Compare AI models
| Specifications | ||
ParametersThe learned values that shape how a model responds. B means billion and T means trillion. For mixture-of-experts models, the total count is larger than the number active for each token. Parameter count alone does not measure quality. | 24B | 2.8T |
Context windowHow much information the model can work with in one request, measured in tokens — pieces of words or other data. This includes your question, attachments, conversation and reply. Limits can vary by model variant and provider. | 40k | 1M |
| API pricingUSD per 1M tokens · lower wins | ||
Input priceWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it. | — | $4.00 |
Output priceWhat you pay for the text the model writes back. It is normally the dearer half: producing an answer costs more than reading one. | — | $20.00 |
Cached input priceA reduced rate for text you send over and over. If every request starts with the same instructions or the same document, the provider keeps a copy ready and charges less to read it again. | — | $0.20 |
| — | $1,800Moonshot AI list price | |
| These models have no shared benchmark scores. | ||
LiveCodeBenchCompetitive coding — Coding problems published so recently the AI can't have seen them in training — a contamination-free test of raw programming skill. Higher is better. | 59.17% | — |
AIME 2024Reasoning — single-answer accuracy on the 2024 invitational mathematics exam without tools | 70.52% | — |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | 62.03% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 65.78% | — |
| Overview | ||
| Company | Mistral | Moonshot AI |
| Release date | Jul 24 2025 | Oct 23 2026 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
Magistral Small 1.1vsClaude Fable 5.2Kimi K3.1 Pro HighspeedvsClaude Fable 5.2Magistral Small 1.1vsGPT-6.2 AstraKimi K3.1 Pro HighspeedvsGPT-6.2 AstraMagistral Small 1.1vsGemini 4 HydrogenKimi K3.1 Pro HighspeedvsGemini 4 HydrogenMagistral Small 1.1vsMuse EmberKimi K3.1 Pro HighspeedvsMuse EmberMagistral Small 1.1vsGrok 4.7Kimi K3.1 Pro HighspeedvsGrok 4.7Magistral Small 1.1vsDeepSeek-V4.1-Flash-1017Kimi K3.1 Pro HighspeedvsDeepSeek-V4.1-Flash-1017Frequently asked questions
Magistral Small 1.1 and Kimi K3.1 Pro Highspeed don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Only Kimi K3.1 Pro Highspeed has a verified first-party price for an available API: $4.00 per million input tokens and $20.00 per million output tokens. No currently available pay-as-you-go API rate is tracked for Magistral Small 1.1. Magistral Small 1.1 shipped 456 days before Kimi K3.1 Pro Highspeed, so benchmark comparisons should account for the intervening progress.
Magistral Small 1.1 has 24B parameters, while Kimi K3.1 Pro Highspeed has 2.8T. Context windows are 40k (Magistral Small 1.1) vs 1M (Kimi K3.1 Pro Highspeed). Magistral Small 1.1 is open weight, while Kimi K3.1 Pro Highspeed is closed.
Direct benchmark comparisons are unavailable — Magistral Small 1.1 and Kimi K3.1 Pro Highspeed don't publish scores on any of the same benchmarks.