Mistral Large 4
Mistral Large 4Rankingin thinking mode?
Alternatives?
CheaperGPT-6.1 Solmax+35%-36%$0.72Remove unsupported parameters+5
BetterClaude Haiku 5.5xhigh+7%-89%$0.12Remove sampling parameters+5
OpenMiMo v2.6 Prothinking+21%-88%$0.13No PDF input+4CheaperGPT-6 Solmax+24%-8%$1.04CheaperClaude Sonnet 5.5high+22%-22%$0.88No forced tool use+5GPT-6.1 Solmax+35%-36%$0.72Remove unsupported parameters+5GPT-6 Solmax+24%-8%$1.04Claude Sonnet 5.5high+22%-22%$0.88No forced tool use+5MiMo v2.6 ProthinkingOpen+21%-88%$0.13No PDF input+4GPT-6 Astralow+19%-28%$0.82Monitoring can return HTTP 403+2Claude Haiku 5.5xhigh+7%-89%$0.12Remove sampling parameters+5GPT-6.1 Sollow+10%-88%$0.13Remove unsupported parameters+5MiMo v2.6 ProthinkingOpen+21%-88%$0.13No PDF input+4
MiniMax M3.1 Flashthinking+11%-81%$0.22No PDF input+1
DeepSeek V4.1 Flash 1017maxOpen+18%-77%$0.26No PDF input+5MiMo v2.6 ProthinkingOpen+21%-88%$0.13No PDF input+4DeepSeek V4.1 Flash 1017maxOpen+18%-77%$0.26No PDF input+5
GLM 5.3maxOpen+17%+77%$2.01No image input+5
Step 5 PreviewthinkingOpen+14%-9%$1.03No PDF input+3
Kimi K3maxOpen+14%+76%$2.00Sampling parameters are fixed+3Mistral Medium 3.5highOpen-63%-56%$0.50Context: 1M → 262KMistral Small 4thinkingOpen-71%-99%$0.015Context: 1M → 262KMistral Large 3non-thinkingOpen-76%-97%$0.031Context: 1M → 262KMagistral Medium 1thinking-76%——Context: 1M → 40K+1Devstral Mediumnon-thinkingOpen-77%—$0.40 / $2Context: 1M → 128K+2Magistral Small 1thinkingOpen-79%—$0.70 / $1.16Context: 1M → 128K+2Mistral Small 3non-thinkingOpen-83%—$0.05 / $0.08Context: 1M → 32K+2Ministral 3 14B 2512non-thinkingOpen-84%-98%$0.019Context: 1M → 262KAll Mistral models →History
4 versionsBenchmarks
all categoriesWatch out 5
Infinite whitespace stream›
In JSON Object mode, include JSON in the system or user prompt to avoid a possible infinite whitespace stream. Source ↗
Content is a list of chunks›
With reasoning_effort high, message.content is a chunk list rather than a plain string; parse thinking and text chunks. Source ↗
Only function calling · Mistral regional endpoints›
Regional endpoints support function calling only and omit Agents, Batch and Files; check regional model availability before routing requests. Source ↗
10% upcharge · Mistral regional endpoints›
Regional inference charges 1.1× standard list prices for input, output, cached reads and cache writes. Source ↗
Reinforcement learning run still in flight›
The public preview reinforcement learning run is still in flight, and Mistral expects further rapid changes as training scales. Source ↗
FAQ
How much does Mistral Large 4 cost?›
$1.36 per 1M input tokens and $4.18 per 1M output tokens; cached input $0.14 per 1M; cheapest via mistralai at $0.68 / $2.09. A typical benchmark task costs about $1.13 at default effort.
Is Mistral Large 4 free to use?›
There is no free API; the cheapest paid price is $0.68 per 1M input tokens.
How good is Mistral Large 4, and what is it best at?›
#62 of 334 in Chat & Knowledge, #23 of 132 in Coding, #19 of 133 in Agents & Tool Use, #90 of 195 in Writing & Language, #39 of 124 in Vision & Documents. Strongest at: Coding, Agents & work tasks, Reasoning, Long context.
Is Mistral Large 4 better than Mistral Large 3?›
On AA Intelligence Index 4.3.2, Mistral Large 4 scores 38.4 vs 9.3 — higher. It is 3,544% more expensive per task.
How can I use Mistral Large 4?›
Through the API of Mistral.
What is the context window of Mistral Large 4?›
1M tokens, with up to 262K output tokens.
When was Mistral Large 4 released? Is there a newer version?›
Released 2026-10-06. It is the current version in its line.
Is Mistral Large 4 open source?›
No, Mistral Large 4 is a closed model available through an API. The closest open-weights option here is MiMo v2.6 Pro.
Can Mistral Large 4 read images?›
It accepts text and images, PDF files as input.
What is Mistral Large 4?›
Mistral Large 4 is a closed language model from Mistral, released Oct 2026, the successor to Mistral Large 3.
What are the best alternatives to Mistral Large 4?›
GPT-6.1 Sol (cheaper), Claude Haiku 5.5 (better), MiMo v2.6 Pro (open weights).