider availability
100.00% (500 samples)
Within deadline
Not measured
Capacity accepted
100.00%
p95 TTFT
Not measured
Failure owner
None
Errors
None
Excluded from provider availability
None
kling 1 models warming 0.00% Not measured Not measured 0 samples, warming 10 with TTFT
More
Provider availability
Not measured (0 samples)
Within deadline
Not measured
Capacity accepted
Not measured
p95 TTFT
Not measured
Failure owner
unknown: 1
Errors
provider_error: 1
Excluded from provider availability
None

Models

#Model / providerCompletionp50 TTFTEffective throughputSamplesDetails
1 mistralai/mistral-medium-3-5 mistral 100.00% 1163 ms Not measured 0 samples, warming 1010 with TTFT
More
Provider availability
100.00% (10 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3114 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T04:00:50.000Z
2 mistralai/mistral-nemo mistral 100.00% 1276 ms 78 tok/s 2 samples, warming 217 with TTFT
More
Provider availability
100.00% (21 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2866 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T23:30:15.218Z
3 scaledown/compress scaledown 1 excluded 100.00% 1303 ms Not measured 0 samples, warming 1010 with TTFT
More
Provider availability
100.00% (10 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3150 ms
Failure owner
None
Errors
None
Excluded from provider availability
provider_error: 1
Last seen
2026-09-16T03:21:43.000Z
4 x-ai/grok-4.6 grok 100.00% 1351 ms 48 tok/s 3 samples 1414 with TTFT
More
Provider availability
100.00% (14 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3295 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T04:10:10.000Z
5 cerebras/qwen-3.8-27b cerebras 100.00% 1395 ms Not measured 0 samples, warming 1313 with TTFT
More
Provider availability
100.00% (13 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4228 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:24:56.000Z
6 inception/mercury-2 inception 100.00% 1526 ms 180 tok/s 2 samples, warming 2626 with TTFT
More
Provider availability
100.00% (26 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3463 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:27:41.000Z
7 minimax/minimax-m3 together 100.00% 1599 ms 137 tok/s 2 samples, warming 455 with TTFT
More
Provider availability
100.00% (45 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4198 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T02:57:48.000Z
8 upstage/solar-pro2 upstage 100.00% 1625 ms Not measured 0 samples, warming 1212 with TTFT
More
Provider availability
100.00% (12 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4277 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T04:06:50.000Z
9 anthropic/claude-haiku-4.5 anthropic 100.00% 1656 ms Not measured 0 samples, warming 9082 with TTFT
More
Provider availability
100.00% (90 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3536 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:06:53.834Z
10 reka/reka-edge-2603 reka 100.00% 1850 ms Not measured 0 samples, warming 2626 with TTFT
More
Provider availability
100.00% (26 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3721 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T02:27:47.000Z
11 deepseek/deepseek-v4-flash-0731 relace 93.75% 1940 ms Not measured 0 samples, warming 1615 with TTFT
More
Provider availability
93.75% (16 samples)
Within deadline
93.75%
Capacity accepted
100.00%
p95 TTFT
4043 ms
Failure owner
provider: 1
Errors
provider_error: 1
Excluded from provider availability
None
Last seen
2026-09-16T00:57:38.000Z
12 minimax/minimax-m3 fireworks 100.00% 1979 ms 150 tok/s 1 samples, warming 273 with TTFT
More
Provider availability
100.00% (27 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3499 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:54:15.011Z
13 anthropic/claude-sonnet-5 anthropic 2 excluded 100.00% 2005 ms Not measured 0 samples, warming 266 with TTFT
More
Provider availability
100.00% (26 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4309 ms
Failure owner
None
Errors
None
Excluded from provider availability
provider_error: 2
Last seen
2026-09-15T20:21:41.000Z
14 moonshotai/kimi-k2.6 kimi 100.00% 2015 ms 27 tok/s 1 samples, warming 1111 with TTFT
More
Provider availability
100.00% (11 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
10062 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T02:55:34.000Z
15 google/gemma-4-12b-it sail-research 100.00% 2059 ms Not measured 0 samples, warming 4683 with TTFT
More
Provider availability
100.00% (468 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2113 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T00:14:31.000Z
16 zero-g/0gm-1.0-35b-a3b-sia zero-g 100.00% 2100 ms Not measured 0 samples, warming 1010 with TTFT
More
Provider availability
100.00% (10 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
5078 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:58:41.000Z
17 deepseek/deepseek-v4-flash-0731 baseten 100.00% 2118 ms Not measured 0 samples, warming 444444 with TTFT
More
Provider availability
100.00% (444 samples)
Within deadline
99.77%
Capacity accepted
100.00%
p95 TTFT
4900 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T00:37:32.677Z
18 deepseek/deepseek-v4-flash deepseek 100.00% 2172 ms 146 tok/s 1 samples, warming 5954 with TTFT
More
Provider availability
100.00% (59 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4743 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T20:39:10.000Z
19 upstage/solar-pro3 upstage 100.00% 2273 ms Not measured 0 samples, warming 1313 with TTFT
More
Provider availability
100.00% (13 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4354 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T02:20:29.000Z
20 prism-ml/ternary-bonsai-27b together 100.00% 2667 ms Not measured 0 samples, warming 555 with TTFT
More
Provider availability
100.00% (55 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2869 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:22:07.455Z
21 perplexity/sonar perplexity 100.00% 2678 ms Not measured 0 samples, warming 3232 with TTFT
More
Provider availability
100.00% (32 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
5233 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:17:34.000Z
22 moonshotai/kimi-k3 relace 100.00% 2694 ms Not measured 0 samples, warming 1212 with TTFT
More
Provider availability
100.00% (12 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
8967 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:36:53.000Z
23 stepfun/step-3.5-flash-2603 stepfun 100.00% 2819 ms Not measured 0 samples, warming 1111 with TTFT
More
Provider availability
100.00% (11 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
5552 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T23:47:08.000Z
24 deepseek/deepseek-v4-flash tinfoil 79.72% 3379 ms Not measured 0 samples, warming 217173 with TTFT
More
Provider availability
79.72% (217 samples)
Within deadline
79.72%
Capacity accepted
81.11%
p95 TTFT
5656 ms
Failure owner
provider: 44
Errors
provider_error: 44
Excluded from provider availability
None
Last seen
2026-09-15T21:42:46.000Z
25 deepseek/deepseek-v4-flash-0731 confidential-ai 100.00% 3641 ms 244 tok/s 2 samples, warming 1414 with TTFT
More
Provider availability
100.00% (14 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4564 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:42:42.000Z
26 deepseek/deepseek-v4-flash-0731 nebius 99.59% 4185 ms Not measured 0 samples, warming 483481 with TTFT
More
Provider availability
99.59% (483 samples)
Within deadline
99.59%
Capacity accepted
100.00%
p95 TTFT
8166 ms
Failure owner
provider: 2
Errors
provider_error: 2
Excluded from provider availability
None
Last seen
2026-09-16T01:30:46.000Z
27 openai/gpt-oss-120b tinfoil 100.00% 4703 ms 73 tok/s 1 samples, warming 103 with TTFT
More
Provider availability
100.00% (10 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
10812 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:21:21.002Z
28 xiaomi/mimo-v2.5-pro xiaomi 100.00% 5113 ms 127 tok/s 1 samples, warming 1010 with TTFT
More
Provider availability
100.00% (10 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
13598 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T00:57:01.000Z
29 sakana-ai/fugu-ultra-v1.1 sakana 17 excluded 58.54% 7213 ms Not measured 0 samples, warming 2424 with TTFT
More
Provider availability
100.00% (24 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
8658 ms
Failure owner
trustedrouter: 17
Errors
None
Excluded from provider availability
router_error: 17
Last seen
2026-09-16T03:20:44.000Z
30 moonshotai/kimi-k3 kimi 100.00% 7274 ms 55 tok/s 1 samples, warming 22920 with TTFT
More
Provider availability
100.00% (229 samples)
Within deadline
95.00%
Capacity accepted
100.00%
p95 TTFT
19710 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:18:50.000Z
stepfun-ai/step-3.7-flash deepinfra warming 100.00% 441 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
441 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T06:59:48.000Z
z-ai/glm-5.3-flash together warming 100.00% 577 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3302 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T22:45:11.000Z
meta-models/muse-glimmer-30b fireworks warming 100.00% 624 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
879 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:21:39.000Z
thinkingmachines/inkling-small deepinfra warming 100.00% 661 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
661 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T19:33:38.000Z
meta-llama/llama-3.2-1b-instruct cloudflare-workers-ai warming 100.00% 707 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1708 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T20:00:39.000Z
poolside/laguna-xs-2.1 nvidia-nim warming 33.33% 711 ms Not measured 0 samples, warming 31 with TTFT
More
Provider availability
33.33% (3 samples)
Within deadline
33.33%
Capacity accepted
100.00%
p95 TTFT
711 ms
Failure owner
provider: 2
Errors
empty_stream: 2
Excluded from provider availability
None
Last seen
2026-09-16T03:55:30.000Z
meta-llama/llama-3.2-11b-vision-instruct nvidia-nim warming 100.00% 745 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
995 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:15:41.000Z
x-ai/grok-build-0.1 grok warming 100.00% 782 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
787 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T19:21:32.000Z
ibm-granite/granite-4.2-30b deepinfra warming 100.00% 788 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1481 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T19:42:25.000Z
meta-llama/llama-3.3-70b-instruct together warming 100.00% 797 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3910 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T00:22:13.000Z
deepseek/deepseek-ocr-2 novita warming 100.00% 801 ms Not measured 0 samples, warming 21 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
801 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:41:40.152Z
google/gemini-2.5-flash google-ai-studio warming 100.00% 804 ms Not measured 0 samples, warming 4911 with TTFT
More
Provider availability
100.00% (491 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
804 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T04:17:05.710Z
bytedance/ui-tars-1.5-7b parasail warming 100.00% 811 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
811 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T08:25:10.000Z
openai/gpt-4.1-mini openai warming 100.00% 811 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
811 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T00:26:12.000Z
nvidia/nemotron-3.5-lightning-30b-a3b nvidia-nim warming 100.00% 819 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
819 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:00:47.000Z
qwen/qwen3-30b-a3b-fp8 cloudflare-workers-ai warming 100.00% 825 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
825 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T08:40:56.000Z
openpipe/qwen3-14b-instruct wandb warming 100.00% 854 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
854 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T12:14:50.000Z
moonshotai/kimi-k3 telnyx warming 100.00% 861 ms 111 tok/s 1 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3246 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:41:54.000Z
undi95/remm-slerp-l2-13b mancer warming 100.00% 884 ms Not measured 0 samples, warming 44 with TTFT
More
Provider availability
100.00% (4 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3253 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T11:51:37.000Z
openai/gpt-4o-2024-05-13 openai warming 100.00% 895 ms Not measured 0 samples, warming 33 with TTFT
More
Provider availability
100.00% (3 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
7238 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T00:24:14.000Z
minimax/minimax-m2.5 digitalocean warming 100.00% 896 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3381 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T20:32:46.000Z
z-ai/glm-5.1 friendli warming 100.00% 903 ms Not measured 0 samples, warming 44 with TTFT
More
Provider availability
100.00% (4 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2937 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T00:39:44.000Z
z-ai/glm-5.2 friendli warming 100.00% 911 ms Not measured 0 samples, warming 66 with TTFT
More
Provider availability
100.00% (6 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3151 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T23:21:53.000Z
nousresearch/hermes-3-llama-3.1-405b deepinfra warming 100.00% 925 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1638 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T23:55:58.000Z
deepseek/deepseek-v3.2 io-net warming 100.00% 941 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
941 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T07:36:06.000Z
qwen/qwen3-235b-a22b-instruct-2507 scaleway warming 100.00% 947 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
947 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T21:56:28.000Z
google/gemini-3.6-flash google-vertex warming 100.00% 952 ms 88 tok/s 2 samples, warming 66 with TTFT
More
Provider availability
100.00% (6 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3479 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:12:13.000Z
mistralai/mistral-small-2603 regolo warming 100.00% 954 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1601 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:24:46.000Z
morph/morph-v3-fast morph warming 100.00% 957 ms Not measured 0 samples, warming 66 with TTFT
More
Provider availability
100.00% (6 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3595 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T02:50:29.000Z
meta-llama/llama-3.3-70b-instruct sambanova warming 100.00% 959 ms Not measured 0 samples, warming 33 with TTFT
More
Provider availability
100.00% (3 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1061 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T02:24:01.000Z
google/gemini-3.1-flash-image-preview google-ai-studio warming 100.00% 981 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3427 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:08:13.000Z
openai/gpt-oss-20b cloudflare-workers-ai warming 100.00% 1022 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1661 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T04:15:44.000Z
deepseek/deepseek-v4-flash wandb warming 100.00% 1035 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3797 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:21:54.000Z
openai/gpt-oss-120b cloudflare-workers-ai warming 100.00% 1035 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1035 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:45:43.000Z
meta-llama/llama-3.3-70b-instruct databricks warming 100.00% 1046 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1051 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T16:30:43.000Z
qwen/qwen-plus alibaba warming 100.00% 1050 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1050 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T04:42:31.000Z
qwen/qwen3-235b-a22b-instruct-2507 venice warming 100.00% 1051 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1051 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:58:50.000Z
deepseek/deepseek-v3.2 friendli warming 100.00% 1063 ms Not measured 0 samples, warming 44 with TTFT
More
Provider availability
100.00% (4 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4297 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:15:46.000Z
deepseek/deepseek-v4.1-flash wafer warming 100.00% 1078 ms Not measured 0 samples, warming 33 with TTFT
More
Provider availability
100.00% (3 samples)
Within deadline
66.67%
Capacity accepted
100.00%
p95 TTFT
25510 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:51:56.000Z
openai/gpt-oss-120b together warming 100.00% 1090 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
6338 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T07:08:00.000Z
mistralai/mistral-small-2603 mistral warming 100.00% 1094 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1094 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T20:51:06.000Z
xiaomi/mimo-v2.5-pro digitalocean warming 80.00% 1109 ms 62 tok/s 2 samples, warming 54 with TTFT
More
Provider availability
80.00% (5 samples)
Within deadline
80.00%
Capacity accepted
100.00%
p95 TTFT
3698 ms
Failure owner
provider: 1
Errors
TimeoutError: 1
Excluded from provider availability
None
Last seen
2026-09-16T03:46:52.000Z
openai/gpt-oss-120b sail-research warming 100.00% 1122 ms 161 tok/s 1 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1540 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:28:47.000Z
deepseek/deepseek-v4-flash-0423 wafer warming 100.00% 1123 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3811 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T18:36:47.000Z
z-ai/glm-5.3 siliconflow warming 100.00% 1126 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1126 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T10:16:48.000Z
openai/gpt-oss-120b nscale warming 100.00% 1136 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1136 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T21:24:45.000Z
qwen/qwen3-235b-a22b-2507 atlas-cloud warming 100.00% 1142 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1142 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T17:13:21.000Z
