Baseten
Explore Baseten models on TrustedRouter with current routes, token pricing, policy sources, privacy posture, regional availability, and API support.
Basetenbaseten
No provider claim
| Provider | Baseten |
|---|---|
| Provider website | https://www.baseten.co/ |
| Models | 12 public models |
| Prepaid routes | 12 |
| BYOK routes | 12 |
| 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
54 samplesContinuously 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 | 2209 ms |
|---|---|
| Effective throughput | 130 tok/s n=11 |
| Uptime | 100.00% |
| Model | p50 TTFT | p50 TTFB | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| openai/gpt-oss-120b | 1046 ms | 1045 ms | 195 tok/s n=1 | 100.00% | — | 1 |
| moonshotai/kimi-k2.7-code | 1254 ms | 1254 ms | 121 tok/s n=1 | 100.00% | — | 2 |
| thinkingmachines/inkling-1m | 1487 ms | 1487 ms | 176 tok/s n=1 | 100.00% | — | 5 |
| moonshotai/kimi-k2.6 | 1832 ms | 1831 ms | 217 tok/s n=1 | 100.00% | — | 3 |
| moonshotai/kimi-k3 | 1972 ms | 1972 ms | 57 tok/s n=2 | 100.00% | — | 6 |
| z-ai/glm-5.2-fast | 2033 ms | 2033 ms | 114 tok/s n=1 | 100.00% | — | 5 |
| nvidia/nemotron-3-ultra-550b-a55b | 2209 ms | 2209 ms | 133 tok/s n=1 | 100.00% | — | 7 |
| thinkingmachines/inkling-small | 2549 ms | 2548 ms | 189 tok/s n=1 | 100.00% | — | 6 |
| z-ai/glm-4.7 | 2605 ms | 2605 ms | — | 100.00% | — | 5 |
| deepseek/deepseek-v4-flash-0731 | 2839 ms | 2838 ms | 130 tok/s n=1 | 100.00% | — | 6 |
| deepseek/deepseek-v4-pro | 3540 ms | 3540 ms | — | 100.00% | — | 3 |
| z-ai/glm-5.2 | 4268 ms | 4268 ms | 51 tok/s n=1 | 100.00% | — | 5 |
Baseten performance history · Full provider & model leaderboard.
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-0731DeepSeek: DeepSeek V4 Flash 0731 |
— | 1,048,576 | 2 | $0.1365/1M | $0.273/1M | prepaid BYOK |
deepseek/deepseek-v4-proDeepSeek: DeepSeek V4 Pro |
IQ 117#25 | 1,048,576 | 2 | $1.827/1M | $3.654/1M | prepaid BYOK |
moonshotai/kimi-k2.6MoonshotAI: Kimi K2.6 |
IQ 119#19 | 262,144 | 2 | $0.9975/1M | $4.2/1M | prepaid BYOK |
moonshotai/kimi-k2.7-codeMoonshotAI: Kimi K2.7 Code |
IQ 118#22 | 262,144 | 2 | $0.9975/1M | $4.2/1M | prepaid BYOK |
moonshotai/kimi-k3MoonshotAI: Kimi K3 |
IQ 123#14 | 1,048,576 | 2 | $3.15/1M | $15.75/1M | prepaid BYOK |
nvidia/nemotron-3-ultra-550b-a55bNVIDIA: Nemotron 3 Ultra |
— | 512,288 | 2 | $0.63/1M | $2.52/1M | prepaid BYOK |
openai/gpt-oss-120bOpenAI: gpt-oss-120b |
IQ 105#53 | 131,072 | 2 | $0.105/1M | $0.525/1M | prepaid BYOK |
thinkingmachines/inkling-1mInkling |
— | 1,048,576 | 2 | $1.05/1M | $4.2525/1M | prepaid BYOK |
thinkingmachines/inkling-smallThinking Machines: Inkling Small |
IQ 105#54 | 524,288 | 2 | $0.525/1M | $1.26/1M | prepaid BYOK |
z-ai/glm-4.7Z.ai: GLM 4.7 |
IQ 103#59 | 204,800 | 2 | $0.63/1M | $2.31/1M | prepaid BYOK |
z-ai/glm-5.2Z.ai: GLM 5.2 |
IQ 120#16 | 1,048,576 | 2 | $1.47/1M | $4.62/1M | prepaid BYOK |
z-ai/glm-5.2-fastGLM 5.2 Fast on Fireworks |
— | 1,048,576 | 2 | $2.205/1M | $6.93/1M | prepaid BYOK |
Questions
Does Baseten have zero data retention?
TrustedRouter does not currently mark Baseten as provider-level zero data retention. Use trustedrouter/zdr or provider.min_privacy=zdr to select a different eligible route, and review the linked policy source for changes.
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 12 public Baseten models, with live pricing, route count, context length, measured performance when available, and links to each model's provider and benchmark pages.