Mistral Large 3 2512
Mistral · Open weights · Released Dec 1, 2025 · mistralai/mistral-large-2512
Best $0.50 in / $1.50 out via Mistral
262K contextVisionToolsStructured outputPrompt cachingOpen weights
Available from 2 providersUSD / MTOK · PRICES 16 MINUTES AGO · SPEED 2 DAYS AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
| PROVIDER | INPUT | OUTPUT | CACHE | CONTEXT | QUANT | TTFT | TPS | UPTIME |
|---|---|---|---|---|---|---|---|---|
| $0.50 | $1.50 | $0.05 | 262K | — | 0.91s | 77 tok/s | 100.0% | |
| $0.55 | $1.65 | $0.055 | 262K | — | — | — | 100.0% |
TTFT/TPS: median (P50) over trailing 504h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · methodology v1.1 · measured 2 days ago
SERVE THIS MODEL AND NOT LISTED? LIST YOUR INFERENCE →
Pricing variants · USD / MTok in / out
STANDARD
$0.50 / $1.50
per MTok in / out
CACHE READ $0.05
Recent changesRSS ↗
Oct 5, 2026endpoint removed · primeintellect3 → 2
Oct 4, 2026endpoint added · primeintellect2 → 3
Sep 25, 2026model added
About
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.
Specifications
Context window262,144
Max output209,715
Modalities intext, image, file
Modalities outtext
LicenseOpen weights
ReleasedDec 1, 2025
TokenizerMistral
WeightsHugging Face ↗
Open weights
Related
Embed badge
[](https://modelindex.ai/models/mistralai/mistral-large-2512)Sources
OpenRouter API16 minutes ago
AGGREGATORHugging Face16 minutes ago
COMMUNITYModelIndex benchmarks2 days ago
MEASUREDVerified 16 minutes ago · list prices, not negotiated rates.