Measured performance

Provider & model performance

Measured time-to-first-token, time-to-first-byte, effective throughput, and uptime for every LLM provider and model TrustedRouter routes to — continuously sampled, not vendor-claimed.

Last updated 2026-08-02T03:08:19Z

Video leaderboard

Continuously sampled from TrustedRouter's monitor regions using a rolling benchmark set of up to 10,000 samples. Time-to-first-token (TTFT), time-to-first-byte (TTFB), effective throughput, and success rate come from real streaming requests, not vendor claims. 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. 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

Ranked by provider-attributed availability, then p50 time-to-first-token across all of a provider's models (40 providers · 2271 availability samples · 220 sustained throughput samples). Providers below the evidence floor remain visible as warming, but do not receive a rank.

#ProviderModels CompletionProvider availabilityWithin deadline Capacity acceptedp50 TTFTp95 TTFT Effective throughputFailure ownerConfig excludedSamples
1 friendli 7 100.00% 100.00% 98.00% 100.00% 1437 ms 7092 ms 84 tok/s 50
2 neurometric 5 98.21% 100.00% 98.18% 100.00% 1440 ms 4087 ms trustedrouter 1 1 router_error 55
3 fireworks 11 100.00% 100.00% 100.00% 100.00% 1464 ms 10865 ms 59 tok/s 65
4 mistral 8 100.00% 100.00% 98.53% 100.00% 1481 ms 6129 ms 68
5 openai 19 100.00% 100.00% 98.46% 100.00% 1509 ms 4557 ms 63 tok/s 70
6 grok 4 100.00% 100.00% 100.00% 100.00% 1549 ms 3858 ms 66 tok/s 61
7 telnyx 10 100.00% 100.00% 97.78% 100.00% 1590 ms 3886 ms 53 tok/s 45
8 google-ai-studio 8 100.00% 100.00% 98.48% 100.00% 1767 ms 4838 ms 83 tok/s 66
9 inceptron 3 97.56% 100.00% 100.00% 100.00% 1801 ms 9076 ms 157 tok/s trustedrouter 1 1 router_error 40
10 together 14 100.00% 100.00% 100.00% 100.00% 1861 ms 18603 ms 61 tok/s 13 probe_config_error 36
11 deepinfra 33 100.00% 100.00% 97.50% 100.00% 1874 ms 8778 ms 53 tok/s 40
12 venice 12 100.00% 100.00% 100.00% 100.00% 1943 ms 12867 ms 34 tok/s 59
13 kimi 11 100.00% 100.00% 100.00% 100.00% 1945 ms 7404 ms 24 tok/s 47
14 anthropic 10 98.11% 100.00% 98.04% 100.00% 2057 ms 7557 ms 60 tok/s trustedrouter 1 1 router_error 52
15 streamlake 3 100.00% 100.00% 96.00% 100.00% 2090 ms 13830 ms 48 tok/s 50
16 deepseek 3 98.33% 100.00% 100.00% 100.00% 2091 ms 3810 ms 59 tok/s trustedrouter 1 1 router_error 59
17 minimax 6 98.11% 100.00% 100.00% 100.00% 2320 ms 7470 ms 59 tok/s trustedrouter 1 1 router_error 52
18 cerebras 6 100.00% 100.00% 100.00% 100.00% 2364 ms 7425 ms 121 tok/s 76
19 wafer 5 100.00% 100.00% 98.18% 100.00% 2365 ms 7312 ms 156 tok/s 55
20 lightning 12 100.00% 100.00% 100.00% 100.00% 2438 ms 6080 ms 46 tok/s 49
21 google-vertex 9 100.00% 100.00% 100.00% 100.00% 2581 ms 5549 ms 69 tok/s 51
22 xiaomi 3 96.92% 100.00% 100.00% 100.00% 2751 ms 5437 ms 109 tok/s trustedrouter 2 2 router_error 63
23 gmi 5 100.00% 100.00% 100.00% 100.00% 3549 ms 7035 ms 30 tok/s 61
24 digitalocean 21 98.53% 98.53% 98.53% 98.53% 1586 ms 5364 ms 33 tok/s provider 1 68
25 thinkingmachines 2 98.48% 98.48% 98.48% 100.00% 2128 ms 7526 ms 77 tok/s provider 1 66
26 phala 2 98.18% 98.18% 96.36% 100.00% 2400 ms 18666 ms 45 tok/s provider 1 55
27 morph 8 96.36% 98.15% 98.15% 100.00% 2289 ms 11779 ms 46 tok/s provider 1, trustedrouter 1 1 router_error 54
28 chutes 10 96.36% 98.15% 94.44% 98.15% 2475 ms 15854 ms 34 tok/s trustedrouter 1, provider 1 1 router_error 54
29 siliconflow 24 98.08% 98.08% 96.00% 98.08% 3370 ms 9705 ms 35 tok/s provider 1 52
30 nebius 22 97.87% 97.87% 97.87% 100.00% 2462 ms 13273 ms 112 tok/s provider 1 47
31 makora 4 95.56% 97.73% 95.45% 100.00% 1626 ms 11509 ms 103 tok/s trustedrouter 1, provider 1 1 router_error 44
32 crusoe 14 96.19% 97.12% 96.15% 97.12% 2982 ms 12793 ms 61 tok/s unknown 1, provider 3 105
33 zai 11 95.38% 96.88% 95.31% 100.00% 2044 ms 7914 ms 63 tok/s provider 2, trustedrouter 1 1 router_error 64
34 atlas-cloud 43 94.83% 96.49% 96.49% 100.00% 2175 ms 5104 ms 55 tok/s trustedrouter 1, provider 2 1 router_error 57
35 cloudflare-workers-ai 18 96.43% 96.43% 96.43% 100.00% 1502 ms 13273 ms 37 tok/s provider 2 56
36 baseten 11 91.80% 94.92% 93.22% 100.00% 1796 ms 14383 ms 72 tok/s trustedrouter 2, provider 3 2 router_error 59
37 tinfoil 5 94.83% 94.83% 93.10% 100.00% 1982 ms 8491 ms 159 tok/s provider 3 58
38 alibaba 39 93.18% 93.18% 93.18% 100.00% 2454 ms 4513 ms 44 tok/s provider 3 44
39 novita 54 91.53% 91.53% 91.53% 96.61% 2581 ms 15311 ms 37 tok/s provider 5 59
40 parasail 19 83.33% 84.75% 81.13% 84.75% 2730 ms 15083 ms 53 tok/s provider 9, trustedrouter 1 2 probe_config_error 59

Models

Qualified models are ranked by provider-attributed availability, then p50 TTFT. Thin availability and throughput measurements stay visible below the ranked set as warming.

#ModelProvider CompletionProvider availabilityWithin deadlineCapacity accepted p50 TTFTp95 TTFTp50 TTFBp95 TTFB Effective throughputConfig excludedSamples
1 google/gemini-2.5-flash google-ai-studio 100.00% 100.00% 100.00% 20s 100.00% 1145 ms 17382 ms 1145 ms 17382 ms 12
2 z-ai/glm-4.7 cerebras 100.00% 100.00% 100.00% 20s 100.00% 1276 ms 7425 ms 1276 ms 7424 ms 13
3 mistralai/mistral-medium-3-5 mistral 100.00% 100.00% 100.00% 20s 100.00% 1287 ms 3089 ms 1287 ms 3089 ms 12
4 openai/gpt-4.1-mini openai 100.00% 100.00% 100.00% 20s 100.00% 1304 ms 3222 ms 792 ms 3222 ms 60 tok/s warming 15
5 z-ai/glm-5.2 friendli 100.00% 100.00% 100.00% 45s 100.00% 1350 ms 3348 ms 1350 ms 3348 ms 75 tok/s warming 12
6 x-ai/grok-4.3 grok 100.00% 100.00% 100.00% 20s 100.00% 1435 ms 10534 ms 1435 ms 10533 ms 21
7 z-ai/glm-5.1 wafer 100.00% 100.00% 100.00% 45s 100.00% 1437 ms 14124 ms 1437 ms 14123 ms 13
8 qwen/qwen3-vl-8b-instruct neurometric 100.00% 100.00% 100.00% 20s 100.00% 1440 ms 3629 ms 1439 ms 3629 ms 12
9 qwen/qwen3-235b-a22b-2507 friendli 100.00% 100.00% 100.00% 20s 100.00% 1441 ms 3396 ms 1441 ms 3396 ms 11
10 mistralai/mistral-nemo mistral 100.00% 100.00% 100.00% 20s 100.00% 1511 ms 7191 ms 1511 ms 7191 ms 11
11 x-ai/grok-build-0.1 grok 100.00% 100.00% 100.00% 20s 100.00% 1549 ms 3130 ms 1549 ms 3130 ms 14
12 mistralai/mistral-small-2603 mistral 100.00% 100.00% 100.00% 20s 100.00% 1569 ms 4039 ms 1569 ms 4038 ms 13
13 ibm-granite/granite-4.1-8b neurometric 100.00% 100.00% 93.33% 20s 100.00% 1570 ms 24611 ms 1569 ms 24611 ms 15
14 moonshotai/kimi-k2.7-code inceptron 100.00% 100.00% 100.00% 20s 100.00% 1590 ms 9076 ms 1589 ms 9075 ms 157 tok/s warming 13
15 kwaipilot/kat-coder-pro-v2 streamlake 100.00% 100.00% 100.00% 20s 100.00% 1601 ms 4251 ms 1601 ms 4251 ms 22
16 deepseek/deepseek-v4-flash makora 92.86% 100.00% 92.31% 20s 100.00% 1626 ms 20994 ms 1626 ms 20993 ms 76 tok/s warming 1 router_error 13
17 google/gemini-3-flash-preview google-ai-studio 100.00% 100.00% 100.00% 20s 100.00% 1629 ms 3807 ms 1629 ms 3807 ms 12
18 x-ai/grok-4.20 grok 100.00% 100.00% 100.00% 20s 100.00% 1636 ms 10153 ms 1636 ms 10153 ms 11
19 google/gemma-4-31b-it tinfoil 100.00% 100.00% 100.00% 20s 100.00% 1660 ms 3386 ms 1660 ms 3386 ms 159 tok/s warming 17
20 x-ai/grok-4.5 grok 100.00% 100.00% 100.00% 20s 100.00% 1780 ms 3662 ms 1780 ms 3661 ms 66 tok/s warming 15
21 moonshotai/kimi-k2.6 inceptron 100.00% 100.00% 100.00% 20s 100.00% 1801 ms 3143 ms 1801 ms 3143 ms 12
22 minimax/minimax-m2.7-highspeed minimax 100.00% 100.00% 100.00% 20s 100.00% 1947 ms 4164 ms 1947 ms 4164 ms 11
23 google/gemma-4-e2b-it neurometric 90.91% 100.00% 100.00% 20s 100.00% 2063 ms 3604 ms 2063 ms 3604 ms 1 router_error 10
24 deepseek/deepseek-v4-flash-0731 deepseek 95.24% 100.00% 100.00% 20s 100.00% 2068 ms 3650 ms 2068 ms 3649 ms 120 tok/s warming 1 router_error 20
25 kwaipilot/kat-coder-air-v2.5 streamlake 100.00% 100.00% 100.00% 20s 100.00% 2090 ms 13830 ms 2090 ms 13829 ms 48 tok/s warming 17
