Inference provider
SambaNova
6 models served. Speed, latency and price below are medians across this provider's catalogue, not per-endpoint measurements.
Models served
6
Median output speed
158 t/s
Median latency
267ms
Median price / 1M
$0.41
Catalogue
Strongest and fastest on this provider
What the catalogue looks like at the top end, on the two axes that usually decide the choice.
Highest Intelligence Index
Among models this provider serves
- MiniMax M3MiniMax29.2
- V3.2DeepSeek16.0
- gpt-oss-120bOpenAI11.6
View as table
| Model | Intelligence |
|---|---|
| MiniMax M3 (MiniMax) | 29.2 |
| V3.2 (DeepSeek) | 16.0 |
| gpt-oss-120b (OpenAI) | 11.6 |
Fastest output
Median tokens per second
- gpt-oss-120bOpenAI641 t/s
- Gemma 4 31BGoogle193 t/s
- 190 t/s
- V3.1DeepSeek126 t/s
- MiniMax M3MiniMax115 t/s
- V3.2DeepSeek64 t/s
View as table
| Model | Tokens/s |
|---|---|
| gpt-oss-120b (OpenAI) | 641 |
| Gemma 4 31B (Google) | 193 |
| Llama 3.3 70B Instruct (Meta) | 190 |
| V3.1 (DeepSeek) | 126 |
| MiniMax M3 (MiniMax) | 115 |
| V3.2 (DeepSeek) | 64 |
Full catalogue
All 6 models on SambaNova
Filter by creator
6 of 6 models| MiniMax M3 MiniMaxopen | 29.2 | $0.11 |
| V3.2 DeepSeekopen | 16.0 | $0.08 |
| gpt-oss-120b OpenAIopen | 11.6 | $0.06 |
| Gemma 4 31B Googleopen | — | $0.04 |
| V3.1 DeepSeekopen | — | $0.09 |
| Llama 3.3 70B Instruct Metaopen | — | $0.05 |