All models
Mistral AI
Ministral 3 8B 2512 fastruns locally
mistral/ministral-8b-2512
A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.
Input / 1M
$0.15
USD per million tokens
Output / 1M
$0.15
USD per million tokens
Est. cost / token
$0.00000015
$0.15 per 1M, 3:1 mix
Context window
262K
max output 262K
Major features
VisionOpen weightsCachingJSON schemaTools
Task suitability (heuristic 1–5, not a benchmark)
- coding3
- reasoning2
- math2
- summarization4
- extraction4
- classification4
- chat3
- creative3
- translation4
- vision3
- long context3
- agentic3
Run it locally
Will it run on my machine? →| Quantization | Quality | Memory needed (8K ctx) |
|---|---|---|
| Q2_K | poor | 5.6 GB |
| Q3_K_M | fair | 6.3 GB |
| Q4_K_Mrecommended | good | 7.4 GB |
| Q5_K_M | very good | 8.4 GB |
| Q6_K | excellent | 9.4 GB |
| Q8_0 | near-lossless | 11.7 GB |
| F16 | lossless | 20.4 GB |
Estimates.
Price history
| Recorded | Input | Output | Cached | Source |
|---|---|---|---|---|
| 2026-11-05 03:20 | $0.15 | $0.15 | $0.015 | litellm+openrouter |
A row is added whenever a sync detects a price change. Vendor pricing source
Pricing (USD per 1M tokens)
- Input
- $0.15
- Output
- $0.15
- Cached input
- $0.015
- Blended (3:1)
- $0.15
Details
- Company
- Mistral AI
- Version
- —
- Family
- Ministral
- Released
- 2025-12-02
- Parameters
- 8.9B
- Max output
- 262K
- Open weights
- Yes
- Inputs
- image, text
- Last synced
- 27 min ago