All models
Mistral AI
Mistral Nemo fastruns locally
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,...
Input / 1M
$0.029
USD per million tokens
Output / 1M
$0.030
USD per million tokens
Est. cost / token
$0.000000029
$0.029 per 1M, 3:1 mix
Context window
131K
max output 16K
Major features
Open weightsJSON schemaTools
Task suitability (heuristic 1–5, not a benchmark)
- coding3
- reasoning2
- math2
- summarization4
- extraction4
- classification4
- chat3
- creative3
- translation4
- vision1
- long context3
- agentic3
Run it locally
Will it run on my machine? →ollama run mistral-nemo| Quantization | Quality | Memory needed (8K ctx) |
|---|---|---|
| Q2_K | poor | 7.2 GB |
| Q3_K_M | fair | 8.1 GB |
| Q4_K_Mrecommended | good | 9.7 GB |
| Q5_K_M | very good | 11 GB |
| Q6_K | excellent | 12.4 GB |
| Q8_0 | near-lossless | 15.5 GB |
| F16 | lossless | 27.5 GB |
Estimates.
Price history
| Recorded | Input | Output | Cached | Source |
|---|---|---|---|---|
| 2026-11-05 03:20 | $0.029 | $0.030 | — | openrouter |
A row is added whenever a sync detects a price change. Vendor pricing source
Pricing (USD per 1M tokens)
- Input
- $0.029
- Output
- $0.030
- Blended (3:1)
- $0.029
Details
- Company
- Mistral AI
- Version
- —
- Family
- Mistral
- Released
- 2024-07-19
- Parameters
- 12.2B
- Max output
- 16K
- Open weights
- Yes
- Inputs
- text
- Last synced
- 21 min ago