z-ai/glm-5 gmi warming 100.00% 1152 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2824 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T00:11:02.000Z
meta-llama/llama-3.3-70b-instruct regolo warming 100.00% 1162 ms Not measured 0 samples, warming 33 with TTFT
More
Provider availability
100.00% (3 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1512 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T16:43:36.000Z
minimax/minimax-m3 telnyx warming 100.00% 1170 ms 131 tok/s 2 samples, warming 44 with TTFT
More
Provider availability
100.00% (4 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3580 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:51:48.000Z
sao10k/l3.3-70b-euryale-v2.3 nextbit warming 75.00% 1174 ms Not measured 0 samples, warming 43 with TTFT
More
Provider availability
75.00% (4 samples)
Within deadline
75.00%
Capacity accepted
75.00%
p95 TTFT
2812 ms
Failure owner
provider: 1
Errors
provider_error: 1
Excluded from provider availability
None
Last seen
2026-09-16T00:26:13.000Z
x-ai/grok-4.20-reasoning grok warming 100.00% 1180 ms Not measured 0 samples, warming 66 with TTFT
More
Provider availability
100.00% (6 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3410 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T02:17:07.000Z
z-ai/glm-5.3-fast fireworks warming 100.00% 1181 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1181 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T12:34:27.000Z
gryphe/mythomax-l2-13b mancer warming 100.00% 1201 ms Not measured 0 samples, warming 88 with TTFT
More
Provider availability
100.00% (8 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3229 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:51:56.000Z
moonshotai/kimi-k2.7-code fireworks warming 100.00% 1203 ms 88 tok/s 2 samples, warming 33 with TTFT
More
Provider availability
100.00% (3 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3158 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T04:17:26.000Z
scaledown/extract scaledown warming 1 excluded 100.00% 1208 ms Not measured 0 samples, warming 99 with TTFT
More
Provider availability
100.00% (9 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
9477 ms
Failure owner
None
Errors
None
Excluded from provider availability
provider_error: 1
Last seen
2026-09-15T20:48:48.000Z
z-ai/glm-4.7-flash cloudflare-workers-ai warming 100.00% 1211 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2914 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T02:48:54.000Z
openai/gpt-4 openai warming 100.00% 1215 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1215 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:18:51.000Z
openai/gpt-3.5-turbo openai warming 100.00% 1223 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1223 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T15:00:44.000Z
jetbrains/mellum2-12b-a2.5b-instruct wandb warming 100.00% 1229 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1229 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T02:20:28.000Z
google/gemma-4-31b-it-nvfp4 sail-research warming 100.00% 1241 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3194 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T02:24:48.000Z
deepseek/deepseek-v4.1-flash engy warming 100.00% 1251 ms Not measured 0 samples, warming 33 with TTFT
More
Provider availability
100.00% (3 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2063 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T19:09:46.000Z
meta-llama/llama-3.1-70b-instruct wandb warming 100.00% 1256 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1256 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T10:24:40.000Z
deepseek/deepseek-v4-pro digitalocean warming 100.00% 1258 ms Not measured 0 samples, warming 66 with TTFT
More
Provider availability
100.00% (6 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3722 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:51:58.000Z
qwen/qwen3.5-plus atlas-cloud warming 100.00% 1261 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1261 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T20:37:32.000Z
deepseek/deepseek-v3.1 wandb warming 100.00% 1280 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1280 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T00:46:28.000Z
minimax/minimax-m2.5 friendli warming 100.00% 1283 ms Not measured 0 samples, warming 44 with TTFT
More
Provider availability
100.00% (4 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3005 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T02:34:07.000Z
openai/gpt-oss-120b parasail warming 100.00% 1284 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2030 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:04:56.000Z
lightning-ai/deepseek-v4-pro lightning warming 100.00% 1285 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3350 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T11:18:54.000Z
deepseek/deepseek-v4-1-flash venice warming 100.00% 1310 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1310 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T22:18:46.000Z
z-ai/glm-4.7-flash io-net warming 100.00% 1311 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1311 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T20:54:20.000Z
nvidia/nemotron-3-ultra-550b-a55b deepinfra warming 100.00% 1313 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1313 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:30:45.000Z
z-ai/glm-5.3 baseten warming 100.00% 1321 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
5118 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:58:42.000Z
openai/gpt-oss-120b fireworks warming 100.00% 1327 ms Not measured 0 samples, warming 33 with TTFT
More
Provider availability
100.00% (3 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1541 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T00:33:40.000Z
z-ai/glm-5.3-flash telnyx warming 100.00% 1327 ms Not measured 0 samples, warming 31 with TTFT
More
Provider availability
100.00% (3 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1327 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T21:35:17.620Z
mistralai/mistral-small-3.2-24b-instruct-2506 deepinfra warming 100.00% 1328 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1328 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T02:09:46.000Z
google/gemma-4-26b-a4b-it parasail warming 50.00% 1336 ms Not measured 0 samples, warming 21 with TTFT
More
Provider availability
50.00% (2 samples)
Within deadline
50.00%
Capacity accepted
100.00%
p95 TTFT
1336 ms
Failure owner
provider: 1
Errors
TimeoutError: 1
Excluded from provider availability
None
Last seen
2026-09-15T14:19:12.000Z
x-ai/grok-build-0.1 atlas-cloud warming 100.00% 1344 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1344 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T23:21:46.000Z
moonshotai/kimi-k2.7-code siliconflow warming 100.00% 1345 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1345 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T11:48:52.000Z
openai/gpt-oss-120b-turbo deepinfra warming 100.00% 1358 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1358 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T00:06:40.000Z
google/gemma-4-31b-it tinfoil warming 100.00% 1359 ms 156 tok/s 2 samples, warming 55 with TTFT
More
Provider availability
100.00% (5 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4243 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:21:21.003Z
google/gemma-4-26b-a4b-it cloudflare-workers-ai warming 100.00% 1369 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1369 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T20:00:38.000Z
meta-llama/llama-3.1-8b-instruct-fp8 cloudflare-workers-ai warming 100.00% 1375 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3083 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T17:06:42.000Z
deepseek/deepseek-v4-flash-0731 mancer warming 100.00% 1382 ms Not measured 0 samples, warming 44 with TTFT
More
Provider availability
100.00% (4 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
6329 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T17:16:26.000Z
ibm-granite/granite-4.2-3b deepinfra warming 100.00% 1383 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1383 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T11:45:45.000Z
google/gemma-3-27b-it parasail warming 100.00% 1393 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1393 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T00:03:49.000Z
meta-llama/llama-3.3-70b-instruct tinfoil warming 100.00% 1397 ms Not measured 0 samples, warming 88 with TTFT
More
Provider availability
100.00% (8 samples)
Within deadline
87.50%
Capacity accepted
100.00%
p95 TTFT
27709 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:45:41.000Z
moonshotai/kimi-k2.7-code io-net warming 100.00% 1401 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1401 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T12:18:56.000Z
qwen/qwen3.7-plus atlas-cloud warming 100.00% 1402 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1402 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T18:01:51.000Z
openai/gpt-oss-120b cerebras warming 100.00% 1403 ms 123 tok/s 1 samples, warming 99 with TTFT
More
Provider availability
100.00% (9 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3711 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T22:47:47.000Z
z-ai/glm-5.3 wafer warming 66.67% 1412 ms Not measured 0 samples, warming 64 with TTFT
More
Provider availability
66.67% (6 samples)
Within deadline
66.67%
Capacity accepted
100.00%
p95 TTFT
3560 ms
Failure owner
provider: 2
Errors
TimeoutError: 2
Excluded from provider availability
None
Last seen
2026-09-16T02:15:39.000Z
mistralai/ministral-3-14b-instruct digitalocean warming 100.00% 1413 ms Not measured 0 samples, warming 55 with TTFT
More
Provider availability
100.00% (5 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3731 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T21:00:39.000Z
nvidia/nemotron-3-super-120b-a12b nvidia-nim warming 100.00% 1415 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1415 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T09:24:42.000Z
bsc-lt/alia-40b-instruct-2601 nextbit warming 100.00% 1417 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1958 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T11:41:49.000Z
meta-llama/llama-4-maverick parasail warming 100.00% 1420 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1420 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T09:18:47.000Z
deepseek/deepseek-v4-flash parasail warming 100.00% 1421 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
5711 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T14:04:39.000Z
anthropic/claude-opus-4.5 anthropic warming 100.00% 1423 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4049 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T23:23:48.000Z
qwen/qwen3.6-35b-a3b akashml warming 100.00% 1425 ms Not measured 0 samples, warming 77 with TTFT
More
Provider availability
100.00% (7 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2321 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:21:53.000Z
openai/gpt-4.1 openai warming 100.00% 1434 ms Not measured 0 samples, warming 21 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1434 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:33:28.917Z
nvidia/nemotron-nano-12b-v2-vl digitalocean warming 100.00% 1435 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1435 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T18:33:37.000Z
moonshotai/kimi-k2.6 digitalocean warming 100.00% 1436 ms 16 tok/s 1 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1436 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T16:58:50.000Z
qwen/qwen3.6-flash alibaba warming 100.00% 1444 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3687 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:02:54.000Z
google/gemma-3-27b-it nebius warming 100.00% 1447 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1447 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T21:48:44.000Z
openai/gpt-oss-120b mancer warming 100.00% 1450 ms 89 tok/s 1 samples, warming 44 with TTFT
More
Provider availability
100.00% (4 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3108 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:27:45.000Z
x-ai/grok-4.20-reasoning azure warming 100.00% 1450 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1450 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T06:00:38.000Z
meta-llama/llama-3.2-3b-instruct cloudflare-workers-ai warming 100.00% 1457 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1457 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T21:14:27.000Z
qwen/qwen2.5-coder-7b-instruct nscale warming 100.00% 1462 ms Not measured 0 samples, warming 32 with TTFT
More
Provider availability
100.00% (3 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3256 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T02:52:08.000Z
moonshotai/kimi-k3 wafer warming 100.00% 1463 ms 110 tok/s 1 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1463 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T00:39:43.000Z
qwen/qwen-mt-plus alibaba warming 100.00% 1466 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1988 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T02:03:36.000Z
moonshotai/kimi-k2.5 io-net warming 100.00% 1468 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1468 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T05:54:42.000Z
meta-llama/llama-3.1-8b-instruct wandb warming 100.00% 1469 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3516 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T09:33:46.000Z
moonshotai/kimi-k2.6 parasail warming 66.67% 1474 ms Not measured 0 samples, warming 32 with TTFT
More
Provider availability
66.67% (3 samples)
Within deadline
66.67%
Capacity accepted
66.67%
p95 TTFT
3661 ms
Failure owner
provider: 1
Errors
provider_error: 1
Excluded from provider availability
None
Last seen
2026-09-15T19:30:49.000Z
moonshotai/Kimi-K2.7-Code nebius warming 100.00% 1477 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1477 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T04:15:45.000Z
mistralai/mistral-nemo-instruct-2407 io-net warming 100.00% 1480 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2930 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T18:27:45.000Z
deepseek/deepseek-v4-pro venice warming 100.00% 1481 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1481 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T14:12:54.000Z
moonshotai/kimi-k2.5 atlas-cloud warming 100.00% 1490 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1490 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T20:15:50.000Z
lightning-ai/nemotron-3-ultra-550b-a55b lightning warming 100.00% 1496 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3690 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T10:39:43.000Z
moonshotai/kimi-k2.6 sail-research warming 100.00% 1499 ms Not measured 0 samples, warming 44 with TTFT
More
Provider availability
100.00% (4 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3767 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T23:48:42.000Z
openai/gpt-oss-120b regolo warming 100.00% 1499 ms 153 tok/s 1 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1499 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T00:02:59.000Z
moonshotai/kimi-k2.7-code inceptron warming 100.00% 1500 ms Not measured 0 samples, warming 44 with TTFT
More
Provider availability
100.00% (4 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
17441 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T04:03:42.000Z
qwen/qwen3-32b nscale warming 100.00% 1504 ms Not measured 0 samples, warming 44 with TTFT
More
Provider availability
100.00% (4 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1597 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T21:20:58.000Z
qwen/qwen3.8-27b pearl warming 100.00% 1504 ms Not measured 0 samples, warming 66 with TTFT
More
Provider availability
100.00% (6 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
5452 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:12:44.000Z
mistralai/codestral-2508 mistral warming 100.00% 1505 ms Not measured 0 samples, warming 55 with TTFT
More
Provider availability
100.00% (5 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3074 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:39:45.000Z
deepseek/deepseek-v4-flash-0731 io-net warming 100.00% 1512 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1512 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T12:28:15.000Z
qwen/qwen3.5-9b regolo warming 100.00% 1515 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1880 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T18:31:56.000Z
z-ai/glm-5.3-flash sail-research warming 80.00% 1515 ms Not measured 0 samples, warming 54 with TTFT
More
Provider availability
80.00% (5 samples)
Within deadline
80.00%
Capacity accepted
100.00%
p95 TTFT
15817 ms
Failure owner
provider: 1
Errors
TimeoutError: 1
Excluded from provider availability
None
Last seen
2026-09-15T19:39:43.000Z
z-ai/glm-5.3 makora warming 80.00% 1519 ms Not measured 0 samples, warming 54 with TTFT
More
Provider availability
80.00% (5 samples)
Within deadline
80.00%
Capacity accepted
100.00%
p95 TTFT
3174 ms
Failure owner
provider: 1
Errors
TimeoutError: 1
Excluded from provider availability
None
Last seen
2026-09-16T02:32:17.000Z
google/gemini-3-flash-preview google-vertex warming 100.00% 1521 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2871 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T22:07:41.000Z
qwen/qwen3.8-27b telnyx warming 100.00% 1523 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1523 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T00:42:40.000Z
z-ai/glm-5.2 morph warming 100.00% 1525 ms 15 tok/s 1 samples, warming 33 with TTFT
More
Provider availability
100.00% (3 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2027 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:46:39.000Z
nvidia/nemotron-3-nano-omni digitalocean warming 100.00% 1527 ms Not measured 0 samples, warming 33 with TTFT
More
Provider availability
100.00% (3 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3226 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T20:18:46.000Z
openai/o3 openai warming 100.00% 1527 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1527 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T22:15:43.000Z
