SambaNova
Explore SambaNova models on TrustedRouter with current routes, token pricing, policy sources, privacy posture, regional availability, and API support.
SambaNovasambanova
No provider claim
These privacy labels describe SambaNova, the upstream model provider. ZDR is a retention policy; verified confidential inference additionally requires attested provider compute and end-to-end encryption.
| Provider | SambaNova |
|---|---|
| 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 |
Measured performance
18 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 | 2302 ms |
|---|---|
| Effective throughput | 222 tok/s n=1 |
| Uptime | 88.89% |
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| meta-llama/llama-3.3-70b-instruct | 959 ms | — | 100.00% | — | 4 |
| deepseek/deepseek-v3.2 | 2042 ms | — | 75.00% | — | 4 |
| google/gemma-4-31b-it | 2302 ms | — | 66.67% | — | 3 |
| minimax/minimax-m2.7 | 3665 ms | — | 100.00% | — | 4 |
| deepseek/deepseek-v3.1 | 3736 ms | — | 100.00% | — | 2 |
| openai/gpt-oss-120b | 3767 ms | 222 tok/s n=1 | 100.00% | — | 1 |
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 V3.1 |
IQ 95#105 | 131,072 | $3.165/1M | Not published | $4.7475/1M |
deepseek/deepseek-v3.2DeepSeek: DeepSeek V3.2 |
IQ 103#77 | 163,840 | $3.165/1M | Not published | $4.7475/1M |
google/gemma-4-31b-itGoogle: Gemma 4 31B |
IQ 103#80 | 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-m2.7MiniMax: MiniMax M2.7 |
IQ 107#72 | 196,608 | $0.633/1M | $0.0633/1M | $2.532/1M |
openai/gpt-oss-120bOpenAI: gpt-oss-120b |
IQ 98#99 | 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.