GeekRadar / The comparison desk

COMPARE.

AI models

mistral

Devstral Medium

AI model Released Jul 10, 2025

Context window: 128,000 tokens
Maximum output: 128,000 tokens
Open weights: No

No matched benchmark results are available for this entry yet.

Run it locally

Inference · memory estimate

Devstral Medium

Closed weights. No supported local deployment or GPU requirement is published.

Capabilities

Context window: 128,000 tokens
Maximum output: 128,000 tokens
Reasoning: No
Tool calling: Yes
Open weights: No
Knowledge cutoff: 2025-05

Input modalities

text

Output modalities

text