moonshotai/kimi-k3 together warming 100.00% 1535 ms 95 tok/s 2 samples, warming 33 with TTFT
More
Provider availability
100.00% (3 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1585 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:11:50.000Z
openai/gpt-oss-20b io-net warming 100.00% 1537 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1537 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:03:41.000Z
deepseek/deepseek-v4-flash-0731 pearl warming 100.00% 1538 ms 152 tok/s 2 samples, warming 99 with TTFT
More
Provider availability
100.00% (9 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3526 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T02:35:35.000Z
z-ai/glm-5.3-flash wafer warming 100.00% 1539 ms Not measured 0 samples, warming 88 with TTFT
More
Provider availability
100.00% (8 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4061 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:30:44.000Z
deepseek/deepseek-v4-flash-0731 fireworks warming 100.00% 1541 ms 12 tok/s 1 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1541 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T22:20:31.000Z
z-ai/glm-5.1 io-net warming 100.00% 1547 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1547 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T06:00:38.000Z
z-ai/glm-5.3 akashml warming 100.00% 1548 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3058 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T09:04:20.000Z
meta-llama/llama-3.3-70b-instruct scaleway warming 100.00% 1557 ms Not measured 0 samples, warming 99 with TTFT
More
Provider availability
100.00% (9 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3053 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T02:47:17.000Z
mistralai/mistral-large mistral warming 100.00% 1561 ms Not measured 0 samples, warming 55 with TTFT
More
Provider availability
100.00% (5 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2406 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T17:39:46.000Z
google/gemini-3.5-flash-lite google-vertex warming 100.00% 1566 ms Not measured 0 samples, warming 33 with TTFT
More
Provider availability
100.00% (3 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3000 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:24:45.000Z
deepseek/deepseek-flash deepseek warming 100.00% 1570 ms Not measured 0 samples, warming 44 with TTFT
More
Provider availability
100.00% (4 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3309 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T20:45:40.000Z
swiss-ai/apertus-70b-instruct regolo warming 100.00% 1574 ms Not measured 0 samples, warming 44 with TTFT
More
Provider availability
100.00% (4 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2728 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T23:02:19.000Z
bytedance/doubao-seed-2.1-pro-260628 atlas-cloud warming 100.00% 1582 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1817 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T11:04:53.000Z
moonshotai/kimi-k2.6 fireworks warming 100.00% 1586 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1726 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T17:46:49.000Z
google/gemini-2.5-flash lightning warming 100.00% 1587 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1976 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T13:15:44.000Z
undi95/remm-slerp-l2-13b nextbit warming 100.00% 1589 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2965 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:03:43.000Z
z-ai/glm-5.2 scaleway warming 100.00% 1592 ms Not measured 0 samples, warming 33 with TTFT
More
Provider availability
100.00% (3 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4475 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:58:51.000Z
deepseek/deepseek-v4-pro-0813 fireworks warming 100.00% 1595 ms 59 tok/s 1 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1595 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T02:52:08.000Z
meituan-longcat/longcat-2.0 atlas-cloud warming 100.00% 1598 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1598 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:55:31.000Z
openai/gpt-4o openai warming 100.00% 1600 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1600 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T07:41:10.000Z
deepseek/deepseek-v4-flash-0731-fast wafer warming 100.00% 1610 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1944 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:10:24.000Z
meta-llama/llama-3.1-70b-instruct telnyx warming 100.00% 1612 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3554 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:50:44.000Z
minimax/minimax-m3 parasail warming 100.00% 1617 ms 156 tok/s 1 samples, warming 44 with TTFT
More
Provider availability
100.00% (4 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4837 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:41:57.000Z
z-ai/glm-5.3-flash friendli warming 100.00% 1621 ms Not measured 0 samples, warming 55 with TTFT
More
Provider availability
100.00% (5 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3782 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T21:06:55.000Z
lightning-ai/gpt-oss-20b lightning warming 100.00% 1626 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1626 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T04:18:45.000Z
moonshotai/kimi-k2.7-code wandb warming 100.00% 1628 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1888 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T16:03:54.000Z
minimax/minimax-m2.7 minimax warming 100.00% 1638 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3716 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T12:45:33.000Z
deepseek/deepseek-v4-flash-0731 sail-research warming 100.00% 1643 ms Not measured 0 samples, warming 33 with TTFT
More
Provider availability
100.00% (3 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2140 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:15:39.000Z
arcee-ai/trinity-large-thinking arcee warming 100.00% 1649 ms Not measured 0 samples, warming 55 with TTFT
More
Provider availability
100.00% (5 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4032 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:51:56.000Z
inclusionai/ling-3.0-flash-fin deepinfra warming 100.00% 1652 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1652 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T00:28:24.000Z
qwen/qwen3.5-397b-a17b digitalocean warming 100.00% 1655 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
5057 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T13:04:09.000Z
deepseek/deepseek-v3.1-terminus atlas-cloud warming 100.00% 1657 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1657 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T05:53:23.000Z
z-ai/glm-5.3-flash fireworks warming 100.00% 1658 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1658 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:12:41.000Z
moonshotai/kimi-k2.6 azure warming 100.00% 1663 ms 99 tok/s 1 samples, warming 44 with TTFT
More
Provider availability
100.00% (4 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3695 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:44:07.000Z
deepseek/deepseek-v4-flash makora warming 100.00% 1667 ms Not measured 0 samples, warming 44 with TTFT
More
Provider availability
100.00% (4 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3571 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T21:36:43.000Z
qwen/qwen3.8-27b novita warming 100.00% 1668 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1730 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:06:45.000Z
deepseek/deepseek-ocr atlas-cloud warming 100.00% 1673 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2983 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:40:31.000Z
qwen/qwen-plus-character alibaba warming 100.00% 1674 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1674 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T20:11:57.000Z
deepseek-ai/DeepSeek-V4-Pro nebius warming 100.00% 1675 ms Not measured 0 samples, warming 44 with TTFT
More
Provider availability
100.00% (4 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1831 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:17:32.000Z
meta-llama/llama-3.3-70b-instruct-fp8-fast cloudflare-workers-ai warming 100.00% 1680 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1984 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T00:00:42.000Z
google/gemma-4-26b-a4b-it scaleway warming 100.00% 1683 ms Not measured 0 samples, warming 44 with TTFT
More
Provider availability
100.00% (4 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2015 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:18:35.000Z
cohere/command-a azure warming 100.00% 1685 ms Not measured 0 samples, warming 44 with TTFT
More
Provider availability
100.00% (4 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3243 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T00:18:35.000Z
deepseek/deepseek-v4-flash-0731 scaleway warming 100.00% 1685 ms Not measured 0 samples, warming 55 with TTFT
More
Provider availability
100.00% (5 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4073 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T21:09:50.000Z
google/gemini-3.1-flash-lite google-ai-studio warming 100.00% 1685 ms Not measured 0 samples, warming 33 with TTFT
More
Provider availability
100.00% (3 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1820 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T02:06:45.000Z
deepseek/deepseek-v4-flash-vision-exp siliconflow warming 100.00% 1686 ms Not measured 0 samples, warming 33 with TTFT
More
Provider availability
100.00% (3 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3611 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T04:00:56.000Z
google/gemini-2.5-flash google-vertex warming 100.00% 1689 ms Not measured 0 samples, warming 52 with TTFT
More
Provider availability
100.00% (5 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3215 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:11:22.814Z
google/gemma-4-31b-it sail-research warming 100.00% 1691 ms 67 tok/s 1 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1691 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T02:42:50.000Z
deepseek/deepseek-v4.1-flash tinfoil warming 100.00% 1693 ms Not measured 0 samples, warming 43 with TTFT
More
Provider availability
100.00% (4 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2035 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:57:47.302Z
google/gemma-4-uncensored venice warming 100.00% 1697 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1697 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T22:54:52.000Z
mistralai/mistral-nemotron nvidia-nim warming 50.00% 1698 ms Not measured 0 samples, warming 21 with TTFT
More
Provider availability
50.00% (2 samples)
Within deadline
50.00%
Capacity accepted
100.00%
p95 TTFT
1698 ms
Failure owner
provider: 1
Errors
TimeoutError: 1
Excluded from provider availability
None
Last seen
2026-09-15T13:15:41.000Z
google/gemma-4-12b-it siliconflow warming 100.00% 1704 ms Not measured 0 samples, warming 4571 with TTFT
More
Provider availability
100.00% (457 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1704 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T20:20:36.000Z
qwen/qwen3.5-397b-a17b venice warming 100.00% 1705 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1705 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T02:05:20.000Z
google/gemini-3-flash-preview lightning warming 100.00% 1716 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2047 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T22:36:48.000Z
qwen/qwen3-next-80b-a3b-instruct parasail warming 100.00% 1717 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1717 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T15:51:05.000Z
z-ai/glm-5.1 telnyx warming 100.00% 1717 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2150 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T16:06:25.000Z
minimax/minimax-m2 minimax warming 100.00% 1721 ms Not measured 0 samples, warming 88 with TTFT
More
Provider availability
100.00% (8 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3521 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:57:52.000Z
z-ai/glm-5.3-flash tinfoil warming 83.33% 1734 ms Not measured 0 samples, warming 62 with TTFT
More
Provider availability
83.33% (6 samples)
Within deadline
66.67%
Capacity accepted
100.00%
p95 TTFT
2994 ms
Failure owner
provider: 1
Errors
provider_error: 1
Excluded from provider availability
None
Last seen
2026-09-16T03:21:00.183Z
moonshotai/kimi-k2.6 atlas-cloud warming 100.00% 1737 ms 42 tok/s 1 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1737 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T21:24:43.000Z
cerebras/gpt-oss-120b cerebras warming 100.00% 1739 ms 403 tok/s 1 samples, warming 99 with TTFT
More
Provider availability
100.00% (9 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3353 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:06:38.000Z
qwen/qwen3-235b-a22b-instruct-2507 nscale warming 100.00% 1739 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1824 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T02:01:47.000Z
z-ai/glm-5.3 sail-research warming 100.00% 1739 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3377 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T15:31:29.000Z
z-ai/glm-4.5-air zai warming 100.00% 1744 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3162 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T18:15:42.000Z
meta-llama/llama-3.1-8b-instruct databricks warming 100.00% 1746 ms Not measured 0 samples, warming 66 with TTFT
More
Provider availability
100.00% (6 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3767 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T19:27:18.000Z
qwen/qwen3.5-27b atlas-cloud warming 100.00% 1755 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1755 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T15:21:53.000Z
deepseek/deepseek-v4p1-flash fireworks warming 100.00% 1760 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1760 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T00:00:41.000Z
x-ai/grok-4.20-non-reasoning azure warming 100.00% 1762 ms Not measured 0 samples, warming 66 with TTFT
More
Provider availability
100.00% (6 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4024 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:39:51.000Z
x-ai/grok-4.6 atlas-cloud warming 100.00% 1766 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1766 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T13:55:36.000Z
openai/gpt-4o lightning warming 100.00% 1769 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1769 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T00:14:30.000Z
moonshotai/kimi-k2.6 deepinfra warming 100.00% 1770 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3158 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T22:45:39.000Z
google/gemma-4-31b-it friendli warming 100.00% 1771 ms 56 tok/s 1 samples, warming 88 with TTFT
More
Provider availability
100.00% (8 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4309 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:09:44.000Z
sao10k/l3-8b-lunaris novita warming 100.00% 1774 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1774 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T12:42:17.000Z
qwen/qwen3.8-27b engy warming 100.00% 1778 ms Not measured 0 samples, warming 77 with TTFT
More
Provider availability
100.00% (7 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3856 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T23:09:25.000Z
qwen/qwen3.6-35b-a3b engy warming 100.00% 1786 ms Not measured 0 samples, warming 55 with TTFT
More
Provider availability
100.00% (5 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3056 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T22:50:15.000Z
qwen/qwen3-vl-235b-a22b-instruct alibaba warming 100.00% 1788 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1788 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T15:31:26.000Z
x-ai/grok-4.1-fast-non-reasoning azure warming 100.00% 1788 ms Not measured 0 samples, warming 33 with TTFT
More
Provider availability
100.00% (3 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3675 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T17:33:46.000Z
x-ai/grok-4.1-fast-reasoning azure warming 100.00% 1789 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2215 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T05:31:28.000Z
thedrummer/unslopnemo-12b-v4.1 nextbit warming 100.00% 1792 ms Not measured 0 samples, warming 33 with TTFT
More
Provider availability
100.00% (3 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3372 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T20:27:41.000Z
google/gemini-3.5-flash google-vertex warming 100.00% 1795 ms 58 tok/s 2 samples, warming 33 with TTFT
More
Provider availability
100.00% (3 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3657 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T23:15:41.000Z
openai/gpt-5.4-mini openai warming 100.00% 1798 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1798 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T10:34:35.000Z
openai/gpt-5.2 openai warming 100.00% 1800 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1800 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T02:21:43.000Z
deepseek/deepseek-v4-flash-vision-exp fireworks warming 100.00% 1804 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1804 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T15:52:39.000Z
qwen/qwen3.8-flash-next featherless warming 100.00% 1808 ms Not measured 0 samples, warming 66 with TTFT
More
Provider availability
100.00% (6 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3879 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:57:46.000Z
minimax/minimax-m2.1-highspeed minimax warming 100.00% 1813 ms Not measured 0 samples, warming 33 with TTFT
More
Provider availability
100.00% (3 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4137 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T21:48:47.000Z
z-ai/glm-5.3 engy warming 100.00% 1813 ms Not measured 0 samples, warming 55 with TTFT
More
Provider availability
100.00% (5 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2262 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T02:42:54.000Z