26 deepseek/deepseek-v4-pro deepseek 100.00% 100.00% 100.00% 20s 100.00% 2091 ms 3500 ms 2091 ms 3500 ms 37 tok/s warming 14
27 deepseek/deepseek-v4-flash deepseek 100.00% 100.00% 100.00% 20s 100.00% 2105 ms 3810 ms 2105 ms 3810 ms 59 tok/s warming 25
28 thinkingmachines/inkling-small thinkingmachines 100.00% 100.00% 100.00% 45s 100.00% 2128 ms 5060 ms 2128 ms 5060 ms 93 tok/s warming 38
29 minimax/minimax-m2.1-highspeed minimax 100.00% 100.00% 100.00% 20s 100.00% 2320 ms 4134 ms 2319 ms 4134 ms 11
30 cerebras/gpt-oss-120b cerebras 100.00% 100.00% 100.00% 15s 100.00% 2364 ms 4021 ms 2735 ms 10154 ms 377 tok/s warming 29
31 z-ai/glm-5.2 phala 100.00% 100.00% 100.00% 45s 100.00% 2400 ms 5124 ms 2400 ms 5124 ms 59 tok/s warming 28
32 minimax/minimax-m3 wafer 100.00% 100.00% 100.00% 20s 100.00% 2450 ms 4016 ms 2450 ms 4016 ms 123 tok/s warming 23
33 xiaomi/mimo-v2.5-pro-ultraspeed xiaomi 100.00% 100.00% 100.00% 20s 100.00% 2537 ms 4173 ms 2537 ms 4173 ms 183 tok/s warming 22
34 kwaipilot/kat-coder-pro-v2.5 streamlake 100.00% 100.00% 81.82% 20s 100.00% 2628 ms 26734 ms 2628 ms 26734 ms 11
35 google/gemma-4-31b-it cerebras 100.00% 100.00% 100.00% 20s 100.00% 2700 ms 8703 ms 2699 ms 8703 ms 79 tok/s warming 11
36 z-ai/glm-5.2 parasail 100.00% 100.00% 100.00% 45s 100.00% 2730 ms 12604 ms 984 ms 984 ms 60 tok/s warming 12
37 xiaomi/mimo-v2.5-pro xiaomi 95.45% 100.00% 100.00% 20s 100.00% 2751 ms 5437 ms 2750 ms 5436 ms 35 tok/s warming 1 router_error 21
38 google/gemini-3.1-flash-lite google-ai-studio 100.00% 100.00% 100.00% 15s 100.00% 2946 ms 3738 ms 2946 ms 3738 ms 11
39 deepseek/deepseek-v3-0324 crusoe 100.00% 100.00% 97.87% 20s 100.00% 2982 ms 14121 ms 2725 ms 4292 ms 47
40 xiaomi/mimo-v2.5 xiaomi 95.24% 100.00% 100.00% 20s 100.00% 3058 ms 5106 ms 3058 ms 5106 ms 1 router_error 20
41 deepseek/deepseek-v4-pro crusoe 90.91% 100.00% 100.00% 20s 100.00% 3281 ms 12740 ms 3281 ms 12740 ms 61 tok/s warming 11
42 qwen/qwen3-32b chutes 100.00% 100.00% 80.00% 20s 100.00% 3504 ms 32652 ms 3503 ms 32651 ms 10
43 deepseek/deepseek-v4-pro gmi 100.00% 100.00% 100.00% 20s 100.00% 3549 ms 13242 ms 3549 ms 13241 ms 30 tok/s warming 19
44 z-ai/glm-5.2 gmi 100.00% 100.00% 100.00% 45s 100.00% 4022 ms 19314 ms 4022 ms 19314 ms 56 tok/s warming 18
45 z-ai/glm-5.2 inceptron 93.75% 100.00% 100.00% 45s 100.00% 6474 ms 28834 ms 6474 ms 28834 ms 1 router_error 15
46 thinkingmachines/inkling thinkingmachines 96.43% 96.43% 96.43% 45s 100.00% 3983 ms 22062 ms 3983 ms 22062 ms 61 tok/s warming 28
47 moonshotai/kimi-k3 phala 96.30% 96.30% 92.59% 20s 100.00% 2962 ms 19836 ms 2961 ms 19835 ms 30 tok/s warming 27
48 z-ai/glm-5.2-nvfp4 makora 92.86% 92.86% 92.86% 45s 100.00% 2378 ms 11509 ms 2378 ms 11509 ms 14
49 openai/gpt-oss-120b tinfoil 92.31% 92.31% 92.31% 20s 100.00% 1982 ms 4057 ms 1982 ms 4057 ms 84 tok/s warming 13
50 z-ai/glm-4.7 zai 90.91% 90.91% 81.82% 20s 100.00% 3231 ms 28741 ms 3231 ms 28740 ms 11
51 qwen/qwen3.5-397b-a17b morph 90.00% 90.00% 90.00% 20s 100.00% 2289 ms 11779 ms 2289 ms 11779 ms 10
52 z-ai/glm-5.2 tinfoil 84.62% 84.62% 76.92% 45s 100.00% 3541 ms 46057 ms 3541 ms 46057 ms 13
qwen/qwen3.5-27b warming deepinfra 100.00% 100.00% 100.00% 20s 100.00% 369 ms 369 ms 368 ms 368 ms 1
qwen/qwen3.5-9b warming deepinfra 100.00% 100.00% 100.00% 20s 100.00% 476 ms 544 ms 476 ms 544 ms 2
z-ai/glm-4.6 warming deepinfra 100.00% 100.00% 100.00% 20s 100.00% 504 ms 3178 ms 504 ms 3177 ms 2
meta-llama/llama-3.3-70b-instruct warming parasail 100.00% 100.00% 100.00% 20s 100.00% 621 ms 849 ms 621 ms 849 ms 2
qwen/qwen3-coder-next warming parasail 100.00% 100.00% 100.00% 20s 100.00% 633 ms 1358 ms 632 ms 1357 ms 2
minimax/minimax-m2.5 warming digitalocean 100.00% 100.00% 100.00% 20s 100.00% 651 ms 1395 ms 651 ms 1395 ms 2
openbmb/MiniCPM-V-4_5 warming nebius 100.00% 100.00% 100.00% 20s 100.00% 659 ms 2696 ms 659 ms 2696 ms 114 tok/s warming 3
moonshotai/kimi-k2.7-code warming fireworks 100.00% 100.00% 100.00% 20s 100.00% 666 ms 1556 ms 666 ms 1556 ms 59 tok/s warming 4
zai-org/autoglm-phone-9b-multilingual warming novita 100.00% 100.00% 100.00% 20s 100.00% 673 ms 3210 ms 673 ms 3210 ms 2
openai/gpt-5.6-terra warming openai 100.00% 100.00% 100.00% 45s 100.00% 714 ms 714 ms 714 ms 714 ms 27 tok/s warming 1
x-ai/grok-build-0.1 warming atlas-cloud 100.00% 100.00% 100.00% 20s 100.00% 722 ms 3976 ms 722 ms 3976 ms 2
nvidia/Llama-3_1-Nemotron-Ultra-253B-v1 warming nebius 100.00% 100.00% 100.00% 20s 100.00% 726 ms 1049 ms 725 ms 1049 ms 2
z-ai/glm-5.2-fast warming fireworks 100.00% 100.00% 100.00% 45s 100.00% 730 ms 3734 ms 729 ms 3734 ms 100 tok/s warming 5
openai/gpt-5.1 warming openai 100.00% 100.00% 100.00% 20s 100.00% 735 ms 735 ms 735 ms 735 ms 1
z-ai/glm-5 warming deepinfra 100.00% 100.00% 100.00% 45s 100.00% 742 ms 3512 ms 742 ms 3512 ms 2
qwen/qwen3-235b-a22b-thinking-2507 warming deepinfra 100.00% 100.00% 100.00% 45s 100.00% 764 ms 764 ms 764 ms 764 ms 1
qwen/qwen3.5-35b-a3b warming deepinfra 100.00% 100.00% 100.00% 20s 100.00% 777 ms 777 ms 776 ms 776 ms 1
openai/gpt-4o-mini warming openai 100.00% 100.00% 100.00% 20s 100.00% 791 ms 1725 ms 791 ms 1725 ms 3
meta-llama/llama-3.1-8b-instruct warming novita 100.00% 100.00% 100.00% 20s 100.00% 807 ms 3139 ms 806 ms 3139 ms 2
google/gemma-2b-it warming telnyx 100.00% 100.00% 100.00% 20s 100.00% 845 ms 1636 ms 845 ms 1635 ms 4
thinkingmachines/inkling-1m warming baseten 80.00% 100.00% 100.00% 45s 100.00% 847 ms 2702 ms 847 ms 2702 ms 64 tok/s warming 1 router_error 4
nvidia/nemotron-3-nano-30b-a3b warming crusoe 100.00% 100.00% 100.00% 20s 100.00% 848 ms 4070 ms 848 ms 4070 ms 4
deepseek/deepseek-v4-flash warming parasail 100.00% 100.00% 100.00% 20s 100.00% 853 ms 1017 ms 853 ms 1017 ms 49 tok/s warming 4
aisingapore/gemma-sea-lion-v4-27b-it warming cloudflare-workers-ai 100.00% 100.00% 100.00% 20s 100.00% 879 ms 3286 ms 879 ms 3286 ms 4
qwen/qwen3-vl-30b-a3b-instruct warming novita 100.00% 100.00% 100.00% 20s 100.00% 892 ms 3406 ms 892 ms 3406 ms 2
google/gemma-4-12b-it warming neurometric 100.00% 100.00% 100.00% 20s 100.00% 893 ms 3218 ms 893 ms 3218 ms 9
nvidia/nemotron-3-super-120b warming digitalocean 100.00% 100.00% 100.00% 20s 100.00% 898 ms 2307 ms 898 ms 2307 ms 2
openai/gpt-oss-120b warming deepinfra 100.00% 100.00% 100.00% 20s 100.00% 923 ms 923 ms 923 ms 923 ms 28 tok/s warming 1
google/gemma-3-12b-it warming deepinfra 100.00% 100.00% 100.00% 20s 100.00% 938 ms 1835 ms 938 ms 1835 ms 2
openai/gpt-4.1 warming openai 100.00% 100.00% 100.00% 20s 100.00% 942 ms 1382 ms 942 ms 1382 ms 2
deepseek/deepseek-v4-pro warming fireworks 100.00% 100.00% 100.00% 20s 100.00% 952 ms 2679 ms 952 ms 2679 ms 59 tok/s warming 6
nvidia/nemotron-3-nano-omni warming digitalocean 100.00% 100.00% 100.00% 20s 100.00% 962 ms 1461 ms 961 ms 1461 ms 3
openai/gpt-4o warming openai 100.00% 100.00% 100.00% 20s 100.00% 967 ms 1010 ms 967 ms 1010 ms 3
minimax/minimax-m3 warming telnyx 100.00% 100.00% 100.00% 20s 100.00% 968 ms 3190 ms 968 ms 3190 ms 53 tok/s warming 6
z-ai/glm-4.7 warming atlas-cloud 100.00% 100.00% 100.00% 20s 100.00% 997 ms 1066 ms 997 ms 1066 ms 2
moonshotai/kimi-k2.6 warming together 100.00% 100.00% 100.00% 20s 100.00% 1000 ms 1158 ms 1000 ms 1158 ms 2
nvidia/nemotron-3-ultra-550b-a55b warming together 100.00% 100.00% 100.00% 20s 100.00% 1008 ms 1515 ms 1007 ms 1515 ms 124 tok/s warming 2
minimax/minimax-m2.5 warming friendli 100.00% 100.00% 100.00% 20s 100.00% 1016 ms 3320 ms 1016 ms 3319 ms 7
qwen/qwen3-omni-30b-a3b-instruct warming novita 100.00% 100.00% 100.00% 20s 100.00% 1038 ms 1038 ms 1038 ms 1038 ms 1
google/gemma-4-31b-it warming lightning 100.00% 100.00% 100.00% 20s 100.00% 1047 ms 1047 ms 1047 ms 1047 ms 72 tok/s warming 1
openai/gpt-oss-20b warming fireworks 100.00% 100.00% 100.00% 20s 100.00% 1060 ms 15014 ms 1059 ms 15013 ms 8
