OpenAI compatible API. Attested gateway. Public status.

Baseten

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

Verify gateway

1 URLbase_url migration

100smodels and routes

0prompt logs by default

`baseten`

No provider claim

All providers

Provider	Baseten
Models	11 public models
Prepaid routes	11
BYOK routes	11
Zero data retention	not claimed
Confidential compute	not claimed
Provider E2EE	not claimed
Policy note	No provider-ZDR claim is tracked here. Baseten's inference and security documentation are linked for users who need to review API data handling. Policy source

Measured performance

267 samples

Continuously sampled across Baseten'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	4214 ms
Throughput	36 tok/s
Uptime	99.63%

Model	p50 TTFT	p50 TTFB	Throughput	Uptime	Config excluded	Samples
nvidia/nvidia-nemotron-3-ultra-550b-a55b	1895 ms	1895 ms	—	100.00%	—	5
moonshotai/kimi-k2.5	1932 ms	1931 ms	—	100.00%	—	6
moonshotai/kimi-k2.7-code	2323 ms	2323 ms	79 tok/s	100.00%	—	66
deepseek/deepseek-v4-pro	2831 ms	2830 ms	15 tok/s	100.00%	—	6
z-ai/glm-4.7	3414 ms	3413 ms	—	100.00%	—	7
nvidia/nemotron-120b-a12b	3525 ms	3525 ms	—	100.00%	—	5
moonshotai/kimi-k2.6	4214 ms	4214 ms	30 tok/s	100.00%	—	74
openai/gpt-oss-120b	4603 ms	4602 ms	—	100.00%	—	7
z-ai/glm-5	6384 ms	6384 ms	—	100.00%	—	11
z-ai/glm-5.2	10585 ms	10584 ms	36 tok/s	98.59%	—	71
z-ai/glm-5.1	13387 ms	13387 ms	—	100.00%	—	9

Full provider & model leaderboard.

Provider models

Models served by Baseten.

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 performance api	IQ 108#30	1,048,576	2	$1.914/1M	$3.828/1M	prepaid BYOK
`moonshotai/kimi-k2.5` MoonshotAI: Kimi K2.5 benchmarks performance api	IQ 109#28	262,144	2	$0.66/1M	$3.3/1M	prepaid BYOK
`moonshotai/kimi-k2.6` MoonshotAI: Kimi K2.6 benchmarks performance api	IQ 117#10	262,144	2	$1.045/1M	$4.4/1M	prepaid BYOK
`moonshotai/kimi-k2.7-code` MoonshotAI: Kimi K2.7 Code benchmarks performance api	IQ 116#12	262,144	2	$1.045/1M	$4.4/1M	prepaid BYOK
`nvidia/nemotron-120b-a12b` Nemotron 120B A12B benchmarks performance api	—	202,800	2	$0.33/1M	$0.825/1M	prepaid BYOK
`nvidia/nvidia-nemotron-3-ultra-550b-a55b` NVIDIA Nemotron 3 Ultra 550B A55B benchmarks performance api	—	202,800	2	$0.66/1M	$2.64/1M	prepaid BYOK
`openai/gpt-oss-120b` OpenAI: gpt-oss-120b benchmarks performance api	IQ 94#56	131,072	2	$0.11/1M	$0.55/1M	prepaid BYOK
`z-ai/glm-4.7` Z.ai: GLM 4.7 benchmarks performance api	IQ 102#44	202,752	2	$0.66/1M	$2.42/1M	prepaid BYOK
`z-ai/glm-5` Z.ai: GLM 5 benchmarks performance api	IQ 107#31	204,800	2	$1.045/1M	$3.465/1M	prepaid BYOK
`z-ai/glm-5.1` Z.ai: GLM 5.1 benchmarks performance api	IQ 112#20	202,752	2	$1.43/1M	$4.73/1M	prepaid BYOK
`z-ai/glm-5.2` GLM 5.2 benchmarks performance api	IQ 116#11	1,048,576	2	$1.54/1M	$4.84/1M	prepaid BYOK