openai/gpt-3.5-turbo-0125 openai warming 100.00% 1819 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1819 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T12:12:52.000Z
thinkingmachines/inkling-small thinkingmachines warming 100.00% 1819 ms Not measured 0 samples, warming 66 with TTFT
More
Provider availability
100.00% (6 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3672 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T02:32:17.000Z
minimax/minimax-m2.7 morph warming 50.00% 1836 ms Not measured 0 samples, warming 42 with TTFT
More
Provider availability
50.00% (4 samples)
Within deadline
50.00%
Capacity accepted
75.00%
p95 TTFT
7111 ms
Failure owner
provider: 2
Errors
TimeoutError: 1, provider_error: 1
Excluded from provider availability
None
Last seen
2026-09-16T02:19:15.000Z
deepseek/deepseek-v4-flash-0731 telnyx warming 100.00% 1837 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1837 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T10:48:47.000Z
moonshotai/kimi-k2.6 telnyx warming 100.00% 1838 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1838 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T16:38:31.000Z
deepseek/deepseek-v4.1-flash featherless warming 100.00% 1841 ms Not measured 0 samples, warming 44 with TTFT
More
Provider availability
100.00% (4 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4210 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T22:33:44.000Z
openai/gpt-oss-120b io-net warming 100.00% 1851 ms 140 tok/s 2 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1851 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T18:22:54.000Z
openai/o3-mini openai warming 100.00% 1852 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4644 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T18:36:50.000Z
deepseek/deepseek-v4-pro-0423 deepinfra warming 100.00% 1854 ms 122 tok/s 2 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1854 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T02:32:14.000Z
google/gemma-4-26b-a4b-it nextbit warming 100.00% 1868 ms Not measured 0 samples, warming 33 with TTFT
More
Provider availability
100.00% (3 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
10076 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:35:38.000Z
moonshotai/kimi-k3 engy warming 100.00% 1868 ms 109 tok/s 1 samples, warming 33 with TTFT
More
Provider availability
100.00% (3 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3886 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:36:57.000Z
deepseek/deepseek-v4-flash-vision-exp deepseek warming 100.00% 1869 ms Not measured 0 samples, warming 44 with TTFT
More
Provider availability
100.00% (4 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3921 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T17:57:42.000Z
moonshotai/kimi-k2.6 inceptron warming 100.00% 1869 ms Not measured 0 samples, warming 66 with TTFT
More
Provider availability
100.00% (6 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
6430 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:35:38.000Z
tencent/hunyuan-a13b-instruct siliconflow warming 100.00% 1870 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1870 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T17:48:02.000Z
qwen/qwen3.5-122b-a10b alibaba warming 100.00% 1874 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1874 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T06:21:45.000Z
google/gemma-4-26b-a4b-it makora warming 100.00% 1882 ms Not measured 0 samples, warming 66 with TTFT
More
Provider availability
100.00% (6 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
6562 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:57:48.000Z
moonshotai/kimi-k3 makora warming 33.33% 1897 ms 13 tok/s 1 samples, warming 31 with TTFT
More
Provider availability
33.33% (3 samples)
Within deadline
33.33%
Capacity accepted
100.00%
p95 TTFT
1897 ms
Failure owner
provider: 2
Errors
TimeoutError: 2
Excluded from provider availability
None
Last seen
2026-09-15T22:52:10.000Z
moonshotai/kimi-k2.6 wafer warming 100.00% 1913 ms Not measured 0 samples, warming 77 with TTFT
More
Provider availability
100.00% (7 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3663 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:06:46.000Z
qwen/qwen3.5-plus alibaba warming 100.00% 1925 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4225 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T14:36:43.000Z
moonshotai/kimi-k3-fast fireworks warming 100.00% 1949 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1949 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T18:42:40.000Z
openai/gpt-oss-20b nscale warming 100.00% 1950 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3297 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T23:42:51.000Z
google/gemini-3.7-flash google-vertex warming 100.00% 1956 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4743 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:30:41.000Z
qwen/qwen3.5-122b-a10b regolo warming 100.00% 1965 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3057 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T02:28:47.000Z
aion-labs/aion-rp-llama-3.1-8b aion-labs warming 100.00% 1968 ms Not measured 0 samples, warming 44 with TTFT
More
Provider availability
100.00% (4 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3263 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:51:45.000Z
moonshotai/kimi-k2-7-code venice warming 100.00% 1972 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1972 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T00:34:29.000Z
google/gemini-3.8-flash google-ai-studio warming 100.00% 1974 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2653 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:24:43.000Z
qwen/qwen3.5-27b novita warming 100.00% 1975 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1975 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T08:36:48.000Z
qwen/qwen3-32b alibaba warming 100.00% 1982 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2089 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T23:55:59.000Z
zai-org/glm-5 novita warming 100.00% 1983 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1983 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T20:30:52.000Z
z-ai/glm-5.2 parasail warming 100.00% 1992 ms 138 tok/s 2 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
1992 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:51:40.000Z
qwen/qwen3.6-27b morph warming 42.86% 1994 ms Not measured 0 samples, warming 73 with TTFT
More
Provider availability
42.86% (7 samples)
Within deadline
42.86%
Capacity accepted
71.43%
p95 TTFT
2775 ms
Failure owner
provider: 4
Errors
TimeoutError: 2, provider_error: 2
Excluded from provider availability
None
Last seen
2026-09-16T01:55:32.000Z
moonshotai/kimi-k2.7-code-highspeed kimi warming 100.00% 1998 ms Not measured 0 samples, warming 77 with TTFT
More
Provider availability
100.00% (7 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3683 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T23:02:18.000Z
moonshotai/kimi-k3 venice warming 100.00% 2002 ms 86 tok/s 2 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2002 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:17:37.000Z
openai/gpt-4 lightning warming 100.00% 2003 ms Not measured 0 samples, warming 33 with TTFT
More
Provider availability
100.00% (3 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4043 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T19:42:43.000Z
bytedance/doubao-seed-1.6-251015 atlas-cloud warming 100.00% 2008 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2008 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T15:54:48.000Z
minimax/minimax-m3 minimax warming 100.00% 2010 ms 153 tok/s 2 samples, warming 66 with TTFT
More
Provider availability
100.00% (6 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4246 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T02:30:40.000Z
qwen/qwen3-235b-a22b nscale warming 100.00% 2014 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2303 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T22:06:50.000Z
qwen/qwen3.7-max-2026-05-20 alibaba warming 100.00% 2015 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2015 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T20:51:45.000Z
meta-llama/llama-4-maverick digitalocean warming 100.00% 2018 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2018 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T18:20:50.000Z
moonshotai/kimi-k2.5 telnyx warming 100.00% 2020 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2724 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T17:45:44.000Z
nvidia/nemotron-3-nano-30b-a3b novita warming 100.00% 2022 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2022 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T02:45:39.000Z
z-ai/glm-4.7 io-net warming 100.00% 2023 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2023 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T13:58:02.000Z
deepseek/deepseek-v3.2 deepinfra warming 100.00% 2025 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2025 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T18:39:50.000Z
z-ai/glm-5.2 engy warming 100.00% 2025 ms 36 tok/s 1 samples, warming 44 with TTFT
More
Provider availability
100.00% (4 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2426 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T02:24:04.000Z
z-ai/glm-5.2 regolo warming 100.00% 2030 ms 45 tok/s 1 samples, warming 66 with TTFT
More
Provider availability
100.00% (6 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
18410 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T02:50:31.000Z
google/gemini-3-flash-preview google-ai-studio warming 100.00% 2032 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2032 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T22:39:47.000Z
deepseek/deepseek-v3.2 sambanova warming 75.00% 2042 ms Not measured 0 samples, warming 43 with TTFT
More
Provider availability
75.00% (4 samples)
Within deadline
75.00%
Capacity accepted
100.00%
p95 TTFT
13318 ms
Failure owner
provider: 1
Errors
provider_error: 1
Excluded from provider availability
None
Last seen
2026-09-15T20:09:47.000Z
moonshotai/kimi-k3 sail-research warming 100.00% 2046 ms Not measured 0 samples, warming 88 with TTFT
More
Provider availability
100.00% (8 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4139 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:50:46.000Z
openai/gpt-oss-20b databricks warming 100.00% 2050 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2050 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T22:09:43.000Z
openai/gpt-oss-120b databricks warming 100.00% 2052 ms Not measured 0 samples, warming 66 with TTFT
More
Provider availability
100.00% (6 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4046 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:09:46.000Z
qwen/qwen3-next-80b venice warming 100.00% 2058 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2058 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T07:54:41.000Z
qwen/qwen3-235b-a22b-instruct-2507 alibaba warming 100.00% 2074 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2074 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T11:35:35.000Z
z-ai/glm-4.7 mancer warming 87.50% 2075 ms Not measured 0 samples, warming 87 with TTFT
More
Provider availability
87.50% (8 samples)
Within deadline
87.50%
Capacity accepted
100.00%
p95 TTFT
6866 ms
Failure owner
provider: 1
Errors
TimeoutError: 1
Excluded from provider availability
None
Last seen
2026-09-16T02:13:31.000Z
anthropic/claude-sonnet-4.5 anthropic warming 100.00% 2078 ms Not measured 0 samples, warming 461 with TTFT
More
Provider availability
100.00% (46 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2078 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T20:46:33.000Z
deepseek/deepseek-v4-pro parasail warming 66.67% 2084 ms Not measured 0 samples, warming 32 with TTFT
More
Provider availability
66.67% (3 samples)
Within deadline
66.67%
Capacity accepted
66.67%
p95 TTFT
4161 ms
Failure owner
provider: 1
Errors
provider_error: 1
Excluded from provider availability
None
Last seen
2026-09-15T19:07:06.000Z
xiaomi/mimo-v2.5 featherless warming 1 excluded 100.00% 2091 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2091 ms
Failure owner
None
Errors
None
Excluded from provider availability
probe_config_error: 1
Last seen
2026-09-15T20:04:35.000Z
qwen/qwen3-vl-235b-a22b-thinking novita warming 100.00% 2096 ms Not measured 0 samples, warming 33 with TTFT
More
Provider availability
100.00% (3 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3587 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T17:08:05.000Z
qwen/qwen3.8-27b regolo warming 100.00% 2096 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2096 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T12:49:50.000Z
qwen/qwen3-vl-30b-a3b-instruct alibaba warming 100.00% 2116 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2116 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T14:36:31.000Z
deepseek/deepseek-v4-flash-0731 deepinfra warming 100.00% 2117 ms Not measured 0 samples, warming 94 with TTFT
More
Provider availability
100.00% (9 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2899 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T04:12:13.872Z
z-ai/glm-5.3 thinkingmachines warming 100.00% 2117 ms Not measured 0 samples, warming 66 with TTFT
More
Provider availability
100.00% (6 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3919 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T22:32:06.000Z
meta-llama/llama-3.2-3b venice warming 100.00% 2126 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
16644 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T19:31:40.000Z
moonshotai/kimi-k3 io-net warming 100.00% 2147 ms 150 tok/s 2 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2147 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T04:06:38.000Z
google/gemma-4-31b-it siliconflow warming 100.00% 2154 ms 21 tok/s 1 samples, warming 61 with TTFT
More
Provider availability
100.00% (6 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2154 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:54:15.219Z
deepseek/deepseek-v4-flash mancer warming 100.00% 2159 ms 156 tok/s 1 samples, warming 66 with TTFT
More
Provider availability
100.00% (6 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4342 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:20:40.000Z
anthropic/claude-sonnet-4.6 anthropic warming 100.00% 2160 ms Not measured 0 samples, warming 44 with TTFT
More
Provider availability
100.00% (4 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2629 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T22:27:48.000Z
nvidia/nemotron-3-super-120b-a12b deepinfra warming 100.00% 2162 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2162 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T18:24:39.000Z
qwen/qwen3.7-flash-2026-07-15 alibaba warming 100.00% 2165 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3296 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:27:43.000Z
openai/gpt-4-turbo lightning warming 100.00% 2198 ms Not measured 0 samples, warming 33 with TTFT
More
Provider availability
100.00% (3 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
6077 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T23:18:44.000Z
moonshotai/kimi-k2.5 alibaba warming 100.00% 2201 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2201 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T15:39:45.000Z
deepseek/deepseek-v4-flash-0731 alibaba warming 100.00% 2212 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2611 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T00:46:30.000Z
qwen/qwen3.8-27b akashml warming 100.00% 2226 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4775 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T02:24:46.000Z
google/gemini-3.1-flash-lite deepinfra warming 100.00% 2229 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2229 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:21:46.000Z
qwen/qwen3-vl-plus-2025-09-23 alibaba warming 100.00% 2247 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2247 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T18:54:36.000Z
qwen/qwen3-coder-plus alibaba warming 100.00% 2248 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2248 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T11:45:43.000Z
z-ai/glm-5.2 wandb warming 100.00% 2258 ms 150 tok/s 1 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2448 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T00:41:50.000Z
openai/gpt-oss-120b scaleway warming 100.00% 2262 ms 77 tok/s 1 samples, warming 33 with TTFT
More
Provider availability
100.00% (3 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3774 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T18:28:16.000Z
openai/gpt-oss-20b akashml warming 100.00% 2265 ms Not measured 0 samples, warming 66 with TTFT
More
Provider availability
100.00% (6 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
5033 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T04:03:45.000Z
deepseek/deepseek-v4-pro siliconflow warming 100.00% 2268 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2268 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T10:57:39.000Z
google/gemini-3.5-flash lightning warming 100.00% 2269 ms 35 tok/s 1 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2269 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T00:42:44.000Z
z-ai/glm-4.5v zai warming 100.00% 2280 ms Not measured 0 samples, warming 33 with TTFT
More
Provider availability
100.00% (3 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
12375 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T19:12:43.000Z
openai/gpt-5-nano openai warming 100.00% 2288 ms Not measured 0 samples, warming 131 with TTFT
More
Provider availability
100.00% (13 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2288 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T22:10:53.792Z
qwen/qwen3.5-35b-a3b wandb warming 100.00% 2298 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3907 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T08:06:58.000Z
qwen/qwen3-vl-32b-instruct alibaba warming 100.00% 2307 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
7370 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T13:32:24.000Z
