Mistral AI · mistral-nemo family
Efficient Mistral-NVIDIA open model for multilingual chat and local deployment
Provider-specific prices and limits stay separate from canonical model facts.
| Provider | Provider model ID | Input | Output | Context | Output limit |
|---|---|---|---|---|---|
| GitHub Models | mistral-ai/mistral-nemo | $0 / 1M | $0 / 1M | 128,000 | 8,192 |
| Mistral | mistral-nemo | $0.15 / 1M | $0.15 / 1M | 128,000 | 128,000 |
| Azure Cognitive Services | mistral-nemo | $0.15 / 1M | $0.15 / 1M | 128,000 | 128,000 |
Attachments
No
Reasoning
No
Tool calling
Yes
Structured output
Unknown
Temperature
Yes
| Azure |
| mistral-nemo |
| $0.15 / 1M |
| $0.15 / 1M |
| 128,000 |
| 128,000 |
| Helicone | mistral-nemo | $20 / 1M | $40 / 1M | 128,000 | 16,400 |
| Vercel AI Gateway | mistral/mistral-nemo | $0.15 / 1M | $0.15 / 1M | 128,000 | 128,000 |
| Kilo Gateway | mistralai/mistral-nemo | $0.02 / 1M | $0.04 / 1M | 131,072 | 16,384 |
| OpenRouter | mistralai/mistral-nemo | $0.019 / 1M | $0.03 / 1M | 131,072 | 16,384 |
| NovitaAI | mistralai/mistral-nemo | $0.04 / 1M | $0.17 / 1M | 60,288 | 16,000 |