Qwen/Qwen3-30B-A3B-Instruct-2507 warming nebius 100.00% 100.00% 100.00% 20s 100.00% 1066 ms 1754 ms 1066 ms 1754 ms 2
inclusionai/ring-2.6-1t warming novita 100.00% 100.00% 100.00% 20s 100.00% 1079 ms 1079 ms 1078 ms 1078 ms 1
deepseek/deepseek-r1-distill-llama-70b warming novita 100.00% 100.00% 100.00% 45s 100.00% 1093 ms 1093 ms 1093 ms 1093 ms 1
openai/gpt-3.5-turbo warming lightning 100.00% 100.00% 100.00% 20s 100.00% 1112 ms 2422 ms 1112 ms 2421 ms 4
mistralai/ministral-14b-2512 warming mistral 100.00% 100.00% 100.00% 20s 100.00% 1134 ms 3844 ms 1134 ms 3844 ms 7
nvidia/nemotron-3-super-120b-a12b warming crusoe 100.00% 100.00% 100.00% 20s 100.00% 1134 ms 4319 ms 1134 ms 4319 ms 4
qwen/qwen3-vl-30b-a3b-instruct warming alibaba 100.00% 100.00% 100.00% 20s 100.00% 1139 ms 1139 ms 1139 ms 1139 ms 1
qwen/qwen3.6-plus warming atlas-cloud 100.00% 100.00% 100.00% 20s 100.00% 1153 ms 2527 ms 1153 ms 2527 ms 2
moonshotai/Kimi-K2.7-Code warming nebius 100.00% 100.00% 100.00% 20s 100.00% 1161 ms 1831 ms 1161 ms 1831 ms 2
openai/gpt-oss-120b warming fireworks 100.00% 100.00% 100.00% 20s 100.00% 1170 ms 1497 ms 1170 ms 1497 ms 116 tok/s warming 6
arcee-ai/trinity-large-thinking warming parasail 100.00% 100.00% 100.00% 45s 100.00% 1180 ms 1587 ms 1180 ms 1586 ms 2
qwen/qwen3-vl-flash-2025-10-15 warming alibaba 100.00% 100.00% 100.00% 20s 100.00% 1185 ms 3494 ms 1185 ms 3494 ms 2
tencent/hy3 warming deepinfra 100.00% 100.00% 100.00% 20s 100.00% 1187 ms 1187 ms 1187 ms 1187 ms 53 tok/s warming 1
moonshotai/kimi-k2.5 warming deepinfra 100.00% 100.00% 100.00% 20s 100.00% 1188 ms 3251 ms 1188 ms 3250 ms 2
xiaomi/mimo-v2.5-pro warming digitalocean 100.00% 100.00% 100.00% 20s 100.00% 1198 ms 1198 ms 1198 ms 1198 ms 64 tok/s warming 1
mistralai/ministral-3b-2512 warming mistral 100.00% 100.00% 100.00% 20s 100.00% 1204 ms 1741 ms 1204 ms 1741 ms 4
google/gemini-3.6-flash warming google-vertex 100.00% 100.00% 100.00% 20s 100.00% 1216 ms 3648 ms 1216 ms 3648 ms 45 tok/s warming 4
openai/gpt-oss-120b warming cloudflare-workers-ai 100.00% 100.00% 100.00% 20s 100.00% 1240 ms 2611 ms 1240 ms 2610 ms 48 tok/s warming 3
moonshotai/kimi-k2.5 warming novita 100.00% 100.00% 100.00% 20s 100.00% 1243 ms 1243 ms 1243 ms 1243 ms 1
bytedance/doubao-seed-2.0-pro-260215 warming atlas-cloud 100.00% 100.00% 100.00% 20s 100.00% 1258 ms 3883 ms 1258 ms 3883 ms 2
qwen/qwen2.5-coder-32b-instruct warming cloudflare-workers-ai 100.00% 100.00% 100.00% 20s 100.00% 1260 ms 1260 ms 1260 ms 1260 ms 1
meituan-longcat/longcat-2.0 warming atlas-cloud 100.00% 100.00% 100.00% 20s 100.00% 1263 ms 1712 ms 1263 ms 1712 ms 2
openai/gpt-5.6-luna warming openai 100.00% 100.00% 100.00% 45s 100.00% 1275 ms 3336 ms 1275 ms 3336 ms 67 tok/s warming 4
openai/gpt-oss-20b warming cloudflare-workers-ai 100.00% 100.00% 100.00% 20s 100.00% 1286 ms 3016 ms 1286 ms 3015 ms 4
google/gemini-2.5-flash-lite warming google-vertex 100.00% 100.00% 100.00% 15s 100.00% 1294 ms 10964 ms 1294 ms 10964 ms 146 tok/s warming 4
z-ai/glm-5.2 warming siliconflow 100.00% 100.00% 100.00% 45s 100.00% 1308 ms 1729 ms 1308 ms 1729 ms 29 tok/s warming 2
openai/gpt-5.5 warming atlas-cloud 100.00% 100.00% 100.00% 45s 100.00% 1325 ms 1325 ms 1325 ms 1325 ms 1
google/gemini-3.1-flash-image-preview warming google-ai-studio 100.00% 100.00% 83.33% 20s 100.00% 1334 ms 20019 ms 1334 ms 20019 ms 6
qwen/qwen3.5-397b-a17b warming deepinfra 100.00% 100.00% 100.00% 20s 100.00% 1338 ms 1673 ms 1338 ms 1673 ms 2
z-ai/glm-5 warming digitalocean 100.00% 100.00% 100.00% 45s 100.00% 1341 ms 1341 ms 1341 ms 1341 ms 1
google/gemma-4-26b-a4b-it warming novita 100.00% 100.00% 100.00% 20s 100.00% 1347 ms 7467 ms 1347 ms 7467 ms 2
z-ai/glm-4.7 warming venice 100.00% 100.00% 100.00% 20s 100.00% 1363 ms 1866 ms 1363 ms 1866 ms 4
lgai-exaone/k-exaone-236b-a23b warming friendli 100.00% 100.00% 100.00% 20s 100.00% 1370 ms 2898 ms 1369 ms 2898 ms 5
qwen/qwen3.5-122b-a10b warming siliconflow 100.00% 100.00% 100.00% 20s 100.00% 1375 ms 3528 ms 1375 ms 3528 ms 2
qwen/qwen3-235b-a22b-thinking-2507 warming chutes 100.00% 100.00% 100.00% 45s 100.00% 1379 ms 3838 ms 1379 ms 3838 ms 4
yutori/n1.5 warming crusoe 100.00% 100.00% 100.00% 20s 100.00% 1382 ms 4245 ms 1382 ms 4245 ms 5
meta-llama/llama-3.1-8b-instruct warming telnyx 100.00% 100.00% 100.00% 20s 100.00% 1383 ms 3177 ms 1383 ms 3177 ms 6
qwen/qwen3.5-397b-a17b warming digitalocean 100.00% 100.00% 100.00% 20s 100.00% 1387 ms 1640 ms 1386 ms 1640 ms 5
qwen/qwen3.7-flash-2026-07-15 warming alibaba 100.00% 100.00% 100.00% 20s 100.00% 1387 ms 1387 ms 1386 ms 1386 ms 123 tok/s warming 1
minimax/minimax-m3 warming atlas-cloud 100.00% 100.00% 100.00% 20s 100.00% 1410 ms 1410 ms 1409 ms 1409 ms 81 tok/s warming 1
mistralai/ministral-8b-2512 warming mistral 100.00% 100.00% 100.00% 20s 100.00% 1414 ms 4660 ms 1413 ms 4660 ms 8
qwen/qwen3-vl-8b-thinking warming neurometric 100.00% 100.00% 100.00% 45s 100.00% 1418 ms 3175 ms 1418 ms 3175 ms 9
NousResearch/Hermes-4-70B warming nebius 100.00% 100.00% 100.00% 20s 100.00% 1423 ms 4220 ms 1422 ms 4220 ms 3
openai/gpt-oss-120b warming cerebras 100.00% 100.00% 100.00% 20s 100.00% 1424 ms 2783 ms 1424 ms 2783 ms 163 tok/s warming 7
meta-llama/llama-4-maverick warming digitalocean 100.00% 100.00% 100.00% 20s 100.00% 1429 ms 3670 ms 1429 ms 3670 ms 5
morph/morph-v3-fast warming morph 100.00% 100.00% 100.00% 15s 100.00% 1430 ms 1584 ms 1430 ms 1583 ms 4
openai/gpt-5.6-sol warming openai 100.00% 100.00% 100.00% 45s 100.00% 1437 ms 2067 ms 1437 ms 2066 ms 75 tok/s warming 4
z-ai/glm-5.1 warming friendli 100.00% 100.00% 100.00% 45s 100.00% 1437 ms 4244 ms 1437 ms 4244 ms 4
qwen/qwen3.6-27b warming venice 100.00% 100.00% 100.00% 20s 100.00% 1442 ms 3444 ms 1442 ms 3444 ms 5
qwen/qwen3-30b-a3b-instruct-2507 warming alibaba 100.00% 100.00% 100.00% 20s 100.00% 1446 ms 15132 ms 1446 ms 15132 ms 2
qwen/qwen3-vl-flash warming alibaba 100.00% 100.00% 100.00% 20s 100.00% 1452 ms 1452 ms 1452 ms 1452 ms 1
qwen/qwen3.5-27b warming alibaba 100.00% 100.00% 100.00% 20s 100.00% 1452 ms 1452 ms 1451 ms 1451 ms 1
z-ai/glm-5.2 warming telnyx 100.00% 100.00% 100.00% 45s 100.00% 1454 ms 3647 ms 1454 ms 3647 ms 100 tok/s warming 6
meta-llama/llama-3.2-1b-instruct warming cloudflare-workers-ai 100.00% 100.00% 100.00% 20s 100.00% 1459 ms 2921 ms 1459 ms 2921 ms 5
qwen/qwq-32b warming cloudflare-workers-ai 100.00% 100.00% 100.00% 20s 100.00% 1462 ms 2407 ms 1461 ms 2407 ms 3
deepseek/deepseek-v4-flash warming fireworks 100.00% 100.00% 100.00% 20s 100.00% 1464 ms 2319 ms 1464 ms 2319 ms 153 tok/s warming 7
google/gemini-2.5-flash warming google-vertex 100.00% 100.00% 100.00% 20s 100.00% 1464 ms 4042 ms 1464 ms 4042 ms 7
qwen/qwen3-235b-a22b-thinking-2507 warming novita 100.00% 100.00% 100.00% 45s 100.00% 1466 ms 1466 ms 1466 ms 1466 ms 1
moonshotai/kimi-k2.6 warming digitalocean 100.00% 100.00% 100.00% 20s 100.00% 1474 ms 3997 ms 1474 ms 3997 ms 33 tok/s warming 4
mistralai/codestral-2508 warming mistral 100.00% 100.00% 83.33% 20s 100.00% 1481 ms 24986 ms 1481 ms 24985 ms 6
thinkingmachines/inkling-small warming baseten 100.00% 100.00% 100.00% 45s 100.00% 1484 ms 3149 ms 1484 ms 3148 ms 69 tok/s warming 6
google/gemini-3-flash-preview warming google-vertex 100.00% 100.00% 100.00% 20s 100.00% 1500 ms 1643 ms 1500 ms 1643 ms 3
ibm-granite/granite-4.0-h-micro warming cloudflare-workers-ai 100.00% 100.00% 100.00% 20s 100.00% 1501 ms 1665 ms 1501 ms 1665 ms 2
meta-llama/llama-4-scout-17b-16e-instruct warming cloudflare-workers-ai 100.00% 100.00% 100.00% 20s 100.00% 1502 ms 15703 ms 1502 ms 15703 ms 4
moonshotai/kimi-k3 warming baseten 87.50% 100.00% 100.00% 20s 100.00% 1504 ms 3800 ms 1504 ms 3799 ms 81 tok/s warming 1 router_error 7
openai/o4-mini warming openai 100.00% 100.00% 100.00% 45s 100.00% 1509 ms 1868 ms 1509 ms 1868 ms 3