anthropic/claude-opus-4.8 anthropic warming 100.00% 2308 ms Not measured 0 samples, warming 33 with TTFT
More
Provider availability
100.00% (3 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2391 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T18:54:43.000Z
openai/gpt-oss-120b siliconflow warming 100.00% 2308 ms 73 tok/s 1 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2308 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T23:41:41.000Z
deepseek/deepseek-v4-pro deepseek warming 100.00% 2347 ms Not measured 0 samples, warming 55 with TTFT
More
Provider availability
100.00% (5 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4371 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:50:37.000Z
qwen/qwen-3-6-plus venice warming 100.00% 2382 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4437 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T21:21:56.000Z
deepseek/deepseek-v3.2 novita warming 100.00% 2410 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2410 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T07:24:45.000Z
deepseek/deepseek-v4-flash-0731 nextbit warming 100.00% 2415 ms 124 tok/s 1 samples, warming 33 with TTFT
More
Provider availability
100.00% (3 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4113 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T23:24:47.000Z
openai/gpt-oss-120b akashml warming 100.00% 2421 ms Not measured 0 samples, warming 55 with TTFT
More
Provider availability
100.00% (5 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
6777 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T23:27:43.000Z
z-ai/glm-5.3-flash featherless warming 100.00% 2424 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2792 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T04:02:02.000Z
minimax/minimax-m2.5-highspeed minimax warming 100.00% 2437 ms Not measured 0 samples, warming 55 with TTFT
More
Provider availability
100.00% (5 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4396 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T14:39:51.000Z
moonshotai/kimi-k3 nebius warming 100.00% 2443 ms Not measured 0 samples, warming 33 with TTFT
More
Provider availability
100.00% (3 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
5676 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:10:28.000Z
deepseek/deepseek-v4-flash-0731 siliconflow warming 100.00% 2456 ms Not measured 0 samples, warming 33 with TTFT
More
Provider availability
100.00% (3 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4365 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T22:41:05.000Z
z-ai/glm-5.3-flash pearl warming 100.00% 2461 ms Not measured 0 samples, warming 77 with TTFT
More
Provider availability
100.00% (7 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
5014 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T00:15:42.000Z
qwen/qwen3.8-max novita warming 100.00% 2466 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2466 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T02:15:42.000Z
openai/gpt-oss-20b regolo warming 100.00% 2469 ms Not measured 0 samples, warming 33 with TTFT
More
Provider availability
100.00% (3 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3109 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:18:37.000Z
google/gemini-3.1-flash-lite google-vertex warming 100.00% 2489 ms Not measured 0 samples, warming 55 with TTFT
More
Provider availability
100.00% (5 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3620 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:48:42.000Z
z-ai/glm-5.3-flash makora warming 1 excluded 100.00% 2498 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4064 ms
Failure owner
None
Errors
None
Excluded from provider availability
unsupported_route: 1
Last seen
2026-09-15T19:33:37.000Z
z-ai/glm-5.2 gmi warming 100.00% 2509 ms Not measured 0 samples, warming 55 with TTFT
More
Provider availability
100.00% (5 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4787 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T22:18:28.000Z
moonshotai/kimi-k2.5 nscale warming 100.00% 2528 ms Not measured 0 samples, warming 44 with TTFT
More
Provider availability
100.00% (4 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4002 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T02:27:45.000Z
anthropic/claude-opus-4.6 anthropic warming 100.00% 2534 ms Not measured 0 samples, warming 201 with TTFT
More
Provider availability
100.00% (20 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2534 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T21:32:13.589Z
moonshotai/kimi-k3 phala warming 100.00% 2545 ms 33 tok/s 1 samples, warming 66 with TTFT
More
Provider availability
100.00% (6 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4076 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:27:08.000Z
anthropic/claude-opus-5 anthropic warming 100.00% 2560 ms 74 tok/s 1 samples, warming 252 with TTFT
More
Provider availability
100.00% (25 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4011 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:50:44.000Z
qwen/qwen3.5-122b-a10b databricks warming 100.00% 2575 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3034 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T02:00:47.000Z
deepseek/deepseek-v4-flash-0731 featherless warming 100.00% 2593 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3647 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T22:30:43.000Z
qwen/qwen3.5-9b together warming 100.00% 2594 ms Not measured 0 samples, warming 44 with TTFT
More
Provider availability
100.00% (4 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
6525 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T15:56:28.000Z
z-ai/glm-5.1 gmi warming 100.00% 2611 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2672 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T04:12:45.000Z
z-ai/glm-5.2 inceptron warming 100.00% 2618 ms 58 tok/s 1 samples, warming 44 with TTFT
More
Provider availability
100.00% (4 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
9565 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:33:56.000Z
z-ai/glm-5.3 atlas-cloud warming 100.00% 2650 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2650 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T04:10:08.000Z
z-ai/glm-5.3 pearl warming 100.00% 2653 ms Not measured 0 samples, warming 55 with TTFT
More
Provider availability
100.00% (5 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3248 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T00:08:22.000Z
moonshotai/kimi-k2.6 wandb warming 100.00% 2659 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2659 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T16:27:31.000Z
qwen/qwq-32b cloudflare-workers-ai warming 100.00% 2667 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2667 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T04:27:43.000Z
qwen/qwen3-235b-a22b telnyx warming 100.00% 2668 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2668 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T23:48:46.000Z
thinkingmachines/inkling thinkingmachines warming 100.00% 2681 ms 79 tok/s 1 samples, warming 88 with TTFT
More
Provider availability
100.00% (8 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4986 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T00:52:08.000Z
qwen/qwen3.8-27b cloudflare-workers-ai warming 100.00% 2683 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2683 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T13:54:51.000Z
z-ai/glm-5v-turbo zai warming 100.00% 2703 ms Not measured 0 samples, warming 33 with TTFT
More
Provider availability
100.00% (3 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2810 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:40:31.000Z
z-ai/glm-5.2 together warming 100.00% 2706 ms 77 tok/s 1 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2706 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T00:24:18.000Z
upstage/solar-pro4 upstage warming 100.00% 2709 ms 87 tok/s 2 samples, warming 77 with TTFT
More
Provider availability
100.00% (7 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4461 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T02:18:45.000Z
zero-g/0gm-1.0-35b-a3b zero-g warming 100.00% 2721 ms Not measured 0 samples, warming 55 with TTFT
More
Provider availability
100.00% (5 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3753 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T13:26:43.000Z
qwen/qwen2.5-coder-32b-instruct cloudflare-workers-ai warming 100.00% 2728 ms Not measured 0 samples, warming 33 with TTFT
More
Provider availability
100.00% (3 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2732 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T02:51:51.000Z
qwen/qwen3-coder-next parasail warming 100.00% 2734 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2734 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T21:45:39.000Z
ibm-granite/granite-4.0-h-micro cloudflare-workers-ai warming 100.00% 2745 ms Not measured 0 samples, warming 33 with TTFT
More
Provider availability
100.00% (3 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3260 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T02:17:05.000Z
google/gemini-3.1-pro-preview lightning warming 100.00% 2757 ms 47 tok/s 2 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3499 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:50:42.000Z
deepseek/deepseek-v4-pro alibaba warming 100.00% 2765 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2765 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T16:54:49.000Z
meta-llama/llama-3.3-70b-instruct wandb warming 100.00% 2767 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2767 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T14:06:51.000Z
z-ai/glm-5.1 siliconflow warming 100.00% 2770 ms Not measured 0 samples, warming 33 with TTFT
More
Provider availability
100.00% (3 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4397 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T12:53:00.000Z
google/gemma-3-4b-it deepinfra warming 100.00% 2777 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
15757 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T00:39:51.000Z
mistralai/pixtral-12b-2409 scaleway warming 100.00% 2781 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2781 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T06:30:43.000Z
moonshotai/Kimi-K2.6 nebius warming 100.00% 2786 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3874 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:36:53.000Z
moonshotai/kimi-k3 arcee warming 100.00% 2796 ms 40 tok/s 1 samples, warming 66 with TTFT
More
Provider availability
100.00% (6 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
6347 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T04:12:40.000Z
stepfun/step-3.7-flash stepfun warming 100.00% 2811 ms 129 tok/s 2 samples, warming 99 with TTFT
More
Provider availability
100.00% (9 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
6532 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:12:13.000Z
gryphe/mythomax-l2-13b nextbit warming 100.00% 2823 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3696 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T15:59:03.000Z
qwen/qwen3-coder-next regolo warming 100.00% 2838 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2838 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T20:12:52.000Z
z-ai/glm-5.3 fireworks warming 100.00% 2841 ms Not measured 0 samples, warming 55 with TTFT
More
Provider availability
100.00% (5 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3028 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:45:45.000Z
openai/gpt-oss-120b wandb warming 100.00% 2858 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2858 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T18:48:46.000Z
z-ai/glm-4.7 venice warming 100.00% 2865 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2865 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T19:07:02.000Z
qwen/qwen3-vl-plus alibaba warming 100.00% 2866 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2866 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T11:21:43.000Z
deepseek/deepseek-v4-pro gmi warming 100.00% 2878 ms Not measured 0 samples, warming 66 with TTFT
More
Provider availability
100.00% (6 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4985 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T23:27:40.000Z
x-ai/grok-4.5 grok warming 100.00% 2890 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3468 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:14:07.000Z
sao10k/l3-8b-lunaris-v1-turbo deepinfra warming 100.00% 2916 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3621 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T17:24:58.000Z
qwen/qwen3.5-flash atlas-cloud warming 100.00% 2926 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2926 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T19:51:49.000Z
google/gemma-4-31b-it parasail warming 100.00% 2932 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2932 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T13:09:23.000Z
qwen/qwen3.6-27b io-net warming 100.00% 2936 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2936 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T18:57:46.000Z
qwen/qwen3.8-max deepinfra warming 100.00% 2936 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2936 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T22:42:47.000Z
morph/morph-v3-large morph warming 100.00% 2945 ms Not measured 0 samples, warming 55 with TTFT
More
Provider availability
100.00% (5 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3782 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:44:07.000Z
bytedance/doubao-seed-2.0-lite-260428 atlas-cloud warming 100.00% 2961 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2961 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T09:33:44.000Z
qwen/qwen-3-7-max venice warming 100.00% 2961 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2961 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:51:49.000Z
deepseek/deepseek-v4-pro-0423 siliconflow warming 100.00% 2978 ms 69 tok/s 2 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
2978 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T02:26:50.000Z
qwen/qwen3-4b-instruct-2507 nscale warming 100.00% 2988 ms Not measured 0 samples, warming 65 with TTFT
More
Provider availability
100.00% (6 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3815 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:29:45.393Z
qwen/qwen3.8-2.4t-a95b siliconflow warming 100.00% 2996 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3083 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T22:20:31.000Z
qwen/qwen3-max-2025-09-23 alibaba warming 100.00% 3002 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3449 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T13:53:09.000Z
z-ai/glm-5.1 phala warming 66.67% 3003 ms Not measured 0 samples, warming 32 with TTFT
More
Provider availability
66.67% (3 samples)
Within deadline
66.67%
Capacity accepted
100.00%
p95 TTFT
3329 ms
Failure owner
provider: 1
Errors
TimeoutError: 1
Excluded from provider availability
None
Last seen
2026-09-16T02:21:48.000Z
google/gemma-4-31b-it sambanova warming 75.00% 3015 ms Not measured 0 samples, warming 43 with TTFT
More
Provider availability
75.00% (4 samples)
Within deadline
75.00%
Capacity accepted
100.00%
p95 TTFT
19308 ms
Failure owner
provider: 1
Errors
provider_error: 1
Excluded from provider availability
None
Last seen
2026-09-16T03:57:55.000Z
qwen/qwen3.6-flash-2026-04-16 alibaba warming 100.00% 3048 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3048 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T22:18:45.000Z
nvidia/nemotron-3-nano-omni-30b-a3b-reasoning nvidia-nim warming 33.33% 3056 ms Not measured 0 samples, warming 31 with TTFT
More
Provider availability
33.33% (3 samples)
Within deadline
33.33%
Capacity accepted
100.00%
p95 TTFT
3056 ms
Failure owner
provider: 2
Errors
empty_stream: 2
Excluded from provider availability
None
Last seen
2026-09-16T00:56:58.000Z
qwen/qwen3-30b-a3b-instruct-2507 wandb warming 100.00% 3062 ms Not measured 0 samples, warming 44 with TTFT
More
Provider availability
100.00% (4 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3847 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T16:57:42.000Z
meta-llama/llama-4-maverick-17b-128e-instruct-fp8 io-net warming 100.00% 3065 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3065 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T11:50:45.000Z
openai/gpt-5-mini openai warming 100.00% 3071 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3633 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T19:55:38.000Z
tencent/hy3 deepinfra warming 100.00% 3072 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3072 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T08:21:52.000Z
google/gemma-4-26b-a4b-it novita warming 100.00% 3080 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3080 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T05:33:45.000Z
scaledown/summarize scaledown warming 100.00% 3086 ms Not measured 0 samples, warming 87 with TTFT
More
Provider availability
100.00% (8 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
6241 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:38:40.226Z
aisingapore/gemma-sea-lion-v4-27b-it cloudflare-workers-ai warming 100.00% 3095 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3095 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T18:39:50.000Z
sao10k/l3.1-70b-euryale-v2.2 deepinfra warming 100.00% 3095 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3095 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T08:48:54.000Z
qwen/qwen3.8-27b cerebras warming 100.00% 3113 ms Not measured 0 samples, warming 33 with TTFT
More
Provider availability
100.00% (3 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
5386 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T15:11:49.000Z
z-ai/glm-5.3 friendli warming 100.00% 3116 ms Not measured 0 samples, warming 55 with TTFT
More
Provider availability
100.00% (5 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
14091 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T21:07:45.000Z
openai/gpt-oss-20b nvidia-nim warming 100.00% 3119 ms Not measured 0 samples, warming 44 with TTFT
More
Provider availability
100.00% (4 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
18949 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:05:28.000Z
