OpenAI compatible API · Attested · Public status

Together

Together models on TrustedRouter with prices, routes, policy notes, and source links.

Verify gateway

Onebase URL to migrate

100sof models and routes

Noneprompt logs by default

`together`

No logs

All providers

Provider	Together
Models	18 public models
Prepaid routes	18
BYOK routes	18
Zero data retention	yes
Confidential compute	not claimed
Provider E2EE	not claimed
Policy note	Tracked as provider ZDR. Together documents that inference inputs and outputs are not stored by default; temporary prompt caching may be used for performance, and sharing content for training is opt-in. Policy source

Measured performance

128 samples

Continuously sampled across Together's routed models — p50 TTFT, throughput, and success rate. Unsupported route and probe-configuration rows are separated from provider downtime. No prompt or output content stored.

p50 TTFT	5270 ms
Throughput	—
Uptime	98.44%

Model	p50 TTFT	p50 TTFB	Throughput	Uptime	Config excluded	Samples
moonshotai/kimi-k2.6	2432 ms	2431 ms	—	100.00%	—	10
moonshotai/kimi-k2.7-code	2570 ms	2570 ms	—	100.00%	—	13
openai/gpt-oss-120b	3349 ms	3349 ms	—	88.89%	—	9
qwen/qwen-2.5-7b-instruct	3693 ms	3693 ms	—	100.00%	—	9
meta-llama/llama-3.3-70b-instruct	4483 ms	4483 ms	—	100.00%	—	16
nvidia/nemotron-3-ultra-550b-a55b	5270 ms	5269 ms	—	100.00%	—	9
openai/gpt-oss-20b	5579 ms	5578 ms	—	100.00%	—	14
thinkingmachines/inkling	5994 ms	5994 ms	—	100.00%	—	9
prism-ml/ternary-bonsai-27b	7821 ms	7821 ms	—	100.00%	—	14
z-ai/glm-5.2	8581 ms	8581 ms	—	90.91%	—	11
google/gemma-3n-e4b-it	9337 ms	9337 ms	—	100.00%	—	14

Together performance history · Full provider & model leaderboard.

Provider models

Models served by Together.

Each row links to pricing, provider, benchmark, and API pages for the model.

Model	AI IQ	Context	Endpoints	Prompt	Completion	Routes
`deepseek/deepseek-v4-pro` DeepSeek: DeepSeek V4 Pro benchmarks providers pricing	IQ 114#27	1,048,576	2	$1.827/1M	$3.654/1M	prepaid BYOK
`google/gemma-3n-e4b-it` Google: Gemma 3n 4B providers pricing	—	32,768	2	$0.063/1M	$0.126/1M	prepaid BYOK
`google/gemma-4-31b-it` Google: Gemma 4 31B providers pricing	IQ 101#65	262,144	2	$0.4095/1M	$1.0185/1M	prepaid BYOK
`intfloat/multilingual-e5-large-instruct` Multilingual E5 Large Instruct providers pricing	—	512	2	$0.021/1M	selected route	prepaid BYOK
`meta-llama/llama-3.3-70b-instruct` Meta: Llama 3.3 70B Instruct benchmarks providers pricing	—	131,072	2	$1.092/1M	$1.092/1M	prepaid BYOK
`minimax/minimax-m2.7` MiniMax: MiniMax M2.7 providers pricing	IQ 107#49	204,800	2	$0.315/1M	$1.26/1M	prepaid BYOK
`minimax/minimax-m3` MiniMax: MiniMax M3 benchmarks providers pricing	IQ 112#37	1,048,576	2	$0.315/1M	$1.26/1M	prepaid BYOK
`moonshotai/kimi-k2.6` MoonshotAI: Kimi K2.6 benchmarks providers pricing	IQ 119#19	262,144	2	$1.26/1M	$4.725/1M	prepaid BYOK
`moonshotai/kimi-k2.7-code` MoonshotAI: Kimi K2.7 Code benchmarks providers pricing	IQ 117#20	262,144	2	$0.9975/1M	$4.2/1M	prepaid BYOK
`nvidia/nemotron-3-ultra-550b-a55b` NVIDIA: Nemotron 3 Ultra providers pricing	—	512,288	2	$0.63/1M	$3.78/1M	prepaid BYOK
`openai/gpt-oss-120b` OpenAI: gpt-oss-120b providers pricing	IQ 103#57	131,072	2	$0.1575/1M	$0.63/1M	prepaid BYOK
`openai/gpt-oss-20b` OpenAI: gpt-oss-20b providers pricing	IQ 100#68	131,072	2	$0.0525/1M	$0.21/1M	prepaid BYOK
`pearl-ai/gemma-4-31b-it` Pearl-ai Gemma-4-31B-it-pearl providers pricing	IQ 101#65	262,144	2	$0.294/1M	$0.903/1M	prepaid BYOK
`prism-ml/ternary-bonsai-27b` Ternary Bonsai 27B providers pricing	—	262,144	2	$0.01/1M	$0.01/1M	prepaid BYOK
`qwen/qwen-2.5-7b-instruct` Qwen: Qwen2.5 7B Instruct providers pricing	—	32,768	2	$0.315/1M	$0.315/1M	prepaid BYOK
`qwen/qwen3.5-9b` Qwen: Qwen3.5-9B providers pricing	IQ 93#88	262,144	2	$0.1785/1M	$0.2625/1M	prepaid BYOK
`thinkingmachines/inkling` Thinking Machines: Inkling providers pricing	IQ 106#51	524,288	2	$1.05/1M	$4.2525/1M	prepaid BYOK
`z-ai/glm-5.2` Z.ai: GLM 5.2 benchmarks providers pricing	IQ 120#16	1,048,576	2	$1.47/1M	$4.62/1M	prepaid BYOK