AI Observatory / Model Radar
Mistral / mistralai/mistral-nemo
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,...
131,072
Context
N/A
Max output
$0.02 / 1M
Prompt price
2024-07-19
Created
01 / Snapshot
Pricing, context, modalities, and parameters.
Model Radar detail pages stay neutral and operator-readable: core metadata first, then workflow fit.
| Provider | Mistral | Input modalities | text |
|---|---|---|---|
| Output modalities | text | Prompt price | $0.02 / 1M |
| Completion price | $0.03 / 1M | Request price | N/A |
| Context length | 131,072 | Max completion tokens | N/A |
| 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 | ||
Best for
mistralai/mistral-nemo
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,...
High-volume usage
Coding workflows
tool-capable
low-cost
03 / Colophon
Routes and exits.
Each model page stays simple: overview, compare, related models, then back to the public hub.