qwen/qwen3-coder-flash warming digitalocean 100.00% 100.00% 100.00% 20s 100.00% 1515 ms 4155 ms 1514 ms 4155 ms 5
deepseek/deepseek-v4-pro warming makora 100.00% 100.00% 100.00% 20s 100.00% 1516 ms 4660 ms 1516 ms 4660 ms 129 tok/s warming 9
qwen/qwen3-max warming alibaba 100.00% 100.00% 100.00% 20s 100.00% 1519 ms 1519 ms 1519 ms 1519 ms 1
anthropic/claude-sonnet-4.5 warming anthropic 100.00% 100.00% 100.00% 20s 100.00% 1543 ms 3181 ms 1543 ms 3180 ms 5
z-ai/glm-4.7 warming baseten 100.00% 100.00% 100.00% 20s 100.00% 1549 ms 14383 ms 1549 ms 14383 ms 7
z-ai/glm-5.1 warming digitalocean 100.00% 100.00% 100.00% 45s 100.00% 1554 ms 10652 ms 1553 ms 10652 ms 4
moonshotai/kimi-k2.6 warming fireworks 100.00% 100.00% 100.00% 20s 100.00% 1562 ms 3076 ms 1562 ms 3076 ms 31 tok/s warming 7
MiniMaxAI/MiniMax-M3 warming nebius 100.00% 100.00% 100.00% 20s 100.00% 1563 ms 1563 ms 1563 ms 1563 ms 112 tok/s warming 1
meta-llama/llama-3.3-70b-instruct warming crusoe 100.00% 100.00% 100.00% 20s 100.00% 1563 ms 1563 ms 1563 ms 1563 ms 1
moonshotai/kimi-k2.7-code-highspeed warming kimi 100.00% 100.00% 100.00% 20s 100.00% 1564 ms 3398 ms 1563 ms 3398 ms 3
anthropic/claude-haiku-4.5 warming anthropic 100.00% 100.00% 100.00% 15s 100.00% 1570 ms 6689 ms 1570 ms 6689 ms 4
meta-llama/llama-4-maverick-17b-128e-instruct-fp8 warming novita 100.00% 100.00% 100.00% 20s 100.00% 1571 ms 1571 ms 1571 ms 1571 ms 1
openai/gpt-4o warming lightning 100.00% 100.00% 100.00% 20s 100.00% 1572 ms 3263 ms 1572 ms 3262 ms 5
nvidia/nemotron-nano-12b-v2-vl warming digitalocean 100.00% 100.00% 100.00% 20s 100.00% 1586 ms 3495 ms 1586 ms 3495 ms 8
moonshotai/moonshot-v1-128k warming kimi 100.00% 100.00% 100.00% 20s 100.00% 1587 ms 18781 ms 1587 ms 18781 ms 6
moonshotai/kimi-k2.7-code warming siliconflow 100.00% 100.00% 100.00% 20s 100.00% 1589 ms 3547 ms 1588 ms 3547 ms 35 tok/s warming 2
qwen/qwen3.5-9b warming venice 100.00% 100.00% 100.00% 20s 100.00% 1589 ms 3101 ms 1589 ms 3100 ms 3
openai/gpt-oss-120b warming baseten 100.00% 100.00% 100.00% 20s 100.00% 1590 ms 1590 ms 1590 ms 1590 ms 121 tok/s warming 1
z-ai/glm-5.1 warming telnyx 100.00% 100.00% 100.00% 45s 100.00% 1590 ms 3844 ms 1590 ms 3844 ms 2
deepseek/deepseek-v3.2 warming digitalocean 100.00% 100.00% 100.00% 20s 100.00% 1596 ms 3431 ms 1596 ms 3431 ms 3
openai/gpt-oss-120b warming parasail 100.00% 100.00% 100.00% 20s 100.00% 1597 ms 1597 ms 1597 ms 1597 ms 58 tok/s warming 1
deepseek/deepseek-v4-flash-0731 warming fireworks 100.00% 100.00% 100.00% 20s 100.00% 1619 ms 14793 ms 1619 ms 14793 ms 57 tok/s warming 6
openai/gpt-oss-120b warming nebius 100.00% 100.00% 100.00% 20s 100.00% 1619 ms 2357 ms 1619 ms 2357 ms 225 tok/s warming 2
mistralai/mistral-large warming mistral 100.00% 100.00% 100.00% 20s 100.00% 1624 ms 3025 ms 1624 ms 3024 ms 7
nvidia/nemotron-3-ultra-550b warming digitalocean 100.00% 100.00% 100.00% 20s 100.00% 1637 ms 3424 ms 1637 ms 3424 ms 3
minimax/minimax-m2.7 warming morph 100.00% 100.00% 100.00% 20s 100.00% 1642 ms 2949 ms 1642 ms 2948 ms 7
google/gemma-3-27b-it warming deepinfra 100.00% 100.00% 100.00% 20s 100.00% 1645 ms 1645 ms 1645 ms 1645 ms 1
bytedance/doubao-seed-1.6-flash-250828 warming atlas-cloud 100.00% 100.00% 100.00% 20s 100.00% 1649 ms 18409 ms 1649 ms 18409 ms 2
z-ai/glm-5v-turbo warming zai 100.00% 100.00% 100.00% 45s 100.00% 1652 ms 3588 ms 1652 ms 3588 ms 9
meta-llama/llama-3.1-70b-instruct warming deepinfra 100.00% 100.00% 100.00% 20s 100.00% 1653 ms 1653 ms 1653 ms 1653 ms 1
deepseek/deepseek-v4-pro warming atlas-cloud 100.00% 100.00% 100.00% 20s 100.00% 1654 ms 1654 ms 1654 ms 1654 ms 94 tok/s warming 1
openai/gpt-4 warming openai 100.00% 100.00% 100.00% 20s 100.00% 1663 ms 3272 ms 1662 ms 3272 ms 2
qwen/qwen3.7-plus warming atlas-cloud 100.00% 100.00% 100.00% 20s 100.00% 1667 ms 3852 ms 1667 ms 3852 ms 2
meta-llama/llama-3.3-70b-instruct warming digitalocean 100.00% 100.00% 100.00% 20s 100.00% 1689 ms 1689 ms 1689 ms 1689 ms 1
moonshotai/kimi-k2.7-code warming together 100.00% 100.00% 100.00% 20s 100.00% 1696 ms 12270 ms 1696 ms 12270 ms 4
moonshotai/kimi-k3 warming together 100.00% 100.00% 100.00% 20s 100.00% 1707 ms 5653 ms 1707 ms 5653 ms 39 tok/s warming 3
moonshotai/moonshot-v1-8k warming kimi 100.00% 100.00% 100.00% 20s 100.00% 1708 ms 3241 ms 1708 ms 3241 ms 7
zai-org/glm-4.7 warming novita 100.00% 100.00% 100.00% 20s 100.00% 1713 ms 1713 ms 1713 ms 1713 ms 1
google/gemini-3.5-flash warming google-vertex 100.00% 100.00% 100.00% 20s 100.00% 1714 ms 3384 ms 1714 ms 3384 ms 80 tok/s warming 6
z-ai/glm-4.7-flash warming venice 100.00% 100.00% 100.00% 20s 100.00% 1723 ms 6522 ms 1722 ms 6521 ms 6
qwen/qwen3-coder-30b-a3b-instruct warming novita 100.00% 100.00% 100.00% 20s 100.00% 1733 ms 1733 ms 1733 ms 1733 ms 1
tencent/hunyuan-a13b-instruct warming siliconflow 100.00% 100.00% 100.00% 20s 100.00% 1745 ms 6124 ms 1745 ms 6124 ms 2
openai/gpt-5.2 warming openai 100.00% 100.00% 100.00% 20s 100.00% 1748 ms 2857 ms 1747 ms 2857 ms 3
google/gemma-4-26b-a4b-it warming cloudflare-workers-ai 100.00% 100.00% 100.00% 20s 100.00% 1756 ms 2793 ms 1756 ms 2792 ms 2
openai/o3-mini warming openai 100.00% 100.00% 100.00% 45s 100.00% 1760 ms 4429 ms 1760 ms 4429 ms 2
google/gemini-3.6-flash warming google-ai-studio 100.00% 100.00% 100.00% 20s 100.00% 1767 ms 10363 ms 1767 ms 10363 ms 5
nvidia/nemotron-3-nano-omni-reasoning-30b-a3b warming crusoe 100.00% 100.00% 100.00% 45s 100.00% 1768 ms 5749 ms 1768 ms 5749 ms 3
z-ai/glm-5.1 warming siliconflow 100.00% 100.00% 100.00% 45s 100.00% 1768 ms 4618 ms 1768 ms 4618 ms 4
moonshotai/kimi-k2.6 warming wafer 100.00% 100.00% 50.00% 20s 100.00% 1772 ms 25150 ms 1771 ms 25150 ms 29 tok/s warming 2
qwen/qwen3-235b-a22b-instruct-2507 warming novita 100.00% 100.00% 100.00% 20s 100.00% 1786 ms 1786 ms 1786 ms 1786 ms 1
deepseek/deepseek-r1-distill-llama-70b warming digitalocean 100.00% 100.00% 100.00% 45s 100.00% 1788 ms 3031 ms 1788 ms 3031 ms 4
nvidia/nemotron-3-ultra-550b-a55b warming baseten 100.00% 100.00% 100.00% 20s 100.00% 1796 ms 3153 ms 1796 ms 3153 ms 234 tok/s warming 6
qwen/qwen3.5-flash warming atlas-cloud 100.00% 100.00% 100.00% 20s 100.00% 1802 ms 1802 ms 1802 ms 1802 ms 1
z-ai/glm-4.6 warming venice 100.00% 100.00% 100.00% 20s 100.00% 1808 ms 3483 ms 1807 ms 3483 ms 6
deepseek/deepseek-v4-flash warming crusoe 100.00% 100.00% 100.00% 20s 100.00% 1812 ms 4051 ms 1812 ms 4051 ms 82 tok/s warming 8
deepseek/deepseek-v4-pro warming siliconflow 100.00% 100.00% 100.00% 20s 100.00% 1814 ms 1814 ms 1814 ms 1814 ms 1
qwen/qwen3.5-35b-a3b warming alibaba 100.00% 100.00% 100.00% 20s 100.00% 1815 ms 1815 ms 1815 ms 1815 ms 1
minimax/minimax-m2.5-highspeed warming minimax 85.71% 100.00% 100.00% 20s 100.00% 1819 ms 2357 ms 1819 ms 2356 ms 1 router_error 6
z-ai/glm-4.6 warming zai 100.00% 100.00% 100.00% 20s 100.00% 1832 ms 15060 ms 1832 ms 15060 ms 3
z-ai/glm-4.6v warming zai 100.00% 100.00% 100.00% 20s 100.00% 1850 ms 4304 ms 1850 ms 4304 ms 5
openai/gpt-oss-20b warming together 100.00% 100.00% 100.00% 20s 100.00% 1861 ms 18603 ms 1860 ms 18603 ms 7
google/gemma-4-31b-it warming friendli 100.00% 100.00% 80.00% 20s 100.00% 1866 ms 21335 ms 1866 ms 21335 ms 84 tok/s warming 5
google/gemma-4-31b-it warming siliconflow 100.00% 100.00% 100.00% 20s 100.00% 1870 ms 1870 ms 1870 ms 1870 ms 39 tok/s warming 1
openai/gpt-4.1 warming lightning 100.00% 100.00% 100.00% 20s 100.00% 1870 ms 3544 ms 1870 ms 3543 ms 5
z-ai/glm-4.7 warming deepinfra 100.00% 100.00% 100.00% 20s 100.00% 1874 ms 1874 ms 1873 ms 1873 ms 1
google/gemini-3.5-flash warming atlas-cloud 100.00% 100.00% 100.00% 20s 100.00% 1882 ms 2095 ms 1880 ms 2094 ms 62 tok/s warming 2
qwen/qwen3.5-27b warming novita 100.00% 100.00% 100.00% 20s 100.00% 1882 ms 1882 ms 1881 ms 1881 ms 1
qwen/qwen3-30b-a3b-fp8 warming cloudflare-workers-ai 100.00% 100.00% 100.00% 20s 100.00% 1903 ms 2926 ms 1903 ms 2926 ms 5
