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
233 t/s
Median latency
341ms
Median price / 1M
$0.231
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
- M2.7MiniMax38.9
- V3.2DeepSeek25.1
- gpt-oss-120bOpenAI24.1
View as table
| Model | Intelligence |
|---|---|
| M2.7 (MiniMax) | 38.9 |
| V3.2 (DeepSeek) | 25.1 |
| gpt-oss-120b (OpenAI) | 24.1 |
Fastest output
Median tokens per second
- gpt-oss-120bOpenAI773 t/s
- M2.7MiniMax307 t/s
- 234 t/s
- Gemma 4 31BGoogle232 t/s
- V3.2DeepSeek100 t/s
- V3.1DeepSeek63 t/s
View as table
| Model | Tokens/s |
|---|---|
| gpt-oss-120b (OpenAI) | 773 |
| M2.7 (MiniMax) | 307 |
| Llama 3.3 70B Instruct (Meta) | 234 |
| Gemma 4 31B (Google) | 232 |
| V3.2 (DeepSeek) | 100 |
| V3.1 (DeepSeek) | 63 |
Full catalogue
All 6 models on SambaNova
Filter by creator
6 of 6 models| M2.7 MiniMaxopen | 38.9 | $0.10 |
| V3.2 DeepSeekopen | 25.1 | $0.05 |
| gpt-oss-120b OpenAIopen | 24.1 | $0.02 |
| Gemma 4 31B Googleopen | — | $0.03 |
| V3.1 DeepSeekopen | — | $0.09 |
| Llama 3.3 70B Instruct Metaopen | — | $0.01 |