OpenAI compatible API · Attested · Public status

Baseten

Explore Baseten models on TrustedRouter with current routes, token pricing, policy sources, privacy posture, regional availability, and API support.

Verify gateway

Onebase URL to migrate

100sof models and routes

0prompt or output logs. Always.

Basetenbaseten

No logs

All providers

Provider	Baseten
Provider website	https://www.baseten.co/
Models	13 public models
Prepaid routes	13
BYOK routes	12
Zero data retention	yes
Confidential compute	not claimed
Provider E2EE	not claimed
Policy note	Baseten states that it does not store synchronous Model API inputs or outputs by default. TrustedRouter uses the synchronous Model API path; Baseten documents separate temporary input storage for async inference. Policy source

Measured performance

53 samples

Continuously sampled across Baseten's routed models: p50 TTFT, effective throughput, and success rate. Effective throughput uses provider-reported output tokens over complete request time. Unsupported route and probe-configuration rows are separated from provider downtime. No prompt or output content stored.

p50 TTFT	1929 ms
Effective throughput	62 tok/s n=12
Uptime	100.00%

Model	p50 TTFT	p50 TTFB	Effective throughput	Uptime	Config excluded	Availability samples
deepseek/deepseek-v4-pro	833 ms	832 ms	—	100.00%	—	3
openai/gpt-oss-120b	977 ms	976 ms	—	100.00%	—	4
thinkingmachines/inkling-1m	997 ms	996 ms	144 tok/s n=1	100.00%	—	3
moonshotai/kimi-k2.6	1122 ms	1121 ms	59 tok/s n=1	100.00%	—	4
nvidia/nemotron-3-ultra-550b-a55b	1339 ms	1338 ms	40 tok/s n=1	100.00%	—	2
deepseek/deepseek-v4-flash-0731	1879 ms	1879 ms	73 tok/s n=1	100.00%	—	2
deepseek/deepseek-v4-pro-0813	1929 ms	1929 ms	62 tok/s n=2	100.00%	—	9
moonshotai/kimi-k3	1979 ms	1979 ms	66 tok/s n=2	100.00%	—	3
z-ai/glm-5.2	2268 ms	2268 ms	46 tok/s n=1	100.00%	—	5
thinkingmachines/inkling-small	2350 ms	2350 ms	52 tok/s n=1	100.00%	—	4
moonshotai/kimi-k2.7-code	2448 ms	2448 ms	58 tok/s n=1	100.00%	—	4
z-ai/glm-4.7	3913 ms	3913 ms	—	100.00%	—	5
z-ai/glm-5.2-fast	4185 ms	4185 ms	157 tok/s n=1	100.00%	—	5

Baseten performance history · 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-flash-0731` DeepSeek: DeepSeek V4 Flash 0731 providers pricing	—	1,048,576	2	$0.13715/1M	$0.2743/1M	prepaid BYOK
`deepseek/deepseek-v4-pro` DeepSeek: DeepSeek V4 Pro benchmarks providers pricing	IQ 117#31	1,048,576	2	$1.8357/1M	$3.6714/1M	prepaid BYOK
`deepseek/deepseek-v4-pro-0813` DeepSeek V4 Pro 0813 providers pricing	—	1,048,576	1	$1.3926/1M	$4.1778/1M	prepaid
`moonshotai/kimi-k2.6` MoonshotAI: Kimi K2.6 benchmarks providers pricing	IQ 119#23	262,144	2	$1.00225/1M	$4.22/1M	prepaid BYOK
`moonshotai/kimi-k2.7-code` MoonshotAI: Kimi K2.7 Code benchmarks providers pricing	IQ 118#28	262,144	2	$1.00225/1M	$4.22/1M	prepaid BYOK
`moonshotai/kimi-k3` MoonshotAI: Kimi K3 providers pricing	IQ 123#16	1,048,576	2	$3.165/1M	$15.825/1M	prepaid BYOK
`nvidia/nemotron-3-ultra-550b-a55b` NVIDIA: Nemotron 3 Ultra providers pricing	—	512,288	2	$0.633/1M	$2.532/1M	prepaid BYOK
`openai/gpt-oss-120b` OpenAI: gpt-oss-120b providers pricing	IQ 105#61	131,072	2	$0.1055/1M	$0.5275/1M	prepaid BYOK
`thinkingmachines/inkling-1m` Inkling providers pricing	—	1,048,576	2	$1.055/1M	$4.27275/1M	prepaid BYOK
`thinkingmachines/inkling-small` Thinking Machines: Inkling Small providers pricing	IQ 106#59	524,288	2	$0.5275/1M	$1.266/1M	prepaid BYOK
`z-ai/glm-4.7` Z.ai: GLM 4.7 providers pricing	IQ 103#66	204,800	2	$0.633/1M	$2.321/1M	prepaid BYOK
`z-ai/glm-5.2` Z.ai: GLM 5.2 benchmarks providers pricing	IQ 120#19	1,048,576	2	$1.477/1M	$4.642/1M	prepaid BYOK
`z-ai/glm-5.2-fast` GLM 5.2 Fast on Fireworks providers pricing	—	1,048,576	2	$2.2155/1M	$6.963/1M	prepaid BYOK

Questions

Does Baseten have zero data retention?

TrustedRouter records Baseten as supporting provider-level zero data retention based on the policy source linked on this page. This is a provider policy claim, separate from TrustedRouter's content-stateless real-time gateway and from end-to-end confidential compute.

Is Baseten end-to-end encrypted?

TrustedRouter does not currently mark Baseten as end-to-end encrypted at the provider boundary. The TrustedRouter gateway is still attested, but the selected provider normally receives the request in order to run the model. Use trustedrouter/e2e for the stronger route requirement.

Which Baseten models are available through TrustedRouter?

This page currently lists 13 public Baseten models, with live pricing, route count, context length, measured performance when available, and links to each model's provider and benchmark pages.