Mistral Small 2503
Mistral Small 2503Compare inon
Benchmarks of Mistral Small 25033
BenchmarkByScoreRank
Legacy · saturated or no longer reported2
No benchmark matches
Ranking?
Retired models are left out of the current rankings.
Alternatives?
ModelScoreCostPer taskWhat changes
CheaperQwen3.7 Flashunstated+73%-63%$0.03 / $0.13
BetterGPT-5.6 Lunalow+73%+200%$0.01
OpenKimi K3max+96%+3,900%$2.00Sampling parameters are fixed+3CheaperQwen 3.5 Flashunstated+73%-24%$0.065 / $0.26CheaperQwen 3.5 9BunstatedOpen+66%-38%$0.08 / $0.13ModelScoreCostPer taskWhat changes
Qwen3.7 Flashunstated+73%-63%$0.03 / $0.13Qwen 3.5 Flashunstated+73%-24%$0.065 / $0.26Qwen 3.5 9BunstatedOpen+66%-38%$0.08 / $0.13GPT OSS 120BhighOpen+60%-60%$0.092No image inputGPT-5 Nano (2025-08-07)high+46%-8%$0.05 / $0.40ModelScoreCostPer taskWhat changes
GPT-5.6 Lunalow+73%+200%$0.01
Gemini 3.1 Flash Litehigh+72%+275%$0.06GPT-6 Lunamax+91%+33%$0.068Function calling only with none · Chat Completions+3GPT OSS 120BhighOpen+60%-60%$0.092No image inputGPT-5.6 Terralow+84%+2,900%$0.14Prompts with >272K input tokensModelScoreCostPer taskWhat changes
Kimi K3maxOpen+96%+3,900%$2.00Sampling parameters are fixed+3
GLM 5.2maxOpen+93%+1,333%$1.47No image input
DeepSeek V4 Pro 0813maxOpen+93%+1,220%$0.67No image input+5
MiniMax M3unstatedOpen+91%+250%$0.30 / $1.20No strict JSON+1GLM 5.3maxOpen+91%+1,333%$2.01No image input+4ModelScoreCostPer taskWhat changes
Mistral Large 4high+86%—$1.36 / $4.18Infinite whitespace stream+4Magistral Small 1unstatedOpen+18%—$0.70 / $1.16No image inputMistral Small 3.1 (25.03)-12%—$0.10 / $0.30Context: not verifiedMixtral 8x7B Instruct v0.1Open-36%—$0.54 / $0.54Context: 128K → 33K+1Mistral 7B Instruct v0.3Open-68%—$0.028 / $0.054Context: 128K → 33K+1Mistral Medium 3.5highOpenn/a—$0.50Mistral Small 4thinkingOpenn/a—$0.015Mistral Smalln/a—$1 / $3Context: 128K → 32KAll Mistral models →FAQ
How much does Mistral Small 2503 cost?›
$0.10 per 1M input tokens and $0.30 per 1M output tokens (cheapest host: Azure Cognitive Services).
Is Mistral Small 2503 free to use?›
There is no free API; the cheapest paid price is $0.10 per 1M input tokens.
How can I use Mistral Small 2503?›
Through the Mistral API.
What is the context window of Mistral Small 2503?›
128K tokens.
When was Mistral Small 2503 released? Is there a newer version?›
It has been superseded by Mistral Small 4.
Can Mistral Small 2503 read images?›
It accepts text and images as input.
What is Mistral Small 2503?›
Mistral Small 2503 is a language model from Mistral.
What are the best alternatives to Mistral Small 2503?›
Qwen3.7 Flash (cheaper), GPT-5.6 Luna (better), Kimi K3 (open weights).