Baseten
Explore Baseten models on TrustedRouter with current routes, token pricing, policy sources, privacy posture, regional availability, and API support.
Basetenbaseten
These privacy labels describe Baseten, the upstream model provider. ZDR is a retention policy; verified confidential inference additionally requires attested provider compute and end-to-end encryption.
| Provider | Baseten |
|---|---|
| API operator country | US Legal home of the API operator, not an inference-location guarantee. |
| Headquarters | Not verified |
| Routing status | Active |
| Provider website | https://www.baseten.co/ |
| Models | 11 public models |
| Credits routes | 11 |
| Zero data retention | yes All routes |
| Verified confidential inference | Not verified |
| 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 |
Inference locations
Provider API declarations are also available on each model's endpoint API. Direct chat and Responses replies separate advertised availability from serving location in usage.inference_location; the actual serving region remains unknown when not reported.
Where the upstream GPUs execute the model, not the provider's headquarters, API ingress, or data storage. ZDR and confidential inference do not by themselves restrict geography.
- Declared countries or regions
- Not verified
No inference-location declaration has been verified for this provider. - Can locations change?
- Not verified. Do not assume that the serving location is fixed.
- Provider region pinning
- Not verified.
- Pinning through TrustedRouter
- No verified provider-specific location pin documented here.
- Infrastructure declaration
- Inference location not verified; no country-specific residency commitment.
- Evidence
- Not yet reviewed.
Provider selection alone is not a region pin. TrustedRouter's US provider filter selects company jurisdiction, not GPU location. A regional gateway hostname does not pin a downstream GPU. For a binding residency requirement, confirm the model, region, failover scope and enforced controls before sending sensitive data.
Measured performance
35 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 | 1369 ms |
|---|---|
| Effective throughput | 105 tok/s n=7 |
| Uptime | 100.00% |
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| z-ai/glm-5.3-fast | 818 ms | — | 100.00% | — | 2 |
| z-ai/glm-5.2-fast | 954 ms | 93 tok/s n=1 | 100.00% | — | 4 |
| deepseek/deepseek-v4-flash-0731 | 1035 ms | — | 100.00% | — | 2 |
| deepseek/deepseek-v4-pro-0813 | 1056 ms | 71 tok/s n=2 | 100.00% | — | 7 |
| z-ai/glm-5.3 | 1369 ms | — | 100.00% | — | 4 |
| openai/gpt-oss-120b | 1382 ms | — | 100.00% | — | 3 |
| moonshotai/kimi-k3 | 1778 ms | 148 tok/s n=2 | 100.00% | — | 4 |
| deepseek/deepseek-v4.1-flash | 1814 ms | 105 tok/s n=1 | 100.00% | — | 2 |
| z-ai/glm-5.3-flash | 1912 ms | — | 100.00% | — | 3 |
| z-ai/glm-5.2 | 2063 ms | 112 tok/s n=1 | 100.00% | — | 4 |
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 | Input | Cached input | Output |
|---|---|---|---|---|---|
deepseek/deepseek-v4-flash-0731DeepSeek: DeepSeek V4 Flash 0731 |
— | 1,048,576 | $0.13715/1M | $0.02954/1M | $0.2743/1M |
deepseek/deepseek-v4-pro-0813DeepSeek V4 Pro 0813 |
— | 1,048,576 | $1.3926/1M | $0.13926/1M | $4.1778/1M |
deepseek/deepseek-v4.1-flashDeepSeek: DeepSeek V4.1 Flash |
IQ 124#23 | 1,048,576 | $0.3165/1M | $0.01/1M | $1.266/1M |
moonshotai/kimi-k3MoonshotAI: Kimi K3 |
IQ 128#14 | 1,048,576 | $3.165/1M | $0.3165/1M | $15.825/1M |
nvidia/nemotron-3-ultra-550b-a55bNVIDIA: Nemotron 3 Ultra |
— | 262,144 | $0.633/1M | $0.1266/1M | $2.532/1M |
openai/gpt-oss-120bOpenAI: gpt-oss-120b |
IQ 97#117 | 131,072 | $0.1055/1M | $0.1055/1M | $0.5275/1M |
z-ai/glm-5.2Z.ai: GLM 5.2 |
IQ 119#40 | 1,048,576 | $1.477/1M | $0.1477/1M | $4.642/1M |
z-ai/glm-5.2-fastGLM 5.2 Fast |
— | 1,048,576 | $2.2155/1M | $0.22155/1M | $6.963/1M |
z-ai/glm-5.3Z.ai: GLM 5.3 |
IQ 127#16 | 1,048,576 | $1.477/1M | $0.1477/1M | $4.642/1M |
z-ai/glm-5.3-fastGLM 5.3 Fast on Fireworks |
— | 1,048,576 | $2.2155/1M | $0.22155/1M | $6.963/1M |
z-ai/glm-5.3-flashZ.ai: GLM 5.3 Flash |
IQ 120#39 | 1,048,576 | $0.15825/1M | $0.03165/1M | $0.5275/1M |
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 11 public Baseten models, with live pricing, route count, context length, measured performance when available, and links to each model's provider and benchmark pages.