nvidia/nemotron-3-ultra-550b digitalocean warming 100.00% 3145 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3145 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T17:48:51.000Z
deepseek/deepseek-v4-flash-0731 engy warming 100.00% 3153 ms Not measured 0 samples, warming 55 with TTFT
More
Provider availability
100.00% (5 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
5648 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:15:45.000Z
openai/gpt-5.6-terra atlas-cloud warming 100.00% 3176 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3176 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T15:12:53.000Z
meta-llama/llama-3.3-70b venice warming 100.00% 3182 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3182 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T10:29:56.000Z
qwen/qwen3-14b nextbit warming 100.00% 3196 ms Not measured 0 samples, warming 55 with TTFT
More
Provider availability
100.00% (5 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4146 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T21:51:45.000Z
qwen/qwen3.8-2.4t-a95b together warming 100.00% 3209 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3209 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T12:51:47.000Z
qwen/qwen3-30b-a3b alibaba warming 100.00% 3212 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3212 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T06:42:07.000Z
qwen/qwen-flash alibaba warming 100.00% 3218 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3218 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T02:33:44.000Z
meta-llama/llama-3.3-70b-instruct io-net warming 100.00% 3224 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3224 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T08:48:48.000Z
NousResearch/Hermes-4-405B nebius warming 100.00% 3230 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3230 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T11:41:52.000Z
x-ai/grok-4.3 grok warming 100.00% 3241 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3241 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T06:18:47.000Z
moonshotai/kimi-k2.7-code kimi warming 100.00% 3258 ms Not measured 0 samples, warming 55 with TTFT
More
Provider availability
100.00% (5 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4216 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:17:34.000Z
z-ai/glm-5.3 zero-g warming 100.00% 3260 ms 93 tok/s 2 samples, warming 88 with TTFT
More
Provider availability
100.00% (8 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
6206 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T00:57:52.000Z
openai/gpt-4o-mini openai warming 100.00% 3282 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3282 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T23:39:39.000Z
qwen/qwen-vl-ocr alibaba warming 100.00% 3283 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3283 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T07:47:21.000Z
thinkingmachines/inkling together warming 100.00% 3289 ms Not measured 0 samples, warming 33 with TTFT
More
Provider availability
100.00% (3 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4689 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T02:50:27.000Z
qwen/qwen3.6-27b deepinfra warming 100.00% 3306 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3306 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T17:25:02.000Z
qwen/qwen3.8-flash-next pearl warming 100.00% 3308 ms Not measured 0 samples, warming 55 with TTFT
More
Provider availability
100.00% (5 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3615 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T17:45:47.000Z
minimax/minimax-m3 featherless warming 100.00% 3316 ms 172 tok/s 2 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3316 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T02:01:44.000Z
openai/gpt-4-0613 openai warming 100.00% 3329 ms Not measured 0 samples, warming 33 with TTFT
More
Provider availability
100.00% (3 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4050 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T00:06:01.000Z
mistralai/mistral-small-3.2-24b-instruct-2506 scaleway warming 100.00% 3343 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3343 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T14:57:07.000Z
qwen/qwen3.6-35b-a3b io-net warming 100.00% 3346 ms Not measured 0 samples, warming 33 with TTFT
More
Provider availability
100.00% (3 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3460 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:31:40.000Z
qwen/qwen3.6-35b-a3b scaleway warming 100.00% 3356 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3885 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T04:09:42.000Z
google/gemma-2b-it telnyx warming 100.00% 3363 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3363 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T08:15:16.000Z
openai/gpt-5.6-terra openai warming 100.00% 3367 ms Not measured 0 samples, warming 55 with TTFT
More
Provider availability
100.00% (5 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4224 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T20:57:43.000Z
deepseek/deepseek-v3.1 sambanova warming 100.00% 3376 ms Not measured 0 samples, warming 44 with TTFT
More
Provider availability
100.00% (4 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4501 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:14:01.000Z
z-ai/glm-5 venice warming 100.00% 3380 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3380 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T06:01:44.000Z
meta-llama/llama-3.3-70b-instruct akashml warming 100.00% 3381 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3381 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T00:09:42.000Z
nvidia/nemotron-3-ultra-550b-a55b wandb warming 100.00% 3389 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3389 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T21:21:48.000Z
scaledown/classify scaledown warming 1 excluded 100.00% 3400 ms Not measured 0 samples, warming 88 with TTFT
More
Provider availability
100.00% (8 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
7732 ms
Failure owner
None
Errors
None
Excluded from provider availability
provider_error: 1
Last seen
2026-09-16T00:03:47.000Z
google/gemini-3.1-pro-preview google-vertex warming 100.00% 3451 ms 36 tok/s 1 samples, warming 44 with TTFT
More
Provider availability
100.00% (4 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
5269 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T23:57:43.000Z
qwen/qwen3.6-plus alibaba warming 100.00% 3455 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3455 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T09:12:47.000Z
nvidia/nemotron-3-120b-a12b cloudflare-workers-ai warming 100.00% 3456 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3456 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T17:33:30.000Z
google/gemma-3-12b-it databricks warming 100.00% 3467 ms Not measured 0 samples, warming 55 with TTFT
More
Provider availability
100.00% (5 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3917 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T22:25:56.000Z
moonshotai/kimi-k2.5 novita warming 100.00% 3475 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3475 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T20:12:57.000Z
z-ai/glm-5.2 atlas-cloud warming 100.00% 3480 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3480 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:02:55.000Z
meta-llama/llama-4-maverick databricks warming 100.00% 3483 ms Not measured 0 samples, warming 33 with TTFT
More
Provider availability
100.00% (3 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3881 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T02:48:48.000Z
moonshotai/kimi-k2-instruct-0905 io-net warming 100.00% 3485 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3485 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T09:09:58.000Z
minimax/minimax-m2.7-highspeed minimax warming 100.00% 3511 ms Not measured 0 samples, warming 55 with TTFT
More
Provider availability
100.00% (5 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4534 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:33:46.000Z
z-ai/glm-5.3 io-net warming 100.00% 3523 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3523 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T08:06:52.000Z
qwen/qwen2.5-coder-3b-instruct nscale warming 100.00% 3534 ms Not measured 0 samples, warming 41 with TTFT
More
Provider availability
100.00% (4 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3534 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:30:45.052Z
z-ai/glm-5.2 zai warming 100.00% 3538 ms 50 tok/s 2 samples, warming 66 with TTFT
More
Provider availability
100.00% (6 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
5813 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T02:38:37.000Z
openai/gpt-3.5-turbo lightning warming 100.00% 3541 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4047 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T20:09:44.000Z
x-ai/grok-4.20 grok warming 100.00% 3553 ms Not measured 0 samples, warming 33 with TTFT
More
Provider availability
100.00% (3 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3827 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:54:43.000Z
z-ai/glm-5.3-flash near-ai warming 3.85% 3555 ms Not measured 0 samples, warming 261 with TTFT
More
Provider availability
3.85% (26 samples)
Within deadline
3.85%
Capacity accepted
100.00%
p95 TTFT
3555 ms
Failure owner
provider: 25
Errors
TimeoutError: 1, provider_error: 24
Excluded from provider availability
None
Last seen
2026-09-16T04:08:34.000Z
z-ai/glm-5.3-flash arcee warming 100.00% 3569 ms Not measured 0 samples, warming 33 with TTFT
More
Provider availability
100.00% (3 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
6524 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T22:45:09.000Z
z-ai/glm-5.3-flash zai warming 100.00% 3569 ms Not measured 0 samples, warming 201 with TTFT
More
Provider availability
100.00% (20 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3569 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:50:44.281Z
meta-llama/llama-4-maverick-17b-128e-instruct-fp8 deepinfra warming 100.00% 3579 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3579 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T04:13:57.000Z
deepseek/deepseek-v3.2 digitalocean warming 100.00% 3585 ms Not measured 0 samples, warming 33 with TTFT
More
Provider availability
100.00% (3 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4122 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T02:50:27.000Z
qwen/qwen-mt-flash alibaba warming 100.00% 3591 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4051 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T19:34:59.000Z
meta-llama/llama-3.3-70b-instruct-turbo deepinfra warming 100.00% 3593 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3593 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T19:40:31.000Z
z-ai/glm-5.3-flash parasail warming 100.00% 3594 ms Not measured 0 samples, warming 33 with TTFT
More
Provider availability
100.00% (3 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3773 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:40:01.000Z
nvidia/nemotron-3-ultra-550b-a55b fireworks warming 100.00% 3618 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3618 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T20:08:26.000Z
minimax/minimax-m2.7 telnyx warming 100.00% 3626 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3626 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T02:51:47.000Z
google/gemini-2.5-pro lightning warming 100.00% 3633 ms Not measured 0 samples, warming 44 with TTFT
More
Provider availability
100.00% (4 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
5240 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:39:45.000Z
qwen/qwen3.5-397b-a17b morph warming 33.33% 3636 ms Not measured 0 samples, warming 31 with TTFT
More
Provider availability
33.33% (3 samples)
Within deadline
33.33%
Capacity accepted
66.67%
p95 TTFT
3636 ms
Failure owner
provider: 2
Errors
TimeoutError: 1, provider_error: 1
Excluded from provider availability
None
Last seen
2026-09-16T02:12:50.000Z
z-ai/glm-5.3 deepinfra warming 100.00% 3688 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
11260 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T04:06:50.051Z
openai/gpt-oss-20b deepinfra warming 100.00% 3694 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3694 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:28:52.000Z
qwen/qwen3.7-plus-2026-05-26 alibaba warming 100.00% 3696 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3696 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T08:36:46.000Z
deepseek/deepseek-v4-pro baseten warming 100.00% 3698 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3698 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T21:30:46.000Z
qwen/qwen3.5-flash-2026-02-23 alibaba warming 100.00% 3722 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3722 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T11:24:58.000Z
minimax/minimax-m2.7 atlas-cloud warming 100.00% 3752 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3752 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T19:10:19.000Z
qwen/qwen3.8-max fireworks warming 100.00% 3752 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3752 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T14:23:53.000Z
google/gemini-3.8-flash google-vertex warming 100.00% 3754 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3754 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T00:54:54.000Z
meta-llama/llama-3.1-8b-instruct telnyx warming 100.00% 3759 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3759 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T12:20:33.000Z
openai/gpt-oss-120b sambanova warming 100.00% 3767 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3767 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T18:13:58.000Z
deepseek/deepseek-v4-pro io-net warming 100.00% 3794 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3794 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T16:49:49.000Z
x-ai/grok-4.3 atlas-cloud warming 100.00% 3801 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3801 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T18:01:55.000Z
qwen/qwen-3-8-27b venice warming 100.00% 3803 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
5079 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:51:46.000Z
z-ai/glm-5.3 inceptron warming 100.00% 3807 ms Not measured 0 samples, warming 77 with TTFT
More
Provider availability
100.00% (7 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
18512 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T02:05:08.000Z
moonshotai/kimi-k2.5 siliconflow warming 100.00% 3813 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3813 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T19:36:51.000Z
z-ai/glm-4.7 baseten warming 100.00% 3815 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3815 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T21:28:42.000Z
google/gemini-3.1-pro-preview atlas-cloud warming 100.00% 3824 ms 31 tok/s 1 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3824 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T12:34:36.000Z
qwen/qwen3-235b-a22b-thinking-2507 venice warming 100.00% 3839 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3839 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T16:27:34.000Z
meta-llama/llama-3.3-70b-instruct parasail warming 100.00% 3856 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3856 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T23:23:51.000Z
qwen/qwen3.6-27b wandb warming 100.00% 3857 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3857 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T14:45:51.000Z
z-ai/glm-4.5-air io-net warming 100.00% 3863 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3863 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:48:47.000Z
qwen/qwen3.5-397b-a17b scaleway warming 100.00% 3865 ms Not measured 0 samples, warming 33 with TTFT
More
Provider availability
100.00% (3 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4250 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T20:18:36.000Z
anthropic/claude-fable-5.1 anthropic warming 88.89% 3904 ms Not measured 0 samples, warming 97 with TTFT
More
Provider availability
88.89% (9 samples)
Within deadline
62.50%
Capacity accepted
100.00%
p95 TTFT
37932 ms
Failure owner
provider: 1
Errors
empty_stream: 1
Excluded from provider availability
None
Last seen
2026-09-15T22:15:53.160Z
thedrummer/skyfall-36b-v2 parasail warming 100.00% 3920 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3920 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:15:41.000Z
google/gemini-3.5-flash google-ai-studio warming 100.00% 3948 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3948 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T22:14:23.000Z
openai/gpt-5.6-luna openai warming 100.00% 3975 ms Not measured 0 samples, warming 31 with TTFT
More
Provider availability
100.00% (3 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
3975 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:34:08.602Z
google/gemini-2.5-pro google-vertex warming 100.00% 3982 ms Not measured 0 samples, warming 33 with TTFT
More
Provider availability
100.00% (3 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
5900 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:04:59.000Z
qwen/qwen3.8-max atlas-cloud warming 100.00% 4005 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4005 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T11:56:19.000Z
qwen/qwen3-max deepinfra warming 100.00% 4026 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4026 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T06:36:54.000Z
nvidia/nemotron-3-nano-30b-a3b-bf16 nscale warming 100.00% 4028 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4028 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T21:02:50.000Z
openai/gpt-oss-20b parasail warming 100.00% 4039 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4039 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T12:39:45.000Z
deepseek/deepseek-v4.1-flash baseten warming 100.00% 4055 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4055 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T22:56:33.000Z
