Devstral Medium
Devstral MediumRankingin non-thinking mode?
Alternatives?
CheaperMiMo v2.6 ProthinkingOpen×5.1-32%$0.13Pass back reasoning_content+3
BetterGPT-6 Lunalow×2.4-75%$0.005Function calling only with none · Chat Completions+3
CheaperDeepSeek V4.1 Flash 1017maxOpen×5-34%$0.26Pass back reasoning_content · Chat Completions+4
CheaperClaude Haiku 5.5max×4.8-75%$0.21Remove sampling parameters+5
CheaperMiniMax M3.1 Flashthinking×4.7-67%$0.22Complete model response must be appendedMiMo v2.6 ProthinkingOpen×5.1-32%$0.13Pass back reasoning_content+3DeepSeek V4.1 Flash 1017maxOpen×5-34%$0.26Pass back reasoning_content · Chat Completions+4Claude Haiku 5.5max×4.8-75%$0.21Remove sampling parameters+5MiniMax M3.1 Flashthinking×4.7-67%$0.22Complete model response must be appended
GLM 5.3 FlashmaxOpen×4.6-70%$0.28Defaults to max · Self-hosted+4GPT-6 Lunalow×2.4-75%$0.005Function calling only with none · Chat Completions+3GPT-5.6 Lunalow×2.3-44%$0.01Mistral Small 4thinkingOpen+25%-67%$0.015MiMo v2.5thinkingOpen×2.4-78%$0.019
Granite 4.2 8BthinkingOpen+23%-87%$0.024MiMo v2.6 ProthinkingOpen×5.1-32%$0.13Pass back reasoning_content+3DeepSeek V4.1 Flash 1017maxOpen×5-34%$0.26Pass back reasoning_content · Chat Completions+4GLM 5.3maxOpen×5+169%$2.01Reasoning cannot be disabled+3
Step 5 PreviewthinkingOpen×4.9+78%$1.03web_search not available · Chat Completions+2
Kimi K3maxOpen×4.8+650%$2.00Sampling parameters are fixed+3Mistral Large 4thinking×4.3—$1.13Infinite whitespace stream+4Mistral Medium 3.5highOpen+58%—$0.50Mistral Small 4thinkingOpen+25%—$0.015Mistral Large 3non-thinkingOpensame—$0.031Magistral Medium 1thinkingsame——Context: 128K → 40KMagistral Small 1thinkingOpensame—$0.70 / $1.16Mistral Small 3non-thinkingOpen-26%—$0.05 / $0.08Context: 128K → 32KMinistral 3 14B 2512non-thinkingOpen-33%—$0.019All Mistral models →Run it yourself
Benchmarks
all categoriesFAQ
How much does Devstral Medium cost?›
$0.40 per 1M input tokens and $2 per 1M output tokens.
Is Devstral Medium free to use?›
There is no free API; the cheapest paid price is $0.40 per 1M input tokens. The weights are open, so you can run it yourself.
How good is Devstral Medium, and what is it best at?›
#318 of 334 in Chat & Knowledge, #97 of 97 in Coding, #192 of 242 in Agents & Tool Use, #213 of 245 in Writing & Language.
Is Devstral Medium better than Llama Nemotron Super 49B v1.5?›
On AA Intelligence Index 4.3.2, Devstral Medium scores 9 vs 9 — about the same.
How can I use Devstral Medium?›
Through the API of Mistral.
What is the context window of Devstral Medium?›
128K tokens, with up to 128K output tokens.
When was Devstral Medium released? Is there a newer version?›
Released 2025-07-10. It is the current version in its line.
Is Devstral Medium open source?›
Yes, the weights are open.
Can I run Devstral Medium locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can Devstral Medium read images?›
No, it accepts text only.
What is Devstral Medium?›
Devstral Medium is an open-weights language model from Mistral, released Jul 2025.
What are the best alternatives to Devstral Medium?›
MiMo v2.6 Pro (cheaper), GPT-6 Luna (better).