Question 1

What does this Mistral Large (latest) vs Mistral Medium (latest) comparison cover?

Accepted Answer

It brings together documented inputs and outputs, token limits, deployment terms and available pricing. When both models have source-linked, verified results on a shared benchmark, those results are shown with their individual sources. The comparison is a starting point for evaluating your own workload.

Question 2

Which is cheaper: Mistral Large (latest) or Mistral Medium (latest)?

Accepted Answer

Mistral Large (latest) lists $0.50 input and $1.50 output per 1M tokens. Mistral Medium (latest) lists $1.50 input and $7.50 output. The cheaper workload depends on the mix of input and output. Long-context tiers, caching, batch processing and retries can change the bill.

Question 3

Which has the larger context window: Mistral Large (latest) or Mistral Medium (latest)?

Accepted Answer

Both records list a 262.14K-token context window. An equal limit does not imply equal recall, instruction following, or long-context quality.

Question 4

Which is faster: Mistral Large (latest) or Mistral Medium (latest)?

Accepted Answer

There is no matched speed measurement for both models with the same source, host, region and date. Test the same prompts at your expected concurrency and measure time to the first useful response as well as complete task time.

Question 5

What input and output types do Mistral Large (latest) and Mistral Medium (latest) support?

Accepted Answer

Mistral Large (latest) records text, image input and text output. Mistral Medium (latest) records text, image input and text output. “Not documented” means the current source record is incomplete; it does not prove that a modality is unsupported.

Question 6

Should I choose Mistral Large (latest) or Mistral Medium (latest)?

Accepted Answer

Consider Mistral Large (latest) if you need a lower listed input rate or a lower listed output rate. Test both on the same representative examples and judge the output against your acceptance criteria. Include tool failures, retries and the time to a completed task.

Specification	Mistral Large (latest)	Mistral Medium (latest)
Provider	Mistral AI	Mistral AI
Listed pricing route	Mistral AI	Mistral AI
Model family	mistral-large	mistral-medium
Accepted inputs	text, image	text, image
Produced outputs	text	text
Context window	262.14K	262.14K
Max output	262.14K	262.14K
Input price / 1M	$0.50Lower	$1.50
Output price / 1M	$1.50Lower	$7.50
Reasoning mode	Not documented	Documented
Tool calling	Documented	Documented
Image input	Documented	Documented
Audio input	Not documented	Not documented
Structured output	Not documented	Documented
License	Open weights	Open weights

Mistral Large (latest) vs Mistral Medium (latest)

Mistral Large (latest)

Mistral Medium (latest)

Key differences

Pricing, limits and capabilities

Which model should you choose?

Documentation and model profiles

Questions people ask

Compare a different pair