deepseek/deepseek-v4.1-flash arcee warming 100.00% 4066 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4599 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T16:18:43.000Z
moonshotai/kimi-k3 fireworks warming 100.00% 4072 ms 49 tok/s 2 samples, warming 75 with TTFT
More
Provider availability
100.00% (7 samples)
Within deadline
80.00%
Capacity accepted
100.00%
p95 TTFT
48997 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T02:57:10.000Z
deepseek/deepseek-v4-flash-0731 inceptron warming 75.00% 4123 ms Not measured 0 samples, warming 43 with TTFT
More
Provider availability
75.00% (4 samples)
Within deadline
75.00%
Capacity accepted
100.00%
p95 TTFT
10217 ms
Failure owner
provider: 1
Errors
provider_error: 1
Excluded from provider availability
None
Last seen
2026-09-15T20:54:46.000Z
z-ai/glm-5.3 arcee warming 100.00% 4143 ms Not measured 0 samples, warming 33 with TTFT
More
Provider availability
100.00% (3 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
5600 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T22:52:40.000Z
Qwen/Qwen3-235B-A22B-Instruct-2507 nebius warming 100.00% 4159 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4159 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:51:48.000Z
deepseek/deepseek-v4-flash morph warming 100.00% 4161 ms 39 tok/s 1 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4161 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T14:38:22.000Z
z-ai/glm-5.3 tinfoil warming 100.00% 4170 ms Not measured 0 samples, warming 65 with TTFT
More
Provider availability
100.00% (6 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
27687 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:21:00.234Z
moonshotai/kimi-k2.5 azure warming 100.00% 4177 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4177 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T04:39:12.000Z
openai/o1 openai warming 100.00% 4180 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4180 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T22:14:21.000Z
google/gemini-3.1-flash-lite-preview lightning warming 100.00% 4214 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4214 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T07:38:04.000Z
qwen/qwen-3-7-plus venice warming 100.00% 4220 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4220 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T16:15:50.000Z
deepseek/deepseek-v4.1-flash deepinfra warming 100.00% 4221 ms Not measured 0 samples, warming 33 with TTFT
More
Provider availability
100.00% (3 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
6094 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T16:06:06.086Z
openai/gpt-4.1 lightning warming 100.00% 4227 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4227 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:48:42.000Z
moonshotai/kimi-k2-thinking io-net warming 100.00% 4255 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4255 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T04:54:42.000Z
qwen/qwen3-max alibaba warming 100.00% 4338 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4338 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T15:38:33.000Z
z-ai/glm-5.2 siliconflow warming 100.00% 4341 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4341 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T23:54:02.000Z
z-ai/glm-5.2 phala warming 85.71% 4342 ms 46 tok/s 2 samples, warming 76 with TTFT
More
Provider availability
85.71% (7 samples)
Within deadline
85.71%
Capacity accepted
100.00%
p95 TTFT
16011 ms
Failure owner
provider: 1
Errors
TimeoutError: 1
Excluded from provider availability
None
Last seen
2026-09-16T03:35:48.000Z
z-ai/glm-5.3-flash engy warming 100.00% 4413 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4413 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:31:39.000Z
deepseek/deepseek-v3.2 atlas-cloud warming 100.00% 4438 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4438 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:39:52.000Z
openai/gpt-5-mini azure warming 100.00% 4503 ms Not measured 0 samples, warming 55 with TTFT
More
Provider availability
100.00% (5 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4979 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T00:41:49.000Z
zai-org/glm-4.7 novita warming 100.00% 4556 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
50.00%
Capacity accepted
100.00%
p95 TTFT
22809 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:36:55.000Z
qwen/qwen3-235b-a22b-instruct-2507 deepinfra warming 100.00% 4574 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4574 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T00:53:24.000Z
z-ai/glm-5.3-flash siliconflow warming 100.00% 4589 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4589 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T11:01:45.000Z
tencent/hy4-preview gmi warming 100.00% 4603 ms Not measured 0 samples, warming 88 with TTFT
More
Provider availability
100.00% (8 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
9883 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:24:44.000Z
minimax/minimax-m25 venice warming 100.00% 4763 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4763 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:45:57.000Z
minimax/minimax-m2.7 sambanova warming 100.00% 4777 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4777 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T02:38:37.000Z
qwen/qwen3.6-35b-a3b parasail warming 100.00% 4784 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4784 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T07:49:42.000Z
moonshotai/kimi-k3 featherless warming 100.00% 4823 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4823 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T04:02:23.000Z
z-ai/glm-4.6v zai warming 100.00% 4827 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
4827 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T00:27:41.000Z
moonshotai/kimi-k2.6 featherless warming 100.00% 4849 ms Not measured 0 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
6028 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T20:30:49.000Z
deepseek/deepseek-v4-pro arcee warming 100.00% 4859 ms Not measured 0 samples, warming 55 with TTFT
More
Provider availability
100.00% (5 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
6263 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T04:02:04.000Z
z-ai/glm-5.2 baseten warming 100.00% 4944 ms Not measured 0 samples, warming 122 with TTFT
More
Provider availability
100.00% (12 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
11074 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:54:15.483Z
moonshotai/kimi-k2.6 chutes warming 100.00% 5120 ms 29 tok/s 1 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
12901 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:15:50.356Z
z-ai/glm-5 zai warming 100.00% 5177 ms Not measured 0 samples, warming 33 with TTFT
More
Provider availability
100.00% (3 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
5653 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:50:47.000Z
deepseek/deepseek-v4-flash arcee warming 100.00% 5230 ms 74 tok/s 1 samples, warming 22 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
14701 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T00:45:10.000Z
z-ai/glm-5.3-fast baseten warming 100.00% 5270 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
5270 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T04:13:59.000Z
stepfun/step-3.5-flash stepfun warming 100.00% 5352 ms Not measured 0 samples, warming 55 with TTFT
More
Provider availability
100.00% (5 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
8921 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T02:30:46.000Z
moonshotai/kimi-k3 cloudflare-workers-ai warming 100.00% 5457 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
5457 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:57:50.000Z
z-ai/glm-5.3 zai warming 100.00% 5527 ms Not measured 0 samples, warming 21 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
5527 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:58:08.941Z
openai/gpt-5 openai warming 100.00% 5573 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
5573 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T02:36:48.000Z
z-ai/glm-5.2 arcee warming 100.00% 5607 ms Not measured 0 samples, warming 33 with TTFT
More
Provider availability
100.00% (3 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
5978 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T19:42:35.000Z
moonshotai/kimi-k3 siliconflow warming 100.00% 6170 ms 43 tok/s 2 samples, warming 33 with TTFT
More
Provider availability
100.00% (3 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
13337 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:01:55.000Z
qwen/qwen3.5-397b-a17b chutes warming 100.00% 6269 ms Not measured 0 samples, warming 44 with TTFT
More
Provider availability
100.00% (4 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
11901 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:16:02.146Z
mistralai/mistral-nemo chutes warming 100.00% 6395 ms Not measured 0 samples, warming 44 with TTFT
More
Provider availability
100.00% (4 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
11394 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T21:56:33.000Z
z-ai/glm-5-turbo venice warming 100.00% 6653 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
6653 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T10:18:57.000Z
deepseek/deepseek-v4-pro-0423 parasail warming 100.00% 6715 ms 43 tok/s 1 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
6715 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T02:42:25.000Z
zai-org/GLM-5.1 nebius warming 100.00% 6718 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
6718 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T21:15:52.000Z
moonshotai/kimi-k3 tinfoil warming 83.33% 6737 ms Not measured 0 samples, warming 61 with TTFT
More
Provider availability
83.33% (6 samples)
Within deadline
50.00%
Capacity accepted
83.33%
p95 TTFT
6737 ms
Failure owner
provider: 1
Errors
provider_error: 1
Excluded from provider availability
None
Last seen
2026-09-16T03:21:00.181Z
deepseek/deepseek-v4-pro featherless warming 100.00% 6961 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
6961 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T09:45:20.000Z
microsoft/wizardlm-2-8x22b novita warming 100.00% 7117 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
7117 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T12:08:46.000Z
xiaomi/mimo-v2.5 xiaomi warming 100.00% 7165 ms Not measured 0 samples, warming 88 with TTFT
More
Provider availability
100.00% (8 samples)
Within deadline
75.00%
Capacity accepted
100.00%
p95 TTFT
24823 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T22:24:41.000Z
qwen/qwen3-32b chutes warming 100.00% 7197 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
7197 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T16:45:54.000Z
minimaxai/minimax-m1-80k novita warming 100.00% 7253 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
7253 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T12:36:59.000Z
z-ai/glm-5.2 chutes warming 100.00% 7486 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
7486 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:15:50.347Z
z-ai/glm-5.1 zai warming 100.00% 7602 ms Not measured 0 samples, warming 33 with TTFT
More
Provider availability
100.00% (3 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
8619 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T22:57:51.000Z
minimax/minimax-m2.7 featherless warming 100.00% 7648 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
7648 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T02:39:55.000Z
google/gemma-4-31b-turbo chutes warming 100.00% 7657 ms Not measured 0 samples, warming 33 with TTFT
More
Provider availability
100.00% (3 samples)
Within deadline
66.67%
Capacity accepted
100.00%
p95 TTFT
20287 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:16:01.860Z
z-ai/glm-5.1 chutes warming 50.00% 7680 ms Not measured 0 samples, warming 63 with TTFT
More
Provider availability
50.00% (6 samples)
Within deadline
50.00%
Capacity accepted
100.00%
p95 TTFT
10194 ms
Failure owner
provider: 3
Errors
TimeoutError: 3
Excluded from provider availability
None
Last seen
2026-09-16T04:05:18.000Z
z-ai/glm-4.5 zai warming 100.00% 7760 ms Not measured 0 samples, warming 44 with TTFT
More
Provider availability
100.00% (4 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
12203 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T02:06:53.000Z
z-ai/glm-5.3-flash io-net warming 100.00% 8004 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
8004 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T15:15:58.000Z
z-ai/glm-5.3-flash deepinfra warming 100.00% 8086 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
8086 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T07:38:07.000Z
z-ai/glm-4.7 zai warming 100.00% 8677 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
8677 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T08:50:03.000Z
ibm-granite/granite-4.1-8b wandb warming 100.00% 9033 ms Not measured 0 samples, warming 33 with TTFT
More
Provider availability
100.00% (3 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
9318 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T00:41:55.000Z
deepseek/deepseek-v3.2 chutes warming 100.00% 9128 ms Not measured 0 samples, warming 65 with TTFT
More
Provider availability
100.00% (6 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
11851 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:15:50.605Z
qwen/qwen3.6-35b-a3b featherless warming 100.00% 9278 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
9278 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T02:59:07.000Z
minimax/minimax-m3 morph warming 40.00% 10027 ms 65 tok/s 2 samples, warming 52 with TTFT
More
Provider availability
40.00% (5 samples)
Within deadline
20.00%
Capacity accepted
40.00%
p95 TTFT
25067 ms
Failure owner
provider: 3
Errors
provider_error: 3
Excluded from provider availability
None
Last seen
2026-09-16T04:05:13.000Z
moonshotai/kimi-k3 gmi warming 100.00% 10391 ms 33 tok/s 2 samples, warming 55 with TTFT
More
Provider availability
100.00% (5 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
12634 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T04:09:55.000Z
deepseek/deepseek-v4-flash-0731 nvidia-nim warming 33.33% 11204 ms Not measured 0 samples, warming 31 with TTFT
More
Provider availability
33.33% (3 samples)
Within deadline
33.33%
Capacity accepted
100.00%
p95 TTFT
11204 ms
Failure owner
provider: 2
Errors
TimeoutError: 2
Excluded from provider availability
None
Last seen
2026-09-16T00:13:04.000Z
qwen/qwen3.6-27b featherless warming 100.00% 11490 ms Not measured 0 samples, warming 33 with TTFT
More
Provider availability
100.00% (3 samples)
Within deadline
66.67%
Capacity accepted
100.00%
p95 TTFT
23235 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T17:25:00.000Z
qwen/qwen3.6-27b chutes warming 66.67% 12543 ms Not measured 0 samples, warming 64 with TTFT
More
Provider availability
66.67% (6 samples)
Within deadline
50.00%
Capacity accepted
100.00%
p95 TTFT
29081 ms
Failure owner
provider: 2
Errors
TimeoutError: 2
Excluded from provider availability
None
Last seen
2026-09-16T03:16:02.367Z
nvidia/nemotron-3-ultra-550b-a55b nvidia-nim warming 100.00% 14912 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
14912 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T09:22:46.000Z
qwen/qwen3-coder-480b-a35b-instruct-turbo venice warming 100.00% 18926 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
18926 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T07:45:20.000Z
z-ai/glm-5.1 featherless warming 100.00% 22661 ms Not measured 0 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
100.00%
Capacity accepted
100.00%
p95 TTFT
22661 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T20:48:43.000Z
google/gemini-3.5-flash atlas-cloud warming 100.00% 28724 ms 10 tok/s 1 samples, warming 11 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
0.00%
Capacity accepted
100.00%
p95 TTFT
28724 ms
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T15:15:33.000Z
deepseek/deepseek-v4-pro deepinfra warming 100.00% Not measured Not measured 0 samples, warming 20 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
Not measured
Capacity accepted
100.00%
p95 TTFT
Not measured
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T11:02:21.180Z
deepseek/deepseek-v4-pro-0813 baseten warming 100.00% Not measured Not measured 0 samples, warming 260 with TTFT
More
Provider availability
100.00% (26 samples)
Within deadline
Not measured
Capacity accepted
100.00%
p95 TTFT
Not measured
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:54:22.534Z
google/gemini-3.1-pro deepinfra warming 100.00% Not measured Not measured 0 samples, warming 700 with TTFT
More
Provider availability
100.00% (70 samples)
Within deadline
Not measured
Capacity accepted
100.00%
p95 TTFT
Not measured
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T22:32:46.509Z
meta-llama/meta-llama-3.1-8b-instruct-turbo deepinfra warming 100.00% Not measured Not measured 0 samples, warming 10 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
Not measured
Capacity accepted
100.00%
p95 TTFT
Not measured
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:39:40.400Z
mistralai/mistral-nemo-instruct-2407 deepinfra warming 100.00% Not measured Not measured 0 samples, warming 10 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
Not measured
Capacity accepted
100.00%
p95 TTFT
Not measured
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:32:45.063Z
moonshotai/kimi-k2.6 baseten warming 100.00% Not measured Not measured 0 samples, warming 10 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
Not measured
Capacity accepted
100.00%
p95 TTFT
Not measured
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:54:15.220Z
moonshotai/kimi-k2.7-code baseten warming 100.00% Not measured 356 tok/s 1 samples, warming 60 with TTFT
More
Provider availability
100.00% (6 samples)
Within deadline
Not measured
Capacity accepted
100.00%
p95 TTFT
Not measured
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T04:12:10.000Z
moonshotai/kimi-k3 baseten warming 100.00% Not measured Not measured 0 samples, warming 20 with TTFT
More
Provider availability
100.00% (2 samples)
Within deadline
Not measured
