Mistral Small 4
Mistral Small 4Alternatives?
CheaperAgnes 2.5 Pro Beta×3.8-43%$0.10 / $0.30
BetterGPT-6 Lunalow×2.1-70%$0.005Function calling only with none · Chat Completions+3
OpenQwen3.8 Flashthinking×3.9+2,373%$0.37Memory (4-bit): 72 GB → 108 GB+6
CheaperLing 3.0 FlashthinkingOpen×2.4-66%$0.06 / $0.18Memory (4-bit): 72 GB → 76 GB+2
CheaperGemma 4 31BthinkingOpen×2.4-39%$0.10 / $0.34Context: 262K → 256KAgnes 2.5 Pro Beta×3.8-43%$0.10 / $0.30Ling 3.0 FlashthinkingOpen×2.4-66%$0.06 / $0.18Memory (4-bit): 72 GB → 76 GB+2Gemma 4 31BthinkingOpen×2.4-39%$0.10 / $0.34Context: 262K → 256KLing 3.0 Flash FinthinkingOpen×2.3-66%$0.06 / $0.18Memory (4-bit): 72 GB → 76 GB+2
MiMo v2 Omnithinking×2.2-33%$0.14 / $0.28GPT-6 Lunalow×2.1-70%$0.005Function calling only with none · Chat Completions+3GPT-5.6 Lunalow×2-35%$0.01MiMo v2.5thinkingOpen×2.8+27%$0.019Memory (4-bit): 72 GB → 186 GB+1
Claude Haiku 5.5low×2.7+63%$0.024Remove sampling parameters+5
Mercury 2high+74%+157%$0.039Context: 262K → 128K+2Qwen3.8 FlashthinkingOpen×3.9+2,373%$0.37Memory (4-bit): 72 GB → 108 GB+6Qwen3.8 27BxhighOpen×3.4+6,596%$1.01max_tokens range · QwenCloud+4TInkling SmallthinkingOpen×3.4+495%$0.089Context: 262K → 256K+2
Nemotron 3.5 Super VLOpen×3.1+1,151%$0.19Memory (4-bit): 72 GB → 75 GB+1
MiniMax M2.7thinkingOpen×3+100%$0.30 / $1.20Context: 262K → 205K+3Mistral Large 4thinking×3.5+7,437%$1.13Infinite whitespace stream+4Mistral Medium 3.5highOpen+39%+3,237%$0.50Memory (4-bit): 72 GB → 77 GBMagistral Medium 1thinkingsame——Context: 262K → 40K+1Magistral Small 1thinkingOpen-23%—$0.70 / $1.16Context: 262K → 128K+2Ministral 3 3B 2512Open-46%-48%$0.008Context: 262K → 131KMinistral 3 14B 2512non-thinkingOpen-53%+29%$0.019Ministral 3 8B 2512Open-57%-26%$0.011Mistral Large 3non-thinkingOpen-58%+107%$0.031Memory (4-bit): not verifiedAll Mistral models →Run it yourself
estimateHistory
3 versionsBenchmarks
in Chat & KnowledgeFAQ
How much does Mistral Small 4 cost?›
$0.15 per 1M input tokens and $0.60 per 1M output tokens; cached input $0.015 per 1M. A typical benchmark task costs about $0.015 at default effort.
Is Mistral Small 4 free to use?›
There is no free API; the cheapest paid price is $0.15 per 1M input tokens. The weights are open, so you can run it yourself.
How good is Mistral Small 4, and what is it best at?›
#193 of 334 in Chat & Knowledge, #75 of 132 in Coding, #112 of 133 in Agents & Tool Use, #73 of 95 in Writing & Language, #101 of 124 in Vision & Documents.
Is Mistral Small 4 better than Saba?›
On Humanity's Last Exam, Mistral Small 4 scores 9.9 vs 4.3 — higher.
How can I use Mistral Small 4?›
Through the API of Mistral.
What is the context window of Mistral Small 4?›
262K tokens, with up to 210K output tokens.
When was Mistral Small 4 released? Is there a newer version?›
Released 2026-03-16. It is the current version in its line.
Is Mistral Small 4 open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run Mistral Small 4 locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can Mistral Small 4 read images?›
It accepts text and images, PDF files as input.
What is Mistral Small 4?›
Mistral Small 4 is an open-weights language model from Mistral, released Mar 2026, the successor to Saba.
What are the best alternatives to Mistral Small 4?›
Agnes 2.5 Pro Beta (cheaper), GPT-6 Luna (better), Qwen3.8 Flash (open weights).