Mistral Large 3

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.

mistral/mistral-large-2512

Organization: Mistral
Family: mistral-large
Providers: 12
Context: 262,144
Output limit: 262,144
Knowledge: 2024-11
Release: 2025-12-02
Updated: 2025-12-02
Weights: Open
Input: text, image
Output: text
Capabilities: Tools, Temperature

Providers

Compare every cataloged offer for this model, including its provider, route, token limits, price, and capabilities.

14 offers · USD per million tokens

Provider	Model ID	Context	Output	Input / output · 1M	Reasoning	Tools	Structured	Details
Amazon Bedrock	mistral.mistral-large-3-675b-instruct	262,144	8,192	$0.50 / $1.50	No	Yes	Yes	View
AnyAPI	mistralai/mistral-large-2512	262,144	262,144	— / —	No	Yes	—	View
Cortecs	mistral-large-2512	256,000	256,000	$0.613 / $1.838	No	Yes	Yes	View
DevPass (LLM Gateway)	mistral-large-2512	262,144	262,144	$0.50 / $1.50	No	Yes	—	View
Eden AI	mistral/mistral-large-2512	262,144	262,144	$0.50 / $1.50	No	Yes	Yes	View
Kilo Gateway	mistralai/mistral-large-2512	262,144	209,715	$0.50 / $1.50	No	Yes	Yes	View
LLM Gateway	mistral/mistral-large-2512	262,144	262,144	$0.50 / $1.50	No	No	No	View
Merge Gateway	mistral/mistral-large-2512	256,000	256,000	$0.50 / $1.50	No	Yes	Yes	View
Mistralvia OpenRouter	mistralai/mistral-large-2512 unknown	262,144	209,715	$0.55 / $1.65	No	Yes	Yes	View
Mistralvia OpenRouter	mistralai/mistral-large-2512 unknown	262,144	209,715	$0.50 / $1.50	No	Yes	Yes	View
PrimeIntellectvia OpenRouter	mistralai/mistral-large-2512 unknown	262,144	209,715	$0.50 / $1.50	No	Yes	Yes	View
Opper	mistral-large-2512	256,000	8,192	$0.50 / $1.50	No	Yes	Yes	View
Pioneer	mistral-large-3	256,000	131,072	$0.50 / $1.50	No	Yes	—	View
Tempr Gateway	mistral/mistral-large-2512	262,144	262,144	$0.50 / $1.50	No	Yes	—	View

Prices and limits apply to each offer. A dash means the value is not provided. OpenRouter offers show the hosting provider and routing channel separately.

Pricing

Compare token rates and cache charges across available routes and hosting configurations.

USD per million tokens

Input from$0.50Per 1M input tokens

Output from$1.50Per 1M output tokens

Available offers14Across 12 providers

Lowest listed input and output prices across the offers above; they may belong to different providers. These are base rates, before conditional pricing, discounts or additional fees.

Endpoint price comparisonLatest observed snapshot · 3 lowest-priced configurations

InputOutput

Mistralmistral/zdr

$0.50$1.50

PrimeIntellectprimeintellect

$0.50$1.50

Mistralmistral/eu

$0.55$1.65

mistralai/mistral-large-2512Observed Oct 4, 2026, 11:31 AM UTC

Input: $0.50
Output: $1.50
Cache read: $0.05

Hosting prices through OpenRouter All endpoints and cache rates

Endpoint	Input / 1M	Output / 1M	Cache read / 1M	Cache write / 1M
Mistralmistral/eu	$0.55	$1.65	$0.055	—
Mistralmistral/zdr	$0.50	$1.50	$0.05	—
PrimeIntellectprimeintellect	$0.50	$1.50	—	—

Each row is a hosting configuration. Open an offer in Providers for its full pricing conditions and additional fees. Endpoint observations may differ from the routing catalog's base price.

Performance

Review reported latency and output-throughput percentiles from the latest observed rolling window.

Latest 30-minute observation

Time to first token · milliseconds

Latency distributionRolling 30-minute snapshot · 3 endpoints

P50P75P90P99

Mistralmistral/eu

657–6,902.35 ms

Mistralmistral/zdr

497–47,022.28 ms

PrimeIntellectprimeintellect

1,014–7,494.28 ms

All latency percentiles 3 endpoints

Endpoint	P50	P75	P90	P99
Mistralmistral/eu	657 ms	1,288.25 ms	2,248 ms	6,902.35 ms
Mistralmistral/zdr	497 ms	673.5 ms	1,319.5 ms	47,022.28 ms
PrimeIntellectprimeintellect	1,014 ms	1,891.5 ms	2,628.6 ms	7,494.28 ms

Output throughput · tokens per second

Throughput distributionRolling 30-minute snapshot · 3 endpoints

P50P75P90P99

Mistralmistral/eu

52–95.26 t/s

Mistralmistral/zdr

50–97 t/s

PrimeIntellectprimeintellect

46–90 t/s

All throughput percentiles 3 endpoints

Endpoint	P50	P75	P90	P99
Mistralmistral/eu	52 t/s	73.75 t/s	80 t/s	95.26 t/s
Mistralmistral/zdr	50 t/s	60.25 t/s	81 t/s	97 t/s
PrimeIntellectprimeintellect	46 t/s	62 t/s	77 t/s	90 t/s

Percentiles describe the observed request distribution. These are snapshots of a rolling window, not a historical time series.

