mistralai / text-generation API-only released 2025-12-01

Mistral Large 3 2512

Name: Mistral Large 3 2512
Price: 0.5 USD
Author: mistralai

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

Output / 1M

$1.50

Context

262.1K

AA Intelligence

9.3

Closed weights — available only as a hosted API text + image + file → text View on OpenRouter ↗

Pricing

via OpenRouter · USD per 1M tokens · synced 2026-10-24

$0.50

input / 1M

$1.50

output / 1M

$0.05

cached input / 1M

$2.00

1M in + 1M out

:batch variant $0.25 in · $0.75 out

Context window: 262,144 tokens
Max output: 209,715 tokens
Providers: 1
Cheapest provider: Mistral · $0.50 / $1.50
Best throughput: —
AA Intelligence / Coding / Agentic: 9.3 / 20.1 / 1

✓ Tool calling ✗ Reasoning ✓ Structured outputs ✓ Image input ✓ File input ✗ Audio input ✓ Prompt caching

Price history

tracking started — chart appears after 7 days of snapshots (6 recorded)

Current: $0.50 input · $1.50 output per 1M tokens

Benchmarks

Third-party indices as published through OpenRouter — Artificial Analysis and Design Arena. Not measured by us.

AA Intelligence Index: 9.3
AA Coding Index: 20.1
AA Agentic Index: 1

Design Arena

CategoryEloWin %Rank

3d 1101 46.9% #89

asciiart 1069 40.3% #66

codecategories 1142 47.6% #92

dataviz 1136 45.7% #87

gamedev 1080 41.5% #105

svg 993 38% #87

uicomponent 1099 43% #94

website 1162 49.5% #87

Providers

1 provider · per 1M tokens · last 30 min metrics

Provider	Quant	Context	Input	Output	Uptime	Tok/s
Mistral	unknown	262.1K	$0.50	$1.50	100%	—
Mistral	unknown	262.1K	$0.55	$1.65	100%	—

Provider data from OpenRouter's endpoint listing, refreshed daily.

Specifications

Organisation: mistralai
Released on OpenRouter: 2025-12-01
Context window: 262,144 tokens
Max output: 209,715 tokens
Input: text, image, file
Output: text
Tokenizer: Mistral
Moderated by provider: No
OpenRouter id: mistralai/mistral-large-2512

Compare with

Popular comparisons

Llama-4-Maverick-17B-128E-Instruct open $0.30 Qwen3-Coder-Next open $0.29 Qwen3-VL-30B-A3B-Thinking open $0.47 Mistral Medium 3.1 $0.80 Qwen3-Next-80B-A3B-Instruct open $0.34 Qwen3-Coder-30B-A3B-Instruct open $0.12 DeepSeek-V3-0324 open $0.50 Mistral Medium 3 $0.80 GPT-4.1 Mini $0.70 Sonar $1.00

Browse

All API-only models Open-weights alternatives Best value via API

Prices, context and providers from the public OpenRouter API, snapshotted daily; benchmark indices from Artificial Analysis. See /methodology.