openai/gpt-oss-20b warming novita 100.00% 100.00% 100.00% 20s 100.00% 1913 ms 2733 ms 1912 ms 2733 ms 2
moonshotai/kimi-k2.6 warming kimi 100.00% 100.00% 100.00% 20s 100.00% 1941 ms 7404 ms 1941 ms 7404 ms 18 tok/s warming 4
z-ai/glm-5.1 warming venice 100.00% 100.00% 100.00% 45s 100.00% 1943 ms 6654 ms 1942 ms 6654 ms 6
moonshotai/kimi-k2.5 warming kimi 100.00% 100.00% 100.00% 20s 100.00% 1945 ms 14565 ms 1945 ms 14565 ms 6
minimax/minimax-m2.7 warming minimax 100.00% 100.00% 100.00% 20s 100.00% 1951 ms 4094 ms 1951 ms 4093 ms 8
moonshotai/kimi-k2.6 warming parasail 100.00% 100.00% 100.00% 20s 100.00% 1952 ms 2045 ms 1952 ms 2044 ms 2
anthropic/claude-opus-4.7 warming anthropic 85.71% 100.00% 100.00% 45s 100.00% 1962 ms 3989 ms 1962 ms 3988 ms 1 router_error 6
moonshotai/moonshot-v1-128k-vision-preview warming kimi 100.00% 100.00% 100.00% 20s 100.00% 1962 ms 3133 ms 1961 ms 3132 ms 5
google/gemma-4-26b-a4b-it warming siliconflow 100.00% 100.00% 100.00% 20s 100.00% 1964 ms 3930 ms 1964 ms 3929 ms 3
openai/gpt-3.5-turbo warming openai 100.00% 100.00% 100.00% 20s 100.00% 1970 ms 3279 ms 1970 ms 3279 ms 4
google/gemini-3.5-flash warming google-ai-studio 100.00% 100.00% 100.00% 20s 100.00% 1986 ms 3998 ms 1986 ms 3998 ms 9
qwen/qwen3.6-27b warming chutes 100.00% 100.00% 100.00% 20s 100.00% 1986 ms 2600 ms 1986 ms 2599 ms 2
z-ai/glm-5.2 warming fireworks 100.00% 100.00% 100.00% 45s 100.00% 2007 ms 2850 ms 2007 ms 2850 ms 38 tok/s warming 2
moonshotai/kimi-k2.6 warming tinfoil 100.00% 100.00% 100.00% 20s 100.00% 2008 ms 4500 ms 2008 ms 4500 ms 8
google/gemini-2.5-flash warming lightning 100.00% 100.00% 100.00% 20s 100.00% 2015 ms 3459 ms 2015 ms 3459 ms 8
z-ai/glm-5 warming venice 100.00% 100.00% 100.00% 45s 100.00% 2016 ms 13671 ms 2016 ms 13671 ms 3
qwen/qwen3.5-122b-a10b warming novita 100.00% 100.00% 100.00% 20s 100.00% 2018 ms 2018 ms 2017 ms 2017 ms 1
anthropic/claude-sonnet-5 warming anthropic 100.00% 100.00% 100.00% 20s 100.00% 2019 ms 3479 ms 2019 ms 3479 ms 6
z-ai/glm-4.5v warming zai 100.00% 100.00% 100.00% 20s 100.00% 2021 ms 3686 ms 2021 ms 3686 ms 5
google/gemini-2.5-flash warming atlas-cloud 100.00% 100.00% 100.00% 20s 100.00% 2022 ms 3800 ms 2021 ms 3800 ms 4
qwen/qwen-vl-ocr warming alibaba 100.00% 100.00% 100.00% 20s 100.00% 2022 ms 2022 ms 2021 ms 2021 ms 1
moonshotai/kimi-k2.6 warming chutes 100.00% 100.00% 100.00% 20s 100.00% 2025 ms 3640 ms 2025 ms 3640 ms 34 tok/s warming 6
z-ai/glm-5.1 warming chutes 100.00% 100.00% 100.00% 45s 100.00% 2027 ms 4202 ms 2027 ms 4201 ms 4
deepseek/deepseek-ocr warming novita 100.00% 100.00% 100.00% 20s 100.00% 2029 ms 2029 ms 2029 ms 2029 ms 1
z-ai/glm-4.5-air warming zai 100.00% 100.00% 100.00% 20s 100.00% 2035 ms 4975 ms 2035 ms 4975 ms 5
z-ai/glm-5-turbo warming zai 100.00% 100.00% 100.00% 45s 100.00% 2044 ms 5086 ms 2044 ms 5086 ms 7
nvidia/nemotron-3-super-120b-a12b warming nebius 100.00% 100.00% 100.00% 20s 100.00% 2047 ms 2047 ms 2046 ms 2046 ms 1
google/gemini-2.5-flash-lite warming atlas-cloud 100.00% 100.00% 100.00% 15s 100.00% 2056 ms 2056 ms 2056 ms 2056 ms 117 tok/s warming 1
anthropic/claude-opus-4.8 warming anthropic 100.00% 100.00% 100.00% 45s 100.00% 2057 ms 7770 ms 2057 ms 7770 ms 101 tok/s warming 6
qwen/qwen3.6-27b warming morph 100.00% 100.00% 100.00% 20s 100.00% 2070 ms 5129 ms 2070 ms 5129 ms 6
zai-org/GLM-5.2 warming nebius 100.00% 100.00% 100.00% 45s 100.00% 2073 ms 20341 ms 2073 ms 20341 ms 2
deepseek/deepseek-v4-pro warming baseten 100.00% 100.00% 85.71% 20s 100.00% 2080 ms 22072 ms 2080 ms 22072 ms 72 tok/s warming 7
qwen/qwen-mt-flash warming alibaba 100.00% 100.00% 100.00% 20s 100.00% 2087 ms 2087 ms 2087 ms 2087 ms 1
nvidia/nemotron-3-nano-30b-a3b warming novita 100.00% 100.00% 100.00% 20s 100.00% 2124 ms 2124 ms 2124 ms 2124 ms 1
qwen/qwen3-omni-30b-a3b-thinking warming novita 100.00% 100.00% 100.00% 45s 100.00% 2129 ms 2129 ms 2129 ms 2129 ms 1
bytedance/doubao-seed-2.1-pro-260628 warming atlas-cloud 100.00% 100.00% 100.00% 20s 100.00% 2132 ms 2132 ms 2132 ms 2132 ms 1
meta-llama/llama-3.1-8b-instruct-fp8 warming cloudflare-workers-ai 100.00% 100.00% 100.00% 20s 100.00% 2145 ms 3231 ms 2145 ms 3230 ms 3
openai/gpt-5.6-terra warming atlas-cloud 100.00% 100.00% 100.00% 45s 100.00% 2145 ms 2145 ms 2145 ms 2145 ms 35 tok/s warming 1
z-ai/glm-5.2 warming makora 100.00% 100.00% 100.00% 45s 100.00% 2148 ms 24352 ms 2147 ms 24352 ms 8
z-ai/glm-4.5-air warming siliconflow 100.00% 100.00% 100.00% 20s 100.00% 2151 ms 2151 ms 2150 ms 2150 ms 1
qwen/qwen3-vl-8b-thinking warming alibaba 100.00% 100.00% 100.00% 45s 100.00% 2159 ms 2243 ms 2159 ms 2243 ms 2
qwen/qwen3.7-max-2026-06-08 warming alibaba 100.00% 100.00% 100.00% 20s 100.00% 2162 ms 2162 ms 2162 ms 2162 ms 1
qwen/qwen3.5-plus warming atlas-cloud 100.00% 100.00% 100.00% 20s 100.00% 2175 ms 2175 ms 2174 ms 2174 ms 1
z-ai/glm-5.2 warming zai 100.00% 100.00% 100.00% 45s 100.00% 2195 ms 3949 ms 2195 ms 3949 ms 63 tok/s warming 4
qwen/qwen3-max-preview warming alibaba 100.00% 100.00% 100.00% 20s 100.00% 2197 ms 2197 ms 2197 ms 2197 ms 1
z-ai/glm-5.1 warming crusoe 100.00% 100.00% 100.00% 45s 100.00% 2205 ms 2906 ms 2205 ms 2906 ms 2
z-ai/glm-5.2 warming morph 100.00% 100.00% 100.00% 45s 100.00% 2213 ms 14247 ms 2213 ms 14247 ms 53 tok/s warming 7
z-ai/glm-5 warming zai 100.00% 100.00% 100.00% 45s 100.00% 2243 ms 4186 ms 2243 ms 4185 ms 4
qwen/qwen3.6-plus warming alibaba 100.00% 100.00% 100.00% 20s 100.00% 2253 ms 2253 ms 2253 ms 2253 ms 1
z-ai/glm-5.2 warming together 100.00% 100.00% 100.00% 45s 100.00% 2263 ms 18324 ms 2263 ms 18324 ms 8
moonshotai/kimi-k3 warming cloudflare-workers-ai 100.00% 100.00% 100.00% 20s 100.00% 2269 ms 5087 ms 2269 ms 5086 ms 25 tok/s warming 2
qwen/qwen3-next-80b-a3b-instruct warming alibaba 100.00% 100.00% 100.00% 20s 100.00% 2274 ms 2274 ms 2274 ms 2274 ms 1
mistralai/mistral-nemo warming chutes 85.71% 100.00% 100.00% 20s 100.00% 2282 ms 3570 ms 2282 ms 3570 ms 1 router_error 6
z-ai/glm-5.2-fast warming wafer 100.00% 100.00% 100.00% 45s 100.00% 2285 ms 4433 ms 2285 ms 4433 ms 219 tok/s warming 9
deepseek/deepseek-v3.1-terminus warming atlas-cloud 100.00% 100.00% 100.00% 20s 100.00% 2306 ms 3622 ms 2305 ms 3622 ms 4
cerebras/gemma-4-31b warming cerebras 100.00% 100.00% 100.00% 15s 100.00% 2315 ms 4594 ms 2315 ms 4594 ms 7
openai/gpt-5.6-sol warming atlas-cloud 100.00% 100.00% 100.00% 45s 100.00% 2329 ms 2329 ms 2329 ms 2329 ms 51 tok/s warming 1
anthropic/claude-sonnet-4.6 warming anthropic 100.00% 100.00% 87.50% 20s 100.00% 2333 ms 21871 ms 2333 ms 21870 ms 50 tok/s warming 8
google/gemma-3n-e4b-it warming together 100.00% 100.00% 100.00% 20s 100.00% 2342 ms 3527 ms 2342 ms 3527 ms 2
moonshotai/Kimi-K2.6 warming nebius 100.00% 100.00% 100.00% 20s 100.00% 2360 ms 3246 ms 2360 ms 3246 ms 3
z-ai/glm-5.2 warming wafer 100.00% 100.00% 100.00% 45s 100.00% 2365 ms 5346 ms 2364 ms 5346 ms 190 tok/s warming 8
qwen/qwen3.7-max warming novita 100.00% 100.00% 100.00% 20s 100.00% 2379 ms 4141 ms 2379 ms 4141 ms 2
minimax/minimax-m3 warming morph 85.71% 100.00% 100.00% 20s 100.00% 2384 ms 6411 ms 2384 ms 6410 ms 46 tok/s warming 1 router_error 6
moonshotai/kimi-k2.6 warming telnyx 100.00% 100.00% 100.00% 20s 100.00% 2393 ms 3292 ms 2392 ms 3292 ms 3
minimax/minimax-m2.7 warming atlas-cloud 100.00% 100.00% 100.00% 20s 100.00% 2401 ms 2401 ms 2401 ms 2401 ms 1
moonshotai/moonshot-v1-8k-vision-preview warming kimi 100.00% 100.00% 100.00% 20s 100.00% 2405 ms 2738 ms 2405 ms 2738 ms 3
deepseek/deepseek-v4-flash warming morph 100.00% 100.00% 100.00% 20s 100.00% 2415 ms 10351 ms 2415 ms 10351 ms 24 tok/s warming 7
qwen/qwen3-vl-32b-thinking warming alibaba 100.00% 100.00% 100.00% 45s 100.00% 2430 ms 2623 ms 2429 ms 2623 ms 2
google/gemini-2.5-pro warming lightning 100.00% 100.00% 100.00% 20s 100.00% 2438 ms 3562 ms 2438 ms 3562 ms 2