Uptime

Compare successful request rates across the latest 5-minute, 30-minute, and 24-hour observations.

Successful requests by window

Availability by endpointCurrent overlapping windows · 3 endpoints

Endpoint5 minutes30 minutes24 hours

Mistralmistral/euObserved Oct 4, 2026, 11:31 AM UTC

100%

99.39%

99.9%

Mistralmistral/zdrObserved Oct 4, 2026, 11:31 AM UTC

100%

99.74%

99.91%

PrimeIntellectprimeintellectObserved Oct 4, 2026, 11:31 AM UTC

100%

99.45%

99.7%

Reported by OpenRouter at the time of collection; rate-limited requests are excluded. A dash means no measurement was reported. This is not a live availability check.

Benchmarks

Review attributed evaluation results on each source's original scale.

External evaluations

mistralai/mistral-large-2512Observed Oct 4, 2026, 11:31 AM UTC

Benchmark profileArtificial Analysis · shared source scale from 0 to 30

Coding

20.1

Agentic

Intelligence

9.3

Design Arena	Category	Elo	Win rate	Rank
models	3d	1,115	46.9%	79
models	asciiart	1,080	40.3%	63
models	codecategories	1,148	47.6%	79
models	dataviz	1,145	45.7%	78
models	gamedev	1,093	41.5%	90
models	svg	992	38%	84
models	uicomponent	1,109	43%	85
models	website	1,169	49.5%	75

Sources: Artificial Analysis and Design Arena, via OpenRouter. Scores retain their original scales and are not OpenAI Suite ratings.

Detailed evaluations

Evaluation	Configuration	Source	Results	Details
models · svg	Mistral Large 3 (2512)mistralai/mistral-large-2512	Design Arena	992 Elo	Details
models · dataviz	Mistral Large 3 (2512)mistralai/mistral-large-2512	Design Arena	1,145 Elo	Details
models · gamedev	Mistral Large 3 (2512)mistralai/mistral-large-2512	Design Arena	1,093 Elo	Details
models · 3d	Mistral Large 3 (2512)mistralai/mistral-large-2512	Design Arena	1,115 Elo	Details
models · website	Mistral Large 3 (2512)mistralai/mistral-large-2512	Design Arena	1,169 Elo	Details
Composite indices	Mistral Large 3mistralai/mistral-large-2512	Artificial Analysis	Intelligence 9.3 · Coding 20.1 · Agentic 1	Details
models · uicomponent	Mistral Large 3 (2512)mistralai/mistral-large-2512	Design Arena	1,109 Elo	Details
models · codecategories	Mistral Large 3 (2512)mistralai/mistral-large-2512	Design Arena	1,148 Elo	Details
models · asciiart	Mistral Large 3 (2512)mistralai/mistral-large-2512	Design Arena	1,080 Elo	Details

Sources: Artificial Analysis, Design Arena and OpenRouter. Evaluation configurations and scales differ; results are not interchangeable. Updated Oct 4, 2026.

Technical details & API

Explore specifications, supported parameters, reasoning controls, and API identifiers for each OpenRouter route.

Current route specifications

mistralai/mistral-large-2512Observed Oct 4, 2026, 11:31 AM UTC

Context: 262,144
Maximum output: 209,715
Tokenizer: Mistral
Input: text, image, file
Output: text
Moderation: No
Added to OpenRouter: 2025-12-01

Base URLhttps://openrouter.ai/api/v1

Model IDmistralai/mistral-large-2512

Version IDmistralai/mistral-large-2512

Supported parameters

frequency_penalty
max_tokens
presence_penalty
response_format
seed
stop
structured_outputs
temperature
tool_choice
tools
top_p

Default parameters

temperature: 0.06

Frequently asked questions

Answers based on the model metadata and serving offers currently in the catalog.

How much does Mistral Large 3 cost?

Listed rates start at $0.50 per million input tokens and $1.50 per million output tokens. Prices vary by provider and configuration; see Pricing for details.

Which providers offer Mistral Large 3?

There are 14 cataloged offers across 12 providers. Compare model IDs, prices and limits in Providers.

What is the context window?

The cataloged model context is 262,144 tokens. Each serving endpoint may apply a different limit.

Does it support tools and structured output?

Tool calling: Yes. Structured output: Not reported. Support can vary by endpoint.

Resources

Hugging Face ↗

Catalog history · 2 recorded revisions

Metadata observations since this model was first cataloged. These are not model release versions.

Sep 14, 2026 · 37ecfe55fd9b
Sep 12, 2026 · a34449405f96