OpenAI compatible API · Attested · Public status

Together performance

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

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

together

36 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 TTFT1861 ms
p95 TTFT18603 ms
p50 TTFB2213 ms
Effective throughput72 tok/s n=11
Uptime100.00%

Measured model routes

Modelp50 TTFTp50 TTFBEffective throughputUptimeConfig excludedAvailability samples
moonshotai/kimi-k2.6 1000 ms 1000 ms 100.00% 2
nvidia/nemotron-3-ultra-550b-a55b 1008 ms 1007 ms 99 tok/s n=2 100.00% 2
moonshotai/kimi-k2.7-code 1696 ms 1696 ms 100.00% 5
moonshotai/kimi-k3 1707 ms 1707 ms 39 tok/s n=2 100.00% 5
openai/gpt-oss-20b 1861 ms 1860 ms 100.00% 7
z-ai/glm-5.2 2263 ms 2263 ms 100.00% 8
meta-llama/llama-3.3-70b-instruct 2632 ms 2632 ms 100.00% 1
qwen/qwen-2.5-7b-instruct 3354 ms 3354 ms 100.00% 4
google/gemma-3n-e4b-it 3527 ms 3527 ms 100.00% 1
openai/gpt-oss-120b 3670 ms 3670 ms 98 tok/s n=2 100.00% 1
deepseek/deepseek-v4-pro 72 tok/s n=1 5 probe_config_error 0
google/gemma-4-31b-it 42 tok/s n=1 0
minimax/minimax-m3 88 tok/s n=1 6 probe_config_error 0
thinkingmachines/inkling 56 tok/s n=2 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.