Mistral Medium 3

by Mistralmistralai/mistral-medium-3

  • Text
  • No route yet
  • Released
  • Knowledge cutoff 31 March 2025

LLMCompare cannot run Mistral Medium 3 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 Medium 3 at a glance

Context length
131,072 tokens
Maximum output
104,857 tokens
Accepts
Text, Image, File
Returns
Text
Features
JSON outputTool callingPrompt cachingImage input
Reasoning effort levels
Not supported
Released
7 May 2025
Knowledge cutoff
31 March 2025

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

Mistral Medium 3 pricing by route

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

Prices of Mistral Medium 3 on each route
RouteOn LLMCompareInputper 1M tokensOutputper 1M tokensCache readper 1M tokensPrice verified onSource
OpenRouterDefaultNot configured$0.40$2.00$0.04openrouter.ai/mistralai/mistral-medium-3

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 Medium 3 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
$0.0014
2 credits
Cost of 100 calls
$0.14
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 Medium 3
ParameterTypeRange or optionsDefault
temperatureNumber0 to 2in steps of 0.1Provider default
top_pNumber0 to 1in steps of 0.05Provider default
max_tokensInteger1 to 104,857Provider default
seedInteger-2,147,483,648 to 4,294,967,295Provider default
response_formatOne oftextjson_objectProvider default

About Mistral Medium 3

Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost...

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

Models to compare with Mistral Medium 3

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

Models to compare with Mistral Medium 3
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 Large 3 2512Mistralmistralai/mistral-large-2512262k210k$0.50$1.50JSONToolsCacheVisionNo route yet
Aion-2.0AionLabsaion-labs/aion-2.0131k32.8k$0.80$1.60JSONToolsCacheNo route yet
GLM 4.5VZ.aiz-ai/glm-4.5v65.5k16.4k$0.60$1.80JSONToolsCacheVisionNo route yet
Aion-RP 1.0 (8B)AionLabsaion-labs/aion-rp-llama-3.1-8b32.8k29.5k$0.80$1.60—No route yet

Questions about Mistral Medium 3

How much does Mistral Medium 3 cost?
On the OpenRouter route, Mistral Medium 3 costs $0.40 per 1 million input tokens and $2.00 per 1 million output tokens, in US dollars. Input tokens that Mistral Medium 3 reads from the prompt cache cost $0.04 per 1 million tokens. LLMCompare verified this price on 21 Oct 2026.
What is the context length of Mistral Medium 3?
Mistral Medium 3 has a context length of 131,072 tokens and returns up to 104,857 output tokens in one call.
What inputs does Mistral Medium 3 accept?
Mistral Medium 3 accepts these inputs: Text, Image, File. Mistral Medium 3 returns: Text.
Can I test Mistral Medium 3 on my own data?
Not yet. LLMCompare lists the prices and parameters of Mistral Medium 3, but no route to Mistral Medium 3 is configured on LLMCompare, so it cannot be selected for an evaluation.