Mistral Large
Mistral LargeRankingin non-thinking mode?
Full ranking →Strong at
Alternatives?
CheaperGemini 3.8 Flashhighwins 75%-50%*$3.49Sampling parameters are ignored+1
BetterGPT-5 Minihighwins 62%-77%$0.053
OpenKimi K3maxwins 74%+100%$2.00Sampling parameters are fixed+3
CheaperMuse Spark 1.3maxwins 75%-33%$3.69Only auto tool_choice is supported+5CheaperMuse Spark 1.2xhighwins 75%-33%$1.29Only auto tool_choice is supported+1Gemini 3.8 Flashhighwins 75%-50%*$3.49Sampling parameters are ignored+1Muse Spark 1.3maxwins 75%-33%$3.69Only auto tool_choice is supported+5Muse Spark 1.2xhighwins 75%-33%$1.29Only auto tool_choice is supported+1Muse Spark 1.1unstatedwins 74%-33%$1.25 / $4.25Only n=1 · Meta / Chat Completions+1Muse Sparkunstatedwins 74%-33%$1.25 / $4.25Only n=1 · Meta / Chat Completions+1GPT-5 Minihighwins 62%-77%$0.053GPT-6 Lunamaxwins 69%-93%$0.068Function calling only with none · Chat Completions+3GPT-5.6 Lunaxhighwins 70%-85%$0.085GPT-5.6 Terraxhighwins 72%+50%$0.63Prompts with >272K input tokensGPT-6.1 Solmaxwins 74%+33%$0.72Remove unsupported parameters+5Kimi K3maxOpenwins 74%+100%$2.00Sampling parameters are fixed+3
MiMo v2.6 ProunstatedOpenwins 73%-82%$0.43 / $0.87Pass back reasoning_content+3
GLM 5.3maxOpenwins 73%-28%$2.01Reasoning cannot be disabled+3GLM 5.2maxOpenwins 73%-28%$1.28GLM 5.3 FlashunstatedOpenwins 72%-92%$0.15 / $0.50Defaults to max · Self-hosted+4Mistral Large 4unstatedwins 67%—$1.36 / $4.18Infinite whitespace stream+4Mistral Medium 3.5unstatedOpenwins 67%—$1.50 / $7.50Mistral Large 3unstatedOpenwins 65%—$0.50 / $1.50Mistral Small 3.1 24BunstatedOpensame—$0.35 / $0.56Mistral Small 3unstatedOpenwins 45%—$0.05 / $0.08Context: 128K → 32KMixtral 8x22B InstructunstatedOpenwins 39%—$2 / $6Context: 128K → 66KMixtral 8x7B Instruct v0.1Openwins 35%—$0.54 / $0.54Context: 128K → 33KMistral 7B Instruct v0.2Openwins 29%—$0.055 / $0.055Context: 128K → 33K+1All Mistral models →History
4 versionsBenchmarks
in Chat & KnowledgeFAQ
How much does Mistral Large cost?›
$2 per 1M input tokens and $6 per 1M output tokens; cached input $0.20 per 1M.
Is Mistral Large free to use?›
There is no free API; the cheapest paid price is $2 per 1M input tokens.
How good is Mistral Large, and what is it best at?›
#327 of 336 in Chat & Knowledge, #138 of 152 in Coding, #156 of 197 in Writing & Language.
Is Mistral Large better than Nemotron 3 Nano 30B A3B?›
On Arena Text · overall, Mistral Large scores 1,306 vs 1,314 — about the same.
How can I use Mistral Large?›
Through the API of AWS Bedrock, Mistral.
What is the context window of Mistral Large?›
128K tokens, with up to 102K output tokens.
When was Mistral Large released? Is there a newer version?›
Released 2024-02-26. It has been superseded by Mistral Large 2407.
Is Mistral Large open source?›
No, Mistral Large is a closed model available through an API. The closest open-weights option here is Kimi K3.
Can Mistral Large read images?›
It accepts text and PDF files as input.
What is Mistral Large?›
Mistral Large is a closed language model from Mistral, released Feb 2024.
What are the best alternatives to Mistral Large?›
Gemini 3.8 Flash (cheaper), GPT-5 Mini (better), Kimi K3 (open weights).