Capacity accepted
100.00%
p95 TTFT
Not measured
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:08:20.000Z
moonshotai/kimi-k3 deepinfra warming 100.00% Not measured 23 tok/s 1 samples, warming 10 with TTFT
More
Provider availability
100.00% (1 samples)
Within deadline
Not measured
Capacity accepted
100.00%
p95 TTFT
Not measured
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:07:21.000Z
neurometric/tool-choice neurometric warming 100.00% Not measured Not measured 0 samples, warming 5000 with TTFT
More
Provider availability
100.00% (500 samples)
Within deadline
Not measured
Capacity accepted
100.00%
p95 TTFT
Not measured
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T04:17:23.916Z
openai/text-embedding-3-large openai warming 100.00% Not measured Not measured 0 samples, warming 1550 with TTFT
More
Provider availability
100.00% (155 samples)
Within deadline
Not measured
Capacity accepted
100.00%
p95 TTFT
Not measured
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:10:31.608Z
xiaomi/mimo-v2.5-pro deepinfra warming 100.00% Not measured 44 tok/s 2 samples, warming 110 with TTFT
More
Provider availability
100.00% (11 samples)
Within deadline
Not measured
Capacity accepted
100.00%
p95 TTFT
Not measured
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T02:11:49.000Z
z-ai/glm-5.2-fast fireworks warming 100.00% Not measured 161 tok/s 1 samples, warming 2280 with TTFT
More
Provider availability
100.00% (228 samples)
Within deadline
Not measured
Capacity accepted
100.00%
p95 TTFT
Not measured
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T04:02:06.074Z
aion-labs/aion-3.0-mini aion-labs warming 11 excluded Not measured Not measured 56 tok/s 1 samples, warming 00 with TTFT
More
Provider availability
Not measured (0 samples)
Within deadline
Not measured
Capacity accepted
Not measured
p95 TTFT
Not measured
Failure owner
None
Errors
None
Excluded from provider availability
probe_config_error: 11
Last seen
2026-09-15T19:24:45.000Z
baichuan/baichuan-m2-32b novita warming 0.00% Not measured Not measured 0 samples, warming 20 with TTFT
More
Provider availability
0.00% (2 samples)
Within deadline
0.00%
Capacity accepted
100.00%
p95 TTFT
Not measured
Failure owner
provider: 2
Errors
TimeoutError: 2
Excluded from provider availability
None
Last seen
2026-09-16T04:07:12.000Z
bytedance/seed-2.0-pro deepinfra warming 0.00% Not measured Not measured 0 samples, warming 10 with TTFT
More
Provider availability
0.00% (1 samples)
Within deadline
0.00%
Capacity accepted
100.00%
p95 TTFT
Not measured
Failure owner
provider: 1
Errors
empty_stream: 1
Excluded from provider availability
None
Last seen
2026-09-15T21:02:47.000Z
deepseek/deepseek-v4-flash atlas-cloud warming Not measured Not measured 149 tok/s 1 samples, warming 00 with TTFT
More
Provider availability
Not measured (0 samples)
Within deadline
Not measured
Capacity accepted
Not measured
p95 TTFT
Not measured
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T14:29:43.000Z
deepseek/deepseek-v4-flash deepinfra warming Not measured Not measured 130 tok/s 1 samples, warming 00 with TTFT
More
Provider availability
Not measured (0 samples)
Within deadline
Not measured
Capacity accepted
Not measured
p95 TTFT
Not measured
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T13:42:46.000Z
deepseek/deepseek-v4-flash digitalocean warming Not measured Not measured 17 tok/s 1 samples, warming 00 with TTFT
More
Provider availability
Not measured (0 samples)
Within deadline
Not measured
Capacity accepted
Not measured
p95 TTFT
Not measured
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T14:08:29.000Z
deepseek/deepseek-v4-flash featherless warming Not measured Not measured 210 tok/s 1 samples, warming 00 with TTFT
More
Provider availability
Not measured (0 samples)
Within deadline
Not measured
Capacity accepted
Not measured
p95 TTFT
Not measured
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T14:33:11.000Z
deepseek/deepseek-v4-flash io-net warming Not measured Not measured 67 tok/s 1 samples, warming 00 with TTFT
More
Provider availability
Not measured (0 samples)
Within deadline
Not measured
Capacity accepted
Not measured
p95 TTFT
Not measured
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T14:48:54.000Z
deepseek/deepseek-v4-flash novita warming Not measured Not measured 92 tok/s 1 samples, warming 00 with TTFT
More
Provider availability
Not measured (0 samples)
Within deadline
Not measured
Capacity accepted
Not measured
p95 TTFT
Not measured
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T13:57:33.000Z
deepseek/deepseek-v4-flash siliconflow warming Not measured Not measured 109 tok/s 2 samples, warming 00 with TTFT
More
Provider availability
Not measured (0 samples)
Within deadline
Not measured
Capacity accepted
Not measured
p95 TTFT
Not measured
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T13:37:45.000Z
deepseek/deepseek-v4-pro-0423 venice warming Not measured Not measured 28 tok/s 2 samples, warming 00 with TTFT
More
Provider availability
Not measured (0 samples)
Within deadline
Not measured
Capacity accepted
Not measured
p95 TTFT
Not measured
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T02:37:08.000Z
google/gemma-4-31b-it lightning warming Not measured Not measured 382 tok/s 1 samples, warming 00 with TTFT
More
Provider availability
Not measured (0 samples)
Within deadline
Not measured
Capacity accepted
Not measured
p95 TTFT
Not measured
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T12:52:56.000Z
google/gemma-4-31b-it nvidia-nim warming 0.00% Not measured Not measured 0 samples, warming 20 with TTFT
More
Provider availability
0.00% (2 samples)
Within deadline
0.00%
Capacity accepted
100.00%
p95 TTFT
Not measured
Failure owner
provider: 2
Errors
TimeoutError: 2
Excluded from provider availability
None
Last seen
2026-09-15T13:13:19.000Z
google/gemma-4-31b-it-ultra deepinfra warming 0.00% Not measured Not measured 0 samples, warming 10 with TTFT
More
Provider availability
0.00% (1 samples)
Within deadline
0.00%
Capacity accepted
100.00%
p95 TTFT
Not measured
Failure owner
provider: 1
Errors
TimeoutError: 1
Excluded from provider availability
None
Last seen
2026-09-15T17:04:11.000Z
kling/v3-pro kling warming 0.00% Not measured Not measured 0 samples, warming 10 with TTFT
More
Provider availability
Not measured (0 samples)
Within deadline
Not measured
Capacity accepted
Not measured
p95 TTFT
Not measured
Failure owner
unknown: 1
Errors
provider_error: 1
Excluded from provider availability
None
Last seen
2026-09-15T09:45:10.000Z
meta-llama/llama-3.2-90b-vision-instruct nvidia-nim warming 0.00% Not measured Not measured 0 samples, warming 40 with TTFT
More
Provider availability
0.00% (4 samples)
Within deadline
0.00%
Capacity accepted
100.00%
p95 TTFT
Not measured
Failure owner
provider: 4
Errors
TimeoutError: 4
Excluded from provider availability
None
Last seen
2026-09-15T16:25:19.000Z
mindai/macaron-v1-tall novita warming 0.00% Not measured Not measured 0 samples, warming 10 with TTFT
More
Provider availability
0.00% (1 samples)
Within deadline
0.00%
Capacity accepted
100.00%
p95 TTFT
Not measured
Failure owner
provider: 1
Errors
empty_stream: 1
Excluded from provider availability
None
Last seen
2026-09-15T13:48:46.000Z
minimax/minimax-m2.5 inceptron warming 0.00% Not measured Not measured 0 samples, warming 20 with TTFT
More
Provider availability
0.00% (2 samples)
Within deadline
0.00%
Capacity accepted
100.00%
p95 TTFT
Not measured
Failure owner
provider: 2
Errors
provider_error: 2
Excluded from provider availability
None
Last seen
2026-09-15T21:16:27.000Z
minimax/minimax-m2.7-turbo deepinfra warming 0.00% Not measured Not measured 0 samples, warming 10 with TTFT
More
Provider availability
0.00% (1 samples)
Within deadline
0.00%
Capacity accepted
100.00%
p95 TTFT
Not measured
Failure owner
provider: 1
Errors
empty_stream: 1
Excluded from provider availability
None
Last seen
2026-09-15T18:51:25.000Z
minimax/minimax-m3 atlas-cloud warming Not measured Not measured 97 tok/s 2 samples, warming 00 with TTFT
More
Provider availability
Not measured (0 samples)
Within deadline
Not measured
Capacity accepted
Not measured
p95 TTFT
Not measured
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:56:50.000Z
minimax/minimax-m3 deepinfra warming Not measured Not measured 24 tok/s 2 samples, warming 00 with TTFT
More
Provider availability
Not measured (0 samples)
Within deadline
Not measured
Capacity accepted
Not measured
p95 TTFT
Not measured
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:29:10.000Z
minimax/minimax-m3 novita warming Not measured Not measured 97 tok/s 2 samples, warming 00 with TTFT
More
Provider availability
Not measured (0 samples)
Within deadline
Not measured
Capacity accepted
Not measured
p95 TTFT
Not measured
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:36:51.000Z
minimax/minimax-m3 wandb warming Not measured Not measured 116 tok/s 2 samples, warming 00 with TTFT
More
Provider availability
Not measured (0 samples)
Within deadline
Not measured
Capacity accepted
Not measured
p95 TTFT
Not measured
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T01:46:35.000Z
moonshotai/kimi-k2.6 io-net warming Not measured Not measured 47 tok/s 1 samples, warming 00 with TTFT
More
Provider availability
Not measured (0 samples)
Within deadline
Not measured
Capacity accepted
Not measured
p95 TTFT
Not measured
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T16:33:26.000Z
moonshotai/kimi-k2.6 novita warming Not measured Not measured 35 tok/s 1 samples, warming 00 with TTFT
More
Provider availability
Not measured (0 samples)
Within deadline
Not measured
Capacity accepted
Not measured
p95 TTFT
Not measured
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T15:59:13.000Z
moonshotai/kimi-k2.6 siliconflow warming Not measured Not measured 25 tok/s 1 samples, warming 00 with TTFT
More
Provider availability
Not measured (0 samples)
Within deadline
Not measured
Capacity accepted
Not measured
p95 TTFT
Not measured
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T15:43:14.000Z
moonshotai/kimi-k2.7-code atlas-cloud warming Not measured Not measured 42 tok/s 1 samples, warming 00 with TTFT
More
Provider availability
Not measured (0 samples)
Within deadline
Not measured
Capacity accepted
Not measured
p95 TTFT
Not measured
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T12:24:17.000Z
moonshotai/kimi-k3 atlas-cloud warming Not measured Not measured 104 tok/s 1 samples, warming 00 with TTFT
More
Provider availability
Not measured (0 samples)
Within deadline
Not measured
Capacity accepted
Not measured
p95 TTFT
Not measured
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:52:00.000Z
moonshotai/kimi-k3 novita warming Not measured Not measured 34 tok/s 2 samples, warming 00 with TTFT
More
Provider availability
Not measured (0 samples)
Within deadline
Not measured
Capacity accepted
Not measured
p95 TTFT
Not measured
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T03:22:01.000Z
moonshotai/kimi-k3 nvidia-nim warming 0.00% Not measured Not measured 0 samples, warming 30 with TTFT
More
Provider availability
0.00% (3 samples)
Within deadline
0.00%
Capacity accepted
100.00%
p95 TTFT
Not measured
Failure owner
provider: 3
Errors
TimeoutError: 3
Excluded from provider availability
None
Last seen
2026-09-16T03:08:57.000Z
openai/gpt-5-nano lightning warming 0.00% Not measured Not measured 0 samples, warming 10 with TTFT
More
Provider availability
0.00% (1 samples)
Within deadline
0.00%
Capacity accepted
100.00%
p95 TTFT
Not measured
Failure owner
provider: 1
Errors
provider_error: 1
Excluded from provider availability
None
Last seen
2026-09-15T11:14:17.000Z
openai/gpt-5.4-2026-03-05 lightning warming 0.00% Not measured Not measured 0 samples, warming 10 with TTFT
More
Provider availability
0.00% (1 samples)
Within deadline
0.00%
Capacity accepted
100.00%
p95 TTFT
Not measured
Failure owner
provider: 1
Errors
provider_error: 1
Excluded from provider availability
None
Last seen
2026-09-15T07:28:47.000Z
openai/gpt-5.4-nano-2026-03-17 lightning warming 0.00% Not measured Not measured 0 samples, warming 10 with TTFT
More
Provider availability
0.00% (1 samples)
Within deadline
0.00%
Capacity accepted
100.00%
p95 TTFT
Not measured
Failure owner
provider: 1
Errors
provider_error: 1
Excluded from provider availability
None
Last seen
2026-09-15T21:12:53.000Z
openai/gpt-5.6-terra lightning warming 0.00% Not measured Not measured 0 samples, warming 10 with TTFT
More
Provider availability
0.00% (1 samples)
Within deadline
0.00%
Capacity accepted
100.00%
p95 TTFT
Not measured
Failure owner
provider: 1
Errors
provider_error: 1
Excluded from provider availability
None
Last seen
2026-09-16T01:31:46.000Z
openai/gpt-oss-120b nebius warming Not measured Not measured 103 tok/s 1 samples, warming 00 with TTFT
More
Provider availability
Not measured (0 samples)
Within deadline
Not measured
Capacity accepted
Not measured
p95 TTFT
Not measured
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T17:47:55.000Z
qwen/qwen3-235b-a22b-thinking-2507 alibaba warming Not measured Not measured 61 tok/s 2 samples, warming 00 with TTFT
More
Provider availability
Not measured (0 samples)
Within deadline
Not measured
Capacity accepted
Not measured
p95 TTFT
Not measured
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T19:04:30.000Z
qwen/qwen3-235b-a22b-thinking-2507 chutes warming 0.00% Not measured Not measured 0 samples, warming 30 with TTFT
More
Provider availability
0.00% (3 samples)
Within deadline
0.00%
Capacity accepted
100.00%
p95 TTFT
Not measured
Failure owner
provider: 3
Errors
provider_error: 3
Excluded from provider availability
None
Last seen
2026-09-15T22:12:45.000Z
qwen/qwen3-235b-a22b-thinking-2507 novita warming Not measured Not measured 63 tok/s 2 samples, warming 00 with TTFT
More
Provider availability
Not measured (0 samples)
Within deadline
Not measured
Capacity accepted
Not measured
p95 TTFT
Not measured
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T18:54:35.000Z
qwen/qwen3.5-397b-a17b parasail warming 0.00% Not measured Not measured 0 samples, warming 10 with TTFT
More
Provider availability
0.00% (1 samples)
Within deadline
0.00%
Capacity accepted
0.00%
p95 TTFT
Not measured
Failure owner
provider: 1
Errors
provider_error: 1
Excluded from provider availability
None
Last seen
2026-09-15T15:52:41.000Z
xiaomi/mimo-v2.5-pro atlas-cloud warming Not measured Not measured 40 tok/s 1 samples, warming 00 with TTFT
More
Provider availability
Not measured (0 samples)
Within deadline
Not measured
Capacity accepted
Not measured
p95 TTFT
Not measured
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T02:17:16.000Z
z-ai/glm-5.2 alibaba warming Not measured Not measured 60 tok/s 1 samples, warming 00 with TTFT
More
Provider availability
Not measured (0 samples)
Within deadline
Not measured
Capacity accepted
Not measured
p95 TTFT
Not measured
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T19:35:00.000Z
z-ai/glm-5.2 deepinfra warming Not measured Not measured 37 tok/s 1 samples, warming 00 with TTFT
More
Provider availability
Not measured (0 samples)
Within deadline
Not measured
Capacity accepted
Not measured
p95 TTFT
Not measured
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T20:32:54.000Z
z-ai/glm-5.2 digitalocean warming Not measured Not measured 6 tok/s 1 samples, warming 00 with TTFT
More
Provider availability
Not measured (0 samples)
Within deadline
Not measured
Capacity accepted
Not measured
p95 TTFT
Not measured
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T20:44:58.000Z
z-ai/glm-5.2 fireworks warming Not measured Not measured 82 tok/s 1 samples, warming 00 with TTFT
More
Provider availability
Not measured (0 samples)
Within deadline
Not measured
Capacity accepted
Not measured
p95 TTFT
Not measured
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T20:57:46.000Z
z-ai/glm-5.2 io-net warming Not measured Not measured 122 tok/s 1 samples, warming 00 with TTFT
More
Provider availability
Not measured (0 samples)
Within deadline
Not measured
Capacity accepted
Not measured
p95 TTFT
Not measured
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T21:36:54.000Z
z-ai/glm-5.2 novita warming Not measured Not measured 72 tok/s 1 samples, warming 00 with TTFT
More
Provider availability
Not measured (0 samples)
Within deadline
Not measured
Capacity accepted
Not measured
p95 TTFT
Not measured
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-15T22:38:15.000Z
z-ai/glm-5.2 telnyx warming Not measured Not measured 60 tok/s 1 samples, warming 00 with TTFT
More
Provider availability
Not measured (0 samples)
Within deadline
Not measured
Capacity accepted
Not measured
p95 TTFT
Not measured
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T00:08:29.000Z
z-ai/glm-5.2 venice warming Not measured Not measured 79 tok/s 2 samples, warming 00 with TTFT
More
Provider availability
Not measured (0 samples)
Within deadline
Not measured
Capacity accepted
Not measured
p95 TTFT
Not measured
Failure owner
None
Errors
None
Excluded from provider availability
None
Last seen
2026-09-16T00:34:31.000Z
z-ai/glm-5.3 nebius warming 0.00% Not measured Not measured 0 samples, warming 10 with TTFT
More
Provider availability
0.00% (1 samples)
Within deadline
0.00%
Capacity accepted
100.00%
p95 TTFT
Not measured
Failure owner
provider: 1
Errors
TimeoutError: 1
Excluded from provider availability
None
Last seen
2026-09-16T02:58:22.000Z
z-ai/glm-5.3 phala warming 0.00% Not measured Not measured 0 samples, warming 70 with TTFT
More
Provider availability
0.00% (7 samples)
Within deadline
0.00%
Capacity accepted
100.00%
p95 TTFT
Not measured
Failure owner
provider: 7
Errors
provider_error: 7
Excluded from provider availability
None
Last seen
2026-09-16T03:17:32.000Z
z-ai/glm-5.3-flash nvidia-nim warming 0.00% Not measured Not measured 0 samples, warming 30 with TTFT
More
Provider availability
0.00% (3 samples)
Within deadline
0.00%
Capacity accepted
100.00%
p95 TTFT
Not measured
Failure owner
provider: 3
Errors
TimeoutError: 3
Excluded from provider availability
None
Last seen
2026-09-16T03:37:26.000Z
z-ai/glm-5.3-flash phala warming 0.00% Not measured Not measured 0 samples, warming 20 with TTFT
More
Provider availability
0.00% (2 samples)
Within deadline
0.00%
Capacity accepted
100.00%
p95 TTFT
Not measured
Failure owner
provider: 2
Errors
provider_error: 2
Excluded from provider availability
None
Last seen
2026-09-15T12:33:52.000Z
Workspace access

Sign in

Choose a sign in method to access your TrustedRouter workspace.

By signing in you agree to the terms of service and privacy policy.