Question 1

What does this Magistral Medium (latest) vs Mistral Large (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: Magistral Medium (latest) or Mistral Large (latest)?

Accepted Answer

Magistral Medium (latest) lists $2.00 input and $5.00 output per 1M tokens. Mistral Large (latest) lists $0.50 input and $1.50 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: Magistral Medium (latest) or Mistral Large (latest)?

Accepted Answer

Magistral Medium (latest) lists 128K tokens and Mistral Large (latest) lists 262.14K. Mistral Large (latest) therefore has the larger recorded context window, but capacity alone is not a quality score.

Question 4

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

Accepted Answer

Magistral Medium (latest) records text input and text output. Mistral Large (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 Magistral Medium (latest) or Mistral Large (latest)?

Accepted Answer

Consider Mistral Large (latest) if you need larger context or larger maximum output or a lower listed input rate or a lower listed output rate. Mistral Large (latest) offers downloadable weights; Magistral Medium (latest) is listed as a proprietary model. Compare licence terms and operating costs before choosing a deployment. 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	Magistral Medium (latest)	Mistral Large (latest)
Provider	Mistral AI	Mistral AI
Listed pricing route	Mistral AI	Mistral AI
Model family	magistral-medium	mistral-large
Accepted inputs	text	text, image
Produced outputs	text	text
Context window	128K	262.14KHigher
Max output	16.38K	262.14KHigher
Input price / 1M	$2.00	$0.50Lower
Output price / 1M	$5.00	$1.50Lower
Reasoning mode	Documented	Not documented
Tool calling	Documented	Documented
Image input	Not documented	Documented
Audio input	Not documented	Not documented
Structured output	Not documented	Not documented
License	Proprietary	Open weights

Magistral Medium (latest) vs Mistral Large (latest)

Magistral Medium (latest)

Mistral Large (latest)

Key differences

Pricing, limits and capabilities

Which model should you choose?

Documentation and model profiles

Questions people ask

Compare a different pair