All models
Mistral AI
Mistral Large 3 2512 fast
mistral/mistral-large-2512
Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.
Input / 1M
$0.50
USD per million tokens
Output / 1M
$1.50
USD per million tokens
Est. cost / token
$0.00000075
$0.75 per 1M, 3:1 mix
Context window
262K
max output 262K
Major features
VisionCachingJSON schemaTools
Task suitability (heuristic 1–5, not a benchmark)
- coding3
- reasoning2
- math2
- summarization4
- extraction4
- classification4
- chat3
- creative3
- translation4
- vision3
- long context3
- agentic3
Price history
| Recorded | Input | Output | Cached | Source |
|---|---|---|---|---|
| 2026-11-05 03:20 | $0.50 | $1.50 | $0.050 | litellm+openrouter |
A row is added whenever a sync detects a price change. Vendor pricing source
Pricing (USD per 1M tokens)
- Input
- $0.50
- Output
- $1.50
- Cached input
- $0.050
- Blended (3:1)
- $0.75
Details
- Company
- Mistral AI
- Version
- —
- Family
- Mistral
- Released
- 2025-12-01
- Parameters
- Undisclosed
- Max output
- 262K
- Open weights
- No
- Inputs
- file, image, text
- Last synced
- 27 min ago