All models
Mistral AI
Devstral 2 2512 fastruns locally
mistral/devstral-2512
Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window. Devstral 2 supports exploring...
Input / 1M
$0.40
USD per million tokens
Output / 1M
$2.00
USD per million tokens
Est. cost / token
$0.0000008
$0.80 per 1M, 3:1 mix
Context window
262K
max output 210K
Major features
Open weightsCachingJSON schemaTools
Task suitability (heuristic 1–5, not a benchmark)
- coding4
- reasoning2
- math2
- summarization4
- extraction4
- classification4
- chat3
- creative3
- translation4
- vision1
- long context3
- agentic3
Run it locally
Will it run on my machine? →| Quantization | Quality | Memory needed (8K ctx) |
|---|---|---|
| Q2_K | poor | 59 GB |
| Q3_K_M | fair | 68.2 GB |
| Q4_K_Mrecommended | good | 84.2 GB |
| Q5_K_M | very good | 97.4 GB |
| Q6_K | excellent | 112 GB |
| Q8_0 | near-lossless | 143 GB |
| F16 | lossless | 267 GB |
Estimates.
Price history
| Recorded | Input | Output | Cached | Source |
|---|---|---|---|---|
| 2026-11-05 03:20 | $0.40 | $2.00 | $0.040 | openrouter |
A row is added whenever a sync detects a price change. Vendor pricing source
Pricing (USD per 1M tokens)
- Input
- $0.40
- Output
- $2.00
- Cached input
- $0.040
- Blended (3:1)
- $0.80
Details
- Company
- Mistral AI
- Version
- —
- Family
- Devstral
- Released
- 2025-12-09
- Parameters
- 125B
- Max output
- 210K
- Open weights
- Yes
- Inputs
- file, text
- Last synced
- 27 min ago