Mistral Small 3
Mistral Small 3Rankingin non-thinking mode?
Alternatives?
CheaperGemma 3 4BunstatedOpenwins 60%-26%$0.04 / $0.05
BetterGPT-5 Minihighwins 71%+1,096%$0.053
OpenQwen3.8 27Bunstatedwins 78%+1,563%$0.42 / $2.55Memory (4-bit): 14 GB → 17 GB+5CheaperGPT OSS 20BunstatedOpenwins 56%-37%$0.018 / $0.09CheaperGemma 2 9B ItOpenwins 46%-35%$0.03 / $0.06Context: 32K → 8KGemma 3 4BunstatedOpenwins 60%-26%$0.04 / $0.05GPT OSS 20BunstatedOpenwins 56%-37%$0.018 / $0.09Gemma 2 9B ItOpenwins 46%-35%$0.03 / $0.06Context: 32K → 8KGPT-5 Minihighwins 71%+1,096%$0.053GPT-6 Lunamaxwins 73%+248%$0.068Function calling only with none · Chat Completions+3GPT-5.6 Lunaxhighwins 80%+683%$0.085GPT-5.6 Terraxhighwins 81%+7,726%$0.63Prompts with >272K input tokensGPT-6 Solmaxwins 72%+6,857%$1.04Qwen3.8 27BunstatedOpenwins 78%+1,563%$0.42 / $2.55Memory (4-bit): 14 GB → 17 GB+5Qwen 3.5 27BunstatedOpenwins 74%+1,335%$0.30 / $2.40Memory (4-bit): 14 GB → 17 GBQwen3 30B A3B Instruct 2507unstatedOpenwins 72%+148%$0.09 / $0.30Memory (4-bit): 14 GB → 18 GBGemma 3 12BunstatedOpenwins 71%+9%$0.05 / $0.10Qwen 3.5 35B A3BunstatedOpenwins 71%+1,096%$0.25 / $2Memory (4-bit): 14 GB → 22 GBMistral Medium 3.5unstatedOpenwins 80%—$1.50 / $7.50Memory (4-bit): 14 GB → 77 GBMistral Large 3unstatedOpenwins 78%—$0.50 / $1.50Memory (4-bit): not verifiedMistral Small 3.1 24BunstatedOpenwins 58%—$0.35 / $0.56Mixtral 8x22B InstructunstatedOpenwins 40%—$2 / $6Memory (4-bit): 14 GB → 84 GBMixtral 8x7B Instruct v0.1Openwins 36%—$0.54 / $0.54Memory (4-bit): 14 GB → 28 GBMistral 7B Instruct v0.2Openwins 22%—$0.055 / $0.055No strict JSONMistral 7B Instructwins 17%——Mistral Large 4thinkingn/a—$1.13Infinite whitespace stream+4All Mistral models →Run it yourself
estimateBenchmarks
all categoriesFAQ
How much does Mistral Small 3 cost?›
$0.05 per 1M input tokens and $0.08 per 1M output tokens (cheapest host: DeepInfra).
Is Mistral Small 3 free to use?›
There is no free API; the cheapest paid price is $0.05 per 1M input tokens. The weights are open, so you can run it yourself.
How good is Mistral Small 3, and what is it best at?›
#316 of 334 in Chat & Knowledge, #129 of 152 in Coding, #194 of 242 in Agents & Tool Use, #168 of 195 in Writing & Language.
Is Mistral Small 3 better than Command R+ (08-2024)?›
On Arena Text · German, Mistral Small 3 scores 1,211.3 vs 1,215.9 — about the same.
How can I use Mistral Small 3?›
Through the API of DeepInfra, Featherless.
What is the context window of Mistral Small 3?›
32K tokens, with up to 16K output tokens.
When was Mistral Small 3 released? Is there a newer version?›
Released 2025-01-30. It is the current version in its line.
Is Mistral Small 3 open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run Mistral Small 3 locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can Mistral Small 3 read images?›
No, it accepts text only.
What is Mistral Small 3?›
Mistral Small 3 is an open-weights language model from Mistral, released Jan 2025.
What are the best alternatives to Mistral Small 3?›
Gemma 3 4B (cheaper), GPT-5 Mini (better), Qwen3.8 27B (open weights).