NousResearch/Hermes-4-405B warming nebius 100.00% 100.00% 100.00% 20s 100.00% 2441 ms 2441 ms 2441 ms 2441 ms 1
qwen/qwen3-vl-235b-a22b-thinking warming alibaba 100.00% 100.00% 100.00% 45s 100.00% 2454 ms 2454 ms 2454 ms 2454 ms 1
google/gemma-3-27b-it warming nebius 100.00% 100.00% 100.00% 20s 100.00% 2462 ms 13273 ms 2462 ms 13273 ms 6
mistralai/mistral-small-3.1-24b-instruct warming cloudflare-workers-ai 100.00% 100.00% 100.00% 20s 100.00% 2466 ms 2862 ms 2466 ms 2862 ms 3
z-ai/glm-5-turbo warming venice 100.00% 100.00% 100.00% 45s 100.00% 2481 ms 4009 ms 2480 ms 4009 ms 5
Qwen/Qwen3-Next-80B-A3B-Thinking warming nebius 100.00% 100.00% 100.00% 45s 100.00% 2484 ms 3330 ms 2484 ms 3330 ms 2
qwen/qwen3.5-plus warming alibaba 100.00% 100.00% 100.00% 20s 100.00% 2484 ms 3565 ms 2484 ms 3564 ms 2
qwen/qwen3.5-27b warming siliconflow 100.00% 100.00% 100.00% 20s 100.00% 2488 ms 2488 ms 2488 ms 2488 ms 1
qwen/qwen3-coder-plus-2025-07-22 warming alibaba 100.00% 100.00% 100.00% 20s 100.00% 2494 ms 2494 ms 2494 ms 2494 ms 1
z-ai/glm-4.7-flash warming cloudflare-workers-ai 100.00% 100.00% 100.00% 20s 100.00% 2494 ms 4089 ms 2494 ms 4089 ms 3
anthropic/claude-opus-4.5 warming anthropic 100.00% 100.00% 100.00% 45s 100.00% 2498 ms 7499 ms 2498 ms 7498 ms 8
deepseek/deepseek-v3.2 warming siliconflow 100.00% 100.00% 100.00% 20s 100.00% 2517 ms 3994 ms 2516 ms 3993 ms 3
morph/morph-v3-large warming morph 100.00% 100.00% 100.00% 20s 100.00% 2521 ms 3161 ms 2521 ms 3161 ms 7
google/gemini-3.5-flash warming lightning 100.00% 100.00% 100.00% 20s 100.00% 2530 ms 4284 ms 2529 ms 4284 ms 45 tok/s warming 6
openai/gpt-4.1-nano warming openai 100.00% 100.00% 83.33% 20s 100.00% 2571 ms 20005 ms 2571 ms 20004 ms 6
cerebras/zai-glm-4.7 warming cerebras 100.00% 100.00% 100.00% 15s 100.00% 2575 ms 10889 ms 2575 ms 10889 ms 69 tok/s warming 9
google/gemini-3.1-flash-lite warming google-vertex 100.00% 100.00% 100.00% 15s 100.00% 2581 ms 3877 ms 2580 ms 3877 ms 8
qwen/qwen3.5-35b-a3b warming novita 100.00% 100.00% 100.00% 20s 100.00% 2581 ms 2581 ms 2581 ms 2581 ms 1
moonshotai/kimi-k3 warming telnyx 100.00% 100.00% 100.00% 20s 100.00% 2582 ms 3738 ms 2581 ms 3738 ms 46 tok/s warming 5
google/gemini-2.5-flash warming deepinfra 100.00% 100.00% 100.00% 20s 100.00% 2584 ms 2584 ms 2583 ms 2583 ms 1
google/gemini-3.1-flash-lite-preview warming lightning 100.00% 100.00% 100.00% 15s 100.00% 2587 ms 3500 ms 2587 ms 3500 ms 3
qwen/qwen3.5-397b-a17b warming venice 100.00% 100.00% 100.00% 20s 100.00% 2587 ms 4429 ms 2587 ms 4429 ms 8
qwen/qwen3-vl-plus-2025-09-23 warming alibaba 100.00% 100.00% 100.00% 20s 100.00% 2595 ms 2595 ms 2595 ms 2595 ms 1
deepseek/deepseek-v3.1-terminus warming siliconflow 100.00% 100.00% 100.00% 20s 100.00% 2596 ms 2596 ms 2595 ms 2595 ms 1
qwen/qwen-plus-2025-12-01 warming alibaba 100.00% 100.00% 100.00% 20s 100.00% 2600 ms 2600 ms 2600 ms 2600 ms 1
google/gemini-3-flash-preview warming lightning 100.00% 100.00% 100.00% 20s 100.00% 2602 ms 11808 ms 2602 ms 11808 ms 4
bytedance/doubao-seed-1.6-251015 warming atlas-cloud 100.00% 100.00% 100.00% 20s 100.00% 2605 ms 3597 ms 2604 ms 3597 ms 2
deepseek/deepseek-v3-0324 warming novita 100.00% 100.00% 100.00% 20s 100.00% 2606 ms 16652 ms 4
meta-llama/llama-3.3-70b-instruct warming together 100.00% 100.00% 100.00% 20s 100.00% 2632 ms 2632 ms 2632 ms 2632 ms 1
qwen/qwen3-next-80b-a3b-thinking warming alibaba 100.00% 100.00% 100.00% 45s 100.00% 2640 ms 3001 ms 2640 ms 3001 ms 2
anthropic/claude-opus-4.6 warming anthropic 100.00% 100.00% 100.00% 45s 100.00% 2644 ms 7557 ms 2643 ms 7557 ms 5
moonshotai/kimi-k2.6 warming crusoe 100.00% 100.00% 100.00% 20s 100.00% 2678 ms 2919 ms 2678 ms 2919 ms 2
google/gemma-4-31b-it warming crusoe 100.00% 100.00% 100.00% 20s 100.00% 2695 ms 3983 ms 2695 ms 3983 ms 30 tok/s warming 3
qwen/qwen3-14b warming deepinfra 100.00% 100.00% 80.00% 20s 100.00% 2696 ms 23303 ms 2696 ms 23303 ms 5
moonshotai/kimi-k2.5 warming telnyx 100.00% 100.00% 100.00% 20s 100.00% 2712 ms 3900 ms 2711 ms 3900 ms 6
deepseek/deepseek-r1-distill-qwen-32b warming cloudflare-workers-ai 100.00% 100.00% 100.00% 45s 100.00% 2715 ms 21190 ms 2715 ms 21190 ms 3
nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B warming nebius 100.00% 100.00% 100.00% 20s 100.00% 2723 ms 2723 ms 2722 ms 2722 ms 1
openai/gpt-4-turbo warming lightning 100.00% 100.00% 100.00% 20s 100.00% 2733 ms 3336 ms 2732 ms 3336 ms 4
Qwen/Qwen3-235B-A22B-Instruct-2507 warming nebius 100.00% 100.00% 100.00% 20s 100.00% 2736 ms 2886 ms 2735 ms 2886 ms 3
nvidia/Cosmos3-Super-Reasoner warming nebius 100.00% 100.00% 100.00% 20s 100.00% 2738 ms 2995 ms 2738 ms 2995 ms 62 tok/s warming 3
z-ai/glm-5.1 warming gmi 100.00% 100.00% 100.00% 45s 100.00% 2757 ms 5076 ms 2757 ms 5075 ms 7
deepseek/deepseek-v3.1-terminus warming novita 100.00% 100.00% 100.00% 20s 100.00% 2783 ms 2783 ms 2782 ms 2782 ms 1
openai/gpt-5.4-mini warming openai 100.00% 100.00% 100.00% 20s 100.00% 2790 ms 3318 ms 2790 ms 3317 ms 2
qwen/qwen-flash-2025-07-28 warming alibaba 100.00% 100.00% 100.00% 20s 100.00% 2812 ms 2812 ms 2812 ms 2812 ms 1
openai/gpt-oss-20b warming deepinfra 100.00% 100.00% 100.00% 20s 100.00% 2819 ms 6416 ms 2819 ms 6416 ms 3
moonshotai/moonshot-v1-32k warming kimi 100.00% 100.00% 100.00% 20s 100.00% 2823 ms 3785 ms 2823 ms 3785 ms 5
z-ai/glm-5 warming atlas-cloud 100.00% 100.00% 100.00% 45s 100.00% 2826 ms 2826 ms 2826 ms 2826 ms 1
google/gemma-4-31b-it warming digitalocean 100.00% 100.00% 100.00% 20s 100.00% 2834 ms 3136 ms 2834 ms 3136 ms 3
deepseek/deepseek-v3.2 warming novita 100.00% 100.00% 100.00% 20s 100.00% 2836 ms 2836 ms 2836 ms 2836 ms 1
deepseek/deepseek-v3.2 warming friendli 100.00% 100.00% 100.00% 20s 100.00% 2869 ms 7092 ms 2869 ms 7091 ms 6
google/gemini-3.1-flash-lite warming deepinfra 100.00% 100.00% 100.00% 15s 100.00% 2872 ms 4578 ms 2872 ms 4578 ms 2
qwen/qwen2.5-vl-72b-instruct warming parasail 100.00% 100.00% 100.00% 20s 100.00% 2882 ms 3839 ms 2882 ms 3839 ms 5
meta-llama/llama-3.3-70b-instruct warming telnyx 100.00% 100.00% 80.00% 20s 100.00% 2894 ms 25365 ms 2893 ms 25365 ms 5
google/gemini-2.5-pro warming atlas-cloud 100.00% 100.00% 100.00% 20s 100.00% 2908 ms 2908 ms 2908 ms 2908 ms 1
z-ai/glm-5.2 warming baseten 100.00% 100.00% 100.00% 45s 100.00% 2912 ms 3474 ms 2912 ms 3474 ms 56 tok/s warming 4
google/gemini-3.1-pro-preview warming google-ai-studio 100.00% 100.00% 100.00% 20s 100.00% 2940 ms 4838 ms 2940 ms 4837 ms 83 tok/s warming 6
meta-llama/llama-3.2-3b-instruct warming cloudflare-workers-ai 100.00% 100.00% 100.00% 20s 100.00% 2950 ms 3819 ms 2950 ms 3819 ms 3
meta-llama/llama-3.3-70b-instruct warming tinfoil 100.00% 100.00% 100.00% 20s 100.00% 2957 ms 18398 ms 2957 ms 18398 ms 7
moonshotai/kimi-k2.5 warming alibaba 100.00% 100.00% 100.00% 20s 100.00% 2959 ms 2959 ms 2959 ms 2959 ms 1
openai/gpt-5.5 warming openai 100.00% 100.00% 100.00% 45s 100.00% 2959 ms 4125 ms 2959 ms 4124 ms 4
thedrummer/cydonia-24b-v4.1 warming parasail 100.00% 100.00% 100.00% 20s 100.00% 2972 ms 2972 ms 2972 ms 2972 ms 1
moonshotai/moonshot-v1-32k-vision-preview warming kimi 100.00% 100.00% 100.00% 20s 100.00% 2974 ms 2978 ms 2973 ms 2978 ms 3
z-ai/glm-5.1 warming atlas-cloud 50.00% 100.00% 100.00% 45s 100.00% 2975 ms 2975 ms 2975 ms 2975 ms 1 router_error 1
moonshotai/kimi-k2.7-code warming kimi 100.00% 100.00% 100.00% 20s 100.00% 2994 ms 2994 ms 2994 ms 2994 ms 29 tok/s warming 1
tencent/hy3 warming siliconflow 100.00% 100.00% 100.00% 20s 100.00% 3000 ms 3000 ms 3000 ms 3000 ms 41 tok/s warming 1
moonshotai/kimi-k2.6 warming atlas-cloud 100.00% 100.00% 100.00% 20s 100.00% 3003 ms 3204 ms 3003 ms 3204 ms 58 tok/s warming 2
meta-llama/llama-3.1-70b-instruct warming telnyx 100.00% 100.00% 100.00% 20s 100.00% 3008 ms 3699 ms 3008 ms 3699 ms 2
