OpenAI compatible API · Attested · Public status

Parasail performance

Measured TTFT, TTFB, effective throughput, uptime, and sampled model routes for Parasail.

Verify gateway
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.

parasail

58 samples

Provider overview

Continuously sampled provider performance. TrustedRouter reports unsupported route and probe-configuration rows separately from provider downtime. Prompt and output content is not stored.

p50 TTFT2766 ms
p95 TTFT15083 ms
p50 TTFB2044 ms
Effective throughput55 tok/s n=8
Uptime84.48%

Measured model routes

Modelp50 TTFTp50 TTFBEffective throughputUptimeConfig excludedAvailability samples
meta-llama/llama-3.3-70b-instruct 621 ms 621 ms 100.00% 2
qwen/qwen2.5-vl-72b-instruct 821 ms 821 ms 100.00% 4
deepseek/deepseek-v4-flash 853 ms 853 ms 49 tok/s n=1 100.00% 4
arcee-ai/trinity-large-thinking 1180 ms 1180 ms 100.00% 2
qwen/qwen3-coder-next 1358 ms 1357 ms 100.00% 3
openai/gpt-oss-120b 1597 ms 1597 ms 61 tok/s n=2 100.00% 1
moonshotai/kimi-k2.6 1952 ms 1952 ms 100.00% 2
z-ai/glm-5.2 2766 ms 60 tok/s n=1 100.00% 11
thedrummer/cydonia-24b-v4.1 2972 ms 2972 ms 100.00% 1
google/gemma-4-31b-it 3203 ms 3202 ms 27 tok/s n=2 100.00% 3
minimax/minimax-m2.5 3287 ms 3287 ms 100.00% 2
meta-llama/llama-4-maverick 3548 ms 3548 ms 100.00% 3
qwen/qwen3-vl-235b-a22b-instruct 3877 ms 3877 ms 100.00% 2
openai/gpt-oss-20b 4137 ms 4137 ms 100.00% 1 probe_config_error 3
qwen/qwen3-vl-8b-instruct 3880 ms 3880 ms 60.00% 5
google/gemma-4-26b-a4b-it 688 ms 688 ms 50.00% 2
deepseek/deepseek-v4-pro 1751 ms 1751 ms 53 tok/s n=1 50.00% 2
minimax/minimax-m3 26905 ms 26905 ms 56 tok/s n=1 50.00% 2
thedrummer/skyfall-36b-v2 0.00% 1 router_error 4
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.