The Orchestrator › Models › Mistral AI
Mistral AI: Mistral: Mistral Nemo
A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese,...
Specifications
| Provider | Mistral AI |
| Model ID | mistralai/mistral-nemo |
| Context window | 131K tokens (131,072) |
| Modalities | text → text |
| Tokenizer | Mistral |
| Router sources | OpenRouter, Vercel AI Gateway |
| Released | 2024-07-19 |
| Tracked since | 2026-11-14 |
| Popularity | Not in the ranked set |
| Reasoning | — |
Pricing (per million tokens)
| Variant | Source | API ID | Input | Output | Context |
|---|---|---|---|---|---|
| standard | OpenRouter | mistralai/mistral-nemo | $0.029 | $0.03 | 131K |
| standard | Vercel AI Gateway | mistralai/mistral-nemo | $0.029 | $0.03 | 131K |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $0.029 | $0.03 | 131K |
| 2026-11-14 | $0.029 | $0.03 | 131K |
Capabilities
Agentic tool useStructured outputsNo training on inputs (attested)
Trust flags come from TrustedRouter's per-provider attestations.
Supported parameters
frequency_penalty, logit_bias, logprobs, max_tokens, min_p, presence_penalty, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p