SambaNova
Explore SambaNova models on TrustedRouter with current routes, token pricing, policy sources, privacy posture, regional availability, and API support.
SambaNovasambanova
These privacy labels describe SambaNova, the upstream model provider. Confidential requires all three: verified provider compute, end-to-end encryption and explicit zero data retention. Account and billing metadata are outside the content-retention claim.
| Provider | SambaNova |
|---|---|
| API operator country | Not verified Legal home of the API operator, not an inference-location guarantee. |
| Headquarters | Not verified |
| Routing status | Active |
| Provider website | https://sambanova.ai/ |
| Models | 6 public models |
| Credits routes | 6 |
| Zero data retention | not claimed |
| Verified confidential inference | Not verified |
| Policy note | No contractual zero-retention, confidential-compute, or E2EE claim is tracked for TrustedRouter's SambaNova account. This route is Standard. 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
27 samplesContinuously sampled across SambaNova'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 | 2809 ms |
|---|---|
| Effective throughput | 116 tok/s n=3 |
| Uptime | 100.00% |
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| openai/gpt-oss-120b | 738 ms | — | 100.00% | — | 3 |
| meta-llama/llama-3.3-70b-instruct | 982 ms | — | 100.00% | — | 4 |
| minimax/minimax-m3 | 2131 ms | 116 tok/s n=2 | 100.00% | — | 3 |
| deepseek/deepseek-v3.2 | 2809 ms | — | 100.00% | — | 8 |
| deepseek/deepseek-v3.1 | 3866 ms | — | 100.00% | — | 6 |
| google/gemma-4-31b-it | 6497 ms | 23 tok/s n=1 | 100.00% | — | 3 |
SambaNova performance history · Full provider & model leaderboard.
Models served by SambaNova.
Each row links to pricing, provider, benchmark, and API pages for the model.
| Model | AI IQ | Context | Input | Cached input | Output |
|---|---|---|---|---|---|
deepseek/deepseek-v3.1deepseek-ai/DeepSeek-V3.1 |
IQ 98#125 | 163,840 | $3.165/1M | Not published | $4.7475/1M |
deepseek/deepseek-v3.2DeepSeek: DeepSeek V3.2 |
IQ 102#105 | 163,840 | $3.165/1M | Not published | $4.7475/1M |
google/gemma-4-31b-itGoogle: Gemma 4 31B |
IQ 101#110 | 262,144 | $0.4009/1M | Not published | $1.21325/1M |
meta-llama/llama-3.3-70b-instructMeta: Llama 3.3 70B Instruct |
— | 131,072 | $0.633/1M | Not published | $1.266/1M |
minimax/minimax-m3MiniMax: MiniMax M3 |
IQ 115#54 | 524,288 | $0.633/1M | $0.0633/1M | $2.532/1M |
openai/gpt-oss-120bOpenAI: gpt-oss-120b |
IQ 98#126 | 131,072 | $0.2321/1M | Not published | $0.62245/1M |
Questions
Does SambaNova have zero data retention?
TrustedRouter does not currently mark SambaNova 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 SambaNova end-to-end encrypted?
TrustedRouter does not currently mark SambaNova 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 SambaNova models are available through TrustedRouter?
This page currently lists 6 public SambaNova models, with live pricing, route count, context length, measured performance when available, and links to each model's provider and benchmark pages.