Mistral Medium 3.5
Mistral Medium 3.5Rankingat high effort?
Alternatives?
CheaperCommand A+thinkingOpen×5.8-80%$0.30 / $1.50Context: 262K → 128K+2
BetterGranite 4.2 3BthinkingOpen×3.1-99%$0.006Context: 262K → 128K+1OOpenMiniCPM5 1Bnon-thinking×90.6——Context: 262K → 131K+1
CheaperGrok 4.3medium×4.8-48%$1.25 / $2.50
CheaperLing 3.0 Flash VLthinkingOpen×3.7-97%$0.06 / $0.18No PDF inputCommand A+thinkingOpen×5.8-80%$0.30 / $1.50Context: 262K → 128K+2Grok 4.3medium×4.8-48%$1.25 / $2.50Ling 3.0 Flash VLthinkingOpen×3.7-97%$0.06 / $0.18No PDF input
MiMo v2.5 ProthinkingOpen×3.3-89%$0.054Memory (4-bit): 77 GB → 614 GB+2Granite 4.2 30BthinkingOpen×3.2-86%$0.072Context: 262K → 128K+1Granite 4.2 3BthinkingOpen×3.1-99%$0.006Context: 262K → 128K+1
Gemma 4 E4BthinkingOpen×2.6-98%$0.008Context: 262K → 128K+1
GPT-5.6 Lunanon-thinking+9%-98%$0.01GPT-6 Lunanon-thinking+3%-98%$0.011Function calling only with none · Chat Completions+3Mistral Small 4thinkingOpen+23%-97%$0.015Command A+thinkingOpen×5.8-80%$0.30 / $1.50Context: 262K → 128K+2lLFM2.5 2.6BthinkingOpen×5.1——Context: 262K → 131K+2Ministral 3 8B 2512Open-13%-98%$0.011Ministral 3 14B 2512non-thinkingOpen-12%-96%$0.019Mistral Large 3non-thinkingOpen-5%-94%$0.031Memory (4-bit): not verifiedMinistral 3 3B 2512Open+2%-98%$0.008Context: 262K → 131KMagistral Small 1thinkingOpen+7%—$0.70 / $1.16Context: 262K → 128K+2Mistral Small 4thinkingOpen+23%-97%$0.015Devstral Mediumnon-thinkingOpen+31%—$0.40 / $2Context: 262K → 128K+3Magistral Medium 1thinking+38%——Context: 262K → 40K+1All Mistral models →Run it yourself
estimateHistory
3 versionsBenchmarks
all categoriesFAQ
How much does Mistral Medium 3.5 cost?›
$1.50 per 1M input tokens and $7.50 per 1M output tokens; cached input $0.15 per 1M; cheapest via Featherless at $1 / $4. A typical benchmark task costs about $0.50 at high effort.
Is Mistral Medium 3.5 free to use?›
There is no free API; the cheapest paid price is $1 per 1M input tokens. The weights are open, so you can run it yourself.
How good is Mistral Medium 3.5, and what is it best at?›
#151 of 334 in Chat & Knowledge, #75 of 132 in Coding, #80 of 133 in Agents & Tool Use, #69 of 195 in Writing & Language, #81 of 124 in Vision & Documents. Strongest at: Tool calling, Instructions.
Is Mistral Medium 3.5 better than Devstral 2 2512?›
On AA Omniscience · Hallucination Rate, Mistral Medium 3.5 scores 81.6 vs 85.3 — higher.
How can I use Mistral Medium 3.5?›
Through the API of Featherless, Mistral.
What is the context window of Mistral Medium 3.5?›
262K tokens, with up to 210K output tokens.
When was Mistral Medium 3.5 released? Is there a newer version?›
Released 2026-04-29. It is the current version in its line.
Is Mistral Medium 3.5 open source?›
Yes, the weights are open.
Can I run Mistral Medium 3.5 locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can Mistral Medium 3.5 read images?›
It accepts text and images, PDF files as input.
What is Mistral Medium 3.5?›
Mistral Medium 3.5 is an open-weights language model from Mistral, released Apr 2026, the successor to Devstral 2 2512.
What are the best alternatives to Mistral Medium 3.5?›
Command A+ (cheaper), Granite 4.2 3B (better), MiniCPM5 1B (open weights).