gryphe/mythomax-l2-13b warming deepinfra 100.00% 100.00% 100.00% 20s 100.00% 3012 ms 3012 ms 3012 ms 3012 ms 1
anthropic/claude-opus-5 warming anthropic 100.00% 100.00% 100.00% 45s 100.00% 3014 ms 5795 ms 3014 ms 5794 ms 60 tok/s warming 3
z-ai/glm-5.1 warming zai 100.00% 100.00% 100.00% 45s 100.00% 3024 ms 7914 ms 3024 ms 7914 ms 5
z-ai/glm-5.2 warming atlas-cloud 100.00% 100.00% 100.00% 45s 100.00% 3024 ms 3024 ms 3024 ms 3024 ms 46 tok/s warming 1
xiaomi/mimo-v2.5-pro warming atlas-cloud 100.00% 100.00% 100.00% 20s 100.00% 3039 ms 3039 ms 3039 ms 3039 ms 29 tok/s warming 1
qwen/qwen3.6-flash warming alibaba 100.00% 100.00% 100.00% 20s 100.00% 3051 ms 3051 ms 3051 ms 3051 ms 1
minimax/minimax-m3 warming minimax 100.00% 100.00% 100.00% 20s 100.00% 3084 ms 4295 ms 3084 ms 4295 ms 59 tok/s warming 7
google/gemini-3.1-pro-preview warming google-vertex 100.00% 100.00% 100.00% 20s 100.00% 3097 ms 15654 ms 3097 ms 15654 ms 59 tok/s warming 5
nousresearch/hermes-3-llama-3.1-405b warming deepinfra 100.00% 100.00% 100.00% 20s 100.00% 3107 ms 4582 ms 3107 ms 4582 ms 3
mistralai/ministral-3-14b-instruct warming digitalocean 100.00% 100.00% 100.00% 20s 100.00% 3109 ms 3109 ms 3109 ms 3109 ms 1
openai/gpt-oss-120b warming novita 100.00% 100.00% 100.00% 20s 100.00% 3146 ms 3146 ms 3146 ms 3146 ms 21 tok/s warming 1
qwen/qwen3.6-35b-a3b warming deepinfra 100.00% 100.00% 100.00% 20s 100.00% 3189 ms 3189 ms 3189 ms 3189 ms 1
google/gemma-4-31b-it warming parasail 100.00% 100.00% 100.00% 20s 100.00% 3203 ms 3523 ms 3202 ms 3523 ms 27 tok/s warming 3
openai/gpt-5 warming openai 100.00% 100.00% 100.00% 20s 100.00% 3204 ms 4557 ms 3203 ms 4557 ms 4
moonshotai/kimi-k2.7-code warming atlas-cloud 100.00% 100.00% 100.00% 20s 100.00% 3212 ms 3987 ms 3211 ms 3987 ms 42 tok/s warming 2
minimax/minimax-m2.5 warming atlas-cloud 100.00% 100.00% 100.00% 20s 100.00% 3221 ms 3221 ms 3221 ms 3221 ms 1
bytedance/doubao-seed-2.0-mini-260428 warming atlas-cloud 100.00% 100.00% 100.00% 20s 100.00% 3231 ms 3231 ms 3231 ms 3231 ms 1
qwen/qwen3-235b-a22b-fp8 warming novita 100.00% 100.00% 100.00% 20s 100.00% 3284 ms 9566 ms 3284 ms 9566 ms 3
minimax/minimax-m2.5 warming parasail 100.00% 100.00% 100.00% 20s 100.00% 3287 ms 3423 ms 3287 ms 3423 ms 2
google/gemini-3.5-flash-lite warming google-vertex 100.00% 100.00% 100.00% 15s 100.00% 3288 ms 3592 ms 3288 ms 3592 ms 42 tok/s warming 7
google/gemini-3.5-flash-lite warming google-ai-studio 100.00% 100.00% 100.00% 15s 100.00% 3295 ms 3447 ms 3294 ms 3447 ms 5
z-ai/glm-5 warming gmi 100.00% 100.00% 100.00% 45s 100.00% 3313 ms 24717 ms 3312 ms 24717 ms 8
deepseek/deepseek-v3.1-terminus warming deepinfra 100.00% 100.00% 100.00% 20s 100.00% 3346 ms 3346 ms 3345 ms 3345 ms 1
qwen/qwen-2.5-7b-instruct warming together 100.00% 100.00% 100.00% 20s 100.00% 3354 ms 19561 ms 3354 ms 19561 ms 5
moonshotai/kimi-k2.5 warming digitalocean 100.00% 100.00% 100.00% 20s 100.00% 3358 ms 7628 ms 3357 ms 7628 ms 2
deepseek/deepseek-v3.2-exp warming siliconflow 100.00% 100.00% 100.00% 20s 100.00% 3370 ms 4697 ms 3370 ms 4696 ms 3
qwen/qwen3-235b-a22b-thinking-2507 warming venice 100.00% 100.00% 100.00% 45s 100.00% 3385 ms 3462 ms 3385 ms 3461 ms 3
deepseek/deepseek-v4-flash warming alibaba 100.00% 100.00% 100.00% 20s 100.00% 3404 ms 3404 ms 3404 ms 3404 ms 52 tok/s warming 1
Qwen/Qwen3-32B warming nebius 100.00% 100.00% 100.00% 20s 100.00% 3411 ms 3411 ms 3411 ms 3411 ms 1
moonshotai/kimi-k2.7-code warming alibaba 100.00% 100.00% 100.00% 20s 100.00% 3421 ms 3421 ms 3421 ms 3421 ms 1
deepseek/deepseek-v4-flash warming digitalocean 100.00% 100.00% 100.00% 20s 100.00% 3423 ms 5163 ms 3423 ms 5162 ms 20 tok/s warming 2
qwen/qwen3.7-max warming alibaba 100.00% 100.00% 100.00% 20s 100.00% 3445 ms 4513 ms 3444 ms 4513 ms 2
minimax/minimax-m2.5 warming siliconflow 100.00% 100.00% 100.00% 20s 100.00% 3454 ms 14429 ms 3454 ms 14429 ms 3
zai-org/glm-4.6 warming novita 100.00% 100.00% 100.00% 20s 100.00% 3467 ms 3467 ms 3467 ms 3467 ms 1
deepseek-ai/DeepSeek-V4-Pro warming nebius 100.00% 100.00% 100.00% 20s 100.00% 3489 ms 3489 ms 3489 ms 3489 ms 1
deepseek/deepseek-v4-pro warming digitalocean 100.00% 100.00% 100.00% 20s 100.00% 3489 ms 5364 ms 3489 ms 5363 ms 26 tok/s warming 6
z-ai/glm-5.2 warming venice 100.00% 100.00% 100.00% 45s 100.00% 3491 ms 4987 ms 3491 ms 4987 ms 34 tok/s warming 4
minimaxai/minimax-m1-80k warming novita 100.00% 100.00% 100.00% 20s 100.00% 3494 ms 3494 ms 3494 ms 3494 ms 1
xiaomimimo/mimo-v2.5-pro warming novita 100.00% 100.00% 100.00% 20s 100.00% 3510 ms 3510 ms 3510 ms 3510 ms 1
moonshotai/kimi-k3 warming kimi 100.00% 100.00% 100.00% 20s 100.00% 3516 ms 5564 ms 3515 ms 5563 ms 32 tok/s warming 4
deepseek/deepseek-v3.2 warming chutes 100.00% 100.00% 100.00% 20s 100.00% 3517 ms 8456 ms 3517 ms 8456 ms 6
qwen/qwen-plus-2025-09-11 warming alibaba 100.00% 100.00% 100.00% 20s 100.00% 3520 ms 3520 ms 3520 ms 3520 ms 1
qwen/qwen3.6-27b warming siliconflow 100.00% 100.00% 100.00% 20s 100.00% 3547 ms 3547 ms 3547 ms 3547 ms 1
meta-llama/llama-4-maverick warming parasail 100.00% 100.00% 100.00% 20s 100.00% 3548 ms 8946 ms 3548 ms 8946 ms 3
google/gemma-4-31b-turbo warming chutes 100.00% 100.00% 100.00% 20s 100.00% 3553 ms 15854 ms 3552 ms 15854 ms 5
qwen/qwen3.5-plus-2026-02-15 warming alibaba 100.00% 100.00% 100.00% 20s 100.00% 3561 ms 4123 ms 3560 ms 4123 ms 2
zai-org/glm-5 warming novita 100.00% 100.00% 100.00% 45s 100.00% 3563 ms 3563 ms 3562 ms 3562 ms 1
qwen/qwen3.7-plus warming alibaba 100.00% 100.00% 100.00% 20s 100.00% 3597 ms 3597 ms 3596 ms 3596 ms 1
thinkingmachines/inkling-small warming deepinfra 100.00% 100.00% 100.00% 45s 100.00% 3641 ms 3641 ms 3641 ms 3641 ms 63 tok/s warming 1
openai/gpt-oss-120b warming together 100.00% 100.00% 100.00% 20s 100.00% 3670 ms 3670 ms 3670 ms 3670 ms 129 tok/s warming 1
minimax/minimax-m3 warming fireworks 100.00% 100.00% 100.00% 20s 100.00% 3677 ms 3935 ms 3677 ms 3935 ms 106 tok/s warming 7
google/gemini-3-flash-preview warming atlas-cloud 100.00% 100.00% 100.00% 20s 100.00% 3680 ms 3680 ms 3680 ms 3680 ms 1
qwen/qwen3.6-35b-a3b warming novita 100.00% 100.00% 100.00% 20s 100.00% 3700 ms 3700 ms 3700 ms 3700 ms 1
qwen/qwen3.5-27b warming atlas-cloud 100.00% 100.00% 100.00% 20s 100.00% 3723 ms 3723 ms 3723 ms 3723 ms 1
minimax/minimax-m2 warming minimax 100.00% 100.00% 100.00% 20s 100.00% 3739 ms 15601 ms 3738 ms 15601 ms 9
zai-org/glm-4.6v warming novita 100.00% 100.00% 100.00% 20s 100.00% 3740 ms 3740 ms 3740 ms 3740 ms 1
kwaipilot/kat-coder-air-v2.5 warming atlas-cloud 100.00% 100.00% 100.00% 20s 100.00% 3762 ms 3762 ms 3762 ms 3762 ms 1
qwen/qwen3-coder-flash warming alibaba 100.00% 100.00% 100.00% 20s 100.00% 3776 ms 3776 ms 3775 ms 3775 ms 1
openai/gpt-oss-120b warming crusoe 100.00% 100.00% 100.00% 20s 100.00% 3787 ms 4457 ms 3787 ms 4457 ms 65 tok/s warming 5
openai/gpt-4 warming lightning 100.00% 100.00% 100.00% 20s 100.00% 3814 ms 12678 ms 3814 ms 12678 ms 4
inclusionai/ling-2.6-1t warming novita 100.00% 100.00% 100.00% 20s 100.00% 3869 ms 3869 ms 3869 ms 3869 ms 1
microsoft/wizardlm-2-8x22b warming novita 100.00% 100.00% 100.00% 20s 100.00% 3877 ms 3877 ms 3876 ms 3876 ms 1
qwen/qwen3-vl-235b-a22b-instruct warming parasail 100.00% 100.00% 100.00% 20s 100.00% 3877 ms 15083 ms 3877 ms 15083 ms 2
deepseek/deepseek-v4-flash-0731 warming siliconflow 100.00% 100.00% 100.00% 20s 100.00% 3879 ms 3879 ms 3878 ms 3878 ms 84 tok/s warming 3
minimax/minimax-m3 warming siliconflow 100.00% 100.00% 100.00% 20s 100.00% 3879 ms 3969 ms 3879 ms 3969 ms 40 tok/s warming 2
thinkingmachines/inkling warming together 100.00% 100.00% 100.00% 45s 100.00% 3882 ms 3882 ms 3882 ms 3882 ms 24 tok/s warming 1
moonshotai/kimi-k3 warming fireworks 100.00% 100.00% 100.00% 20s 100.00% 3928 ms 16568 ms 3927 ms 16568 ms 36 tok/s warming 7
