Mistral Large 3 2512

by Mistralmistralai/mistral-large-2512

  • Text
  • No route yet
  • Released

LLMCompare cannot run Mistral Large 3 2512 yet.No route to this model is configured on this site yet. Its prices and parameters are listed below for reference.

See the models that can be run now

Mistral Large 3 2512 at a glance

Context length
262,144 tokens
Maximum output
209,715 tokens
Accepts
Text, Image, File
Returns
Text
Features
JSON outputTool callingPrompt cachingImage input
Reasoning effort levels
Not supported
Released
1 Dec 2025
Knowledge cutoff
Not published

Model facts synced from the OpenRouter model list on 21 Oct 2026.

Mistral Large 3 2512 pricing by route

A route is the service LLMCompare calls to reach the model. Mistral Large 3 2512 has 1 route. Prices are in US dollars.

Prices of Mistral Large 3 2512 on each route
RouteOn LLMCompareInputper 1M tokensOutputper 1M tokensCache readper 1M tokensPrice verified onSource
OpenRouterDefaultNot configured$0.50$1.50$0.05openrouter.ai/mistralai/mistral-large-2512

The cost shown in an LLMCompare report is calculated from these prices as they were at the time of the run.

Cost calculator

Estimate what a batch of calls to Mistral Large 3 2512 costs. The starting numbers are examples. Change them to match your task.

Part of the input tokens above, billed at the cache read price.

Cost per call
$0.0013
2 credits
Cost of 100 calls
$0.125
200 credits

Calculated from the OpenRouter prices verified on 21 Oct 2026. Credits are the cost plus a 20% service fee, at $0.001 per credit, rounded up for each call, with a minimum of 1 per call. A real run is charged for the usage the provider reports.

Parameters you can set

These are the parameters LLMCompare can set when it calls the model through OpenRouter.

Parameters of Mistral Large 3 2512
ParameterTypeRange or optionsDefault
temperatureNumber0 to 2in steps of 0.1Provider default
top_pNumber0 to 1in steps of 0.05Provider default
max_tokensInteger1 to 209,715Provider default
seedInteger-2,147,483,648 to 4,294,967,295Provider default
response_formatOne oftextjson_objectProvider default

About Mistral Large 3 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.

Description as published for this model. LLMCompare has not edited it.

Models to compare with Mistral Large 3 2512

Text models from the same provider and models at the nearest price. The order is not a ranking.

Models to compare with Mistral Large 3 2512
Add to comparisonModelContextMax outputInput priceper 1M tokensOutput priceper 1M tokensFeaturesReleasedOn LLMCompare
Devstral 2 2512Mistralmistralai/devstral-2512262k210k$0.40$2.00JSONToolsCacheNo route yet
Mistral Medium 3.1Mistralmistralai/mistral-medium-3.1131k105k$0.40$2.00JSONToolsCacheVisionNo route yet
Mistral Medium 3Mistralmistralai/mistral-medium-3131k105k$0.40$2.00JSONToolsCacheVisionNo route yet
Morph V3 FastMorphmorph/morph-v3-fast262k131k$0.80$1.20JSONNo route yet
GPT-4.1 MiniOpenAIopenai/gpt-4.1-mini1.05M32.8k$0.40$1.60JSONToolsCacheVisionNo route yet
SonarPerplexityperplexity/sonar127k114k$1.00$1.00VisionNo route yet

Questions about Mistral Large 3 2512

How much does Mistral Large 3 2512 cost?
On the OpenRouter route, Mistral Large 3 2512 costs $0.50 per 1 million input tokens and $1.50 per 1 million output tokens, in US dollars. Input tokens that Mistral Large 3 2512 reads from the prompt cache cost $0.05 per 1 million tokens. LLMCompare verified this price on 21 Oct 2026.
What is the context length of Mistral Large 3 2512?
Mistral Large 3 2512 has a context length of 262,144 tokens and returns up to 209,715 output tokens in one call.
What inputs does Mistral Large 3 2512 accept?
Mistral Large 3 2512 accepts these inputs: Text, Image, File. Mistral Large 3 2512 returns: Text.
Can I test Mistral Large 3 2512 on my own data?
Not yet. LLMCompare lists the prices and parameters of Mistral Large 3 2512, but no route to Mistral Large 3 2512 is configured on LLMCompare, so it cannot be selected for an evaluation.