moonshotai/kimi-k2.7-code warming novita 100.00% 100.00% 100.00% 20s 100.00% 3940 ms 3940 ms 3940 ms 3940 ms 25 tok/s warming 1
x-ai/grok-4.3 warming atlas-cloud 100.00% 100.00% 100.00% 20s 100.00% 3953 ms 3953 ms 3953 ms 3953 ms 1
deepseek/deepseek-r1-0528 warming novita 100.00% 100.00% 100.00% 45s 100.00% 3972 ms 3972 ms 3972 ms 3972 ms 1
deepseek/deepseek-v3.2 warming atlas-cloud 100.00% 100.00% 100.00% 20s 100.00% 3980 ms 3980 ms 3980 ms 3980 ms 1
qwen/qwen3.5-397b-a17b warming novita 100.00% 100.00% 100.00% 20s 100.00% 4010 ms 4080 ms 4010 ms 4080 ms 2
z-ai/glm-5v-turbo warming siliconflow 100.00% 100.00% 100.00% 45s 100.00% 4010 ms 9705 ms 4010 ms 9705 ms 6
z-ai/glm-5.2 warming chutes 100.00% 100.00% 100.00% 45s 100.00% 4049 ms 9240 ms 4049 ms 9240 ms 21 tok/s warming 5
openai/gpt-5-nano warming openai 100.00% 100.00% 100.00% 20s 100.00% 4117 ms 4835 ms 4117 ms 4835 ms 6
z-ai/glm-5 warming siliconflow 100.00% 100.00% 100.00% 45s 100.00% 4135 ms 4458 ms 4135 ms 4458 ms 3
openai/gpt-oss-20b warming parasail 100.00% 100.00% 100.00% 20s 100.00% 4137 ms 4187 ms 4137 ms 4187 ms 1 probe_config_error 3
qwen/qwen3.6-35b-a3b warming siliconflow 100.00% 100.00% 100.00% 20s 100.00% 4174 ms 4174 ms 4174 ms 4174 ms 1
openai/gpt-5.6-luna warming atlas-cloud 100.00% 100.00% 100.00% 45s 100.00% 4252 ms 4252 ms 4252 ms 4252 ms 64 tok/s warming 1
z-ai/glm-5.2 warming crusoe 100.00% 100.00% 100.00% 45s 100.00% 4316 ms 26272 ms 2584 ms 26271 ms 146 tok/s warming 5
google/gemini-3.1-pro-preview warming lightning 100.00% 100.00% 100.00% 20s 100.00% 4341 ms 6080 ms 4341 ms 6080 ms 46 tok/s warming 3
openai/gpt-4-turbo warming openai 100.00% 100.00% 100.00% 20s 100.00% 4357 ms 4357 ms 4357 ms 4357 ms 1
z-ai/glm-5v-turbo warming venice 100.00% 100.00% 100.00% 45s 100.00% 4670 ms 30080 ms 4670 ms 30079 ms 6
google/gemini-2.5-pro warming google-vertex 100.00% 100.00% 100.00% 20s 100.00% 4722 ms 5549 ms 4722 ms 5549 ms 7
moonshotai/kimi-k3 warming atlas-cloud 100.00% 100.00% 100.00% 20s 100.00% 5104 ms 5104 ms 5104 ms 5104 ms 21 tok/s warming 1
moonshotai/kimi-k3 warming gmi 100.00% 100.00% 100.00% 20s 100.00% 5519 ms 7035 ms 5519 ms 7035 ms 21 tok/s warming 9
anthropic/claude-fable-5 warming anthropic 100.00% 100.00% 100.00% 20s 100.00% 5624 ms 5624 ms 5624 ms 5624 ms 1
deepseek/deepseek-v4-flash warming siliconflow 100.00% 100.00% 100.00% 20s 100.00% 5820 ms 5820 ms 5819 ms 5819 ms 32 tok/s warming 1
meta-llama/Llama-3.3-70B-Instruct warming nebius 100.00% 100.00% 100.00% 20s 100.00% 6942 ms 15839 ms 6942 ms 15839 ms 6
qwen/qwen-2.5-72b-instruct warming novita 100.00% 100.00% 100.00% 20s 100.00% 7456 ms 7456 ms 7456 ms 7456 ms 1
minimax/minimax-m2.7 warming deepinfra 100.00% 100.00% 100.00% 20s 100.00% 8778 ms 8778 ms 8778 ms 8778 ms 1
qwen/qwen-mt-plus warming novita 100.00% 100.00% 100.00% 20s 100.00% 10959 ms 11239 ms 820 ms 11238 ms 3
qwen/qwen3.7-plus-2026-05-26 warming alibaba 100.00% 100.00% 100.00% 20s 100.00% 11343 ms 11343 ms 11343 ms 11343 ms 1
deepseek/deepseek-v3.2 warming deepinfra 100.00% 100.00% 100.00% 20s 100.00% 13567 ms 13567 ms 13567 ms 13567 ms 1
deepseek/deepseek-v4-flash warming atlas-cloud 100.00% 100.00% 100.00% 20s 100.00% 14794 ms 14794 ms 14794 ms 14794 ms 43 tok/s warming 1
moonshotai/kimi-k3 warming novita 100.00% 100.00% 100.00% 20s 100.00% 19657 ms 19657 ms 19657 ms 19657 ms 24 tok/s warming 1
openai/gpt-oss-120b warming siliconflow 100.00% 100.00% 0.00% 20s 100.00% 26205 ms 26205 ms 26204 ms 26204 ms 1
z-ai/glm-5.2-fast warming baseten 85.71% 85.71% 85.71% 45s 100.00% 3179 ms 5323 ms 3179 ms 5323 ms 70 tok/s warming 7
moonshotai/kimi-k2.6 warming baseten 85.71% 85.71% 85.71% 20s 100.00% 3440 ms 3969 ms 3440 ms 3968 ms 76 tok/s warming 7
qwen/qwen3.5-397b-a17b warming chutes 83.33% 83.33% 83.33% 20s 83.33% 2475 ms 4045 ms 2475 ms 4045 ms 6
z-ai/glm-4.5 warming zai 71.43% 83.33% 83.33% 20s 100.00% 3685 ms 5459 ms 3685 ms 5459 ms 1 router_error 6
meta-llama/llama-3.3-70b-instruct-fp8-fast warming cloudflare-workers-ai 75.00% 75.00% 75.00% 15s 100.00% 816 ms 2624 ms 816 ms 2624 ms 4
moonshotai/kimi-k3 warming siliconflow 75.00% 75.00% 75.00% 20s 75.00% 4012 ms 5081 ms 4012 ms 5081 ms 24 tok/s warming 4
moonshotai/kimi-k2.7-code warming baseten 66.67% 66.67% 66.67% 20s 100.00% 567 ms 1586 ms 567 ms 1586 ms 40 tok/s warming 3
deepseek/deepseek-v4-pro warming parasail 66.67% 66.67% 66.67% 20s 66.67% 1751 ms 3537 ms 1751 ms 3537 ms 53 tok/s warming 3
z-ai/glm-5.2 warming digitalocean 66.67% 66.67% 66.67% 45s 66.67% 5351 ms 9801 ms 5351 ms 9801 ms 41 tok/s warming 3
qwen/qwen3-vl-8b-instruct warming parasail 60.00% 60.00% 60.00% 20s 60.00% 3880 ms 15239 ms 3880 ms 15239 ms 5
zai-org/GLM-5.1 warming nebius 50.00% 50.00% 50.00% 45s 100.00% 4479 ms 4479 ms 4479 ms 4479 ms 2
nvidia/nemotron-3-120b-a12b warming cloudflare-workers-ai 50.00% 50.00% 50.00% 20s 100.00% 13273 ms 13273 ms 13272 ms 13272 ms 2
minimax/minimax-m3 warming parasail 50.00% 50.00% 0.00% 20s 50.00% 26905 ms 26905 ms 26905 ms 26905 ms 56 tok/s warming 2
qwen/qwen3-235b-a22b-2507 warming crusoe 40.00% 40.00% 40.00% 20s 40.00% 1431 ms 4486 ms 1431 ms 4486 ms 5
baidu/cobuddy warming novita 0.00% 0.00% 0.00% 20s 0.00% 1
deepseek/deepseek-v4-flash warming deepinfra 28 tok/s warming 0
deepseek/deepseek-v4-flash warming novita 39 tok/s warming 0
deepseek/deepseek-v4-flash-0731 warming atlas-cloud 0.00% 0.00% 0.00% 20s 100.00% 2
deepseek/deepseek-v4-flash-0731 warming deepinfra 63 tok/s warming 0
deepseek/deepseek-v4-flash-0731 warming novita 34 tok/s warming 0
deepseek/deepseek-v4-pro warming alibaba 36 tok/s warming 0
deepseek/deepseek-v4-pro warming deepinfra 73 tok/s warming 0
deepseek/deepseek-v4-pro warming novita 54 tok/s warming 0
deepseek/deepseek-v4-pro warming together 69 tok/s warming 7 probe_config_error 0
google/gemini-3.1-pro-preview warming atlas-cloud 71 tok/s warming 0
google/gemma-3-12b-it warming novita 0.00% 0.00% 0.00% 20s 100.00% 2
google/gemma-4-26b-a4b-it warming parasail 0.00% 0.00% 0.00% 20s 0.00% 1
google/gemma-4-31b-it warming deepinfra 54 tok/s warming 0
google/gemma-4-31b-it warming novita 40 tok/s warming 0
google/gemma-4-31b-it warming together 53 tok/s warming 0
inclusionai/ling-2.6-flash warming novita 0.00% 0.00% 0.00% 20s 0.00% 1
inclusionai/ling-3.0-flash warming novita 68 tok/s warming 0
mindai/macaron-v1-tall warming novita 0.00% 0.00% 0.00% 20s 100.00% 1
mindai/macaron-v1-venti warming novita 12 tok/s warming 0
minimax/minimax-m3 warming deepinfra 5 tok/s warming 0
minimax/minimax-m3 warming novita 83 tok/s warming 0
minimax/minimax-m3 warming together 88 tok/s warming 6 probe_config_error 0
moonshotai/kimi-k2.6 warming deepinfra 35 tok/s warming 0
moonshotai/kimi-k2.6 warming novita 23 tok/s warming 0
moonshotai/kimi-k3 warming nebius 65 tok/s warming 0
nvidia/nemotron-3-ultra-550b-a55b warming nebius 112 tok/s warming 0
openai/gpt-4.1-mini warming atlas-cloud 99 tok/s warming 0
qwen/qwen-plus-character warming alibaba 33 tok/s warming 0
qwen/qwen3-vl-flash-2026-01-22 warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 1
qwen/qwen3.5-397b-a17b warming alibaba 0.00% 0.00% 0.00% 20s 100.00% 2
qwen/qwen3.7-flash warming alibaba 114 tok/s warming 0
tencent/hy3 warming atlas-cloud 104 tok/s warming 0
tencent/hy3 warming novita 76 tok/s warming 0
thedrummer/skyfall-36b-v2 warming parasail 0.00% 0.00% 0.00% 20s 0.00% 1 router_error 4
thinkingmachines/inkling warming deepinfra 67 tok/s warming 0
x-ai/grok-4.5 warming atlas-cloud 50 tok/s warming 0
z-ai/glm-5.2 warming alibaba 31 tok/s warming 0
z-ai/glm-5.2 warming deepinfra 42 tok/s warming 0
z-ai/glm-5.2 warming novita 35 tok/s warming 0
Workspace access

Sign in

Choose a sign in method. New email and OAuth accounts include $0.10 in starter credit; wallet-only accounts start at $0.

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