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 | 1T |
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 | 256k |
| API pricingUSD per 1M tokens · lower wins | ||
Cheapest inputLowest input rate across every provider on OpenRouter, the lab included. The cheapest endpoint may run a quantised build or a shorter context — see "Available from" on the model page. | — | $0.60Novita |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | — | $2.50Novita |
| — | $245Novita · fp8 | |
| Benchmarks | ||
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% | 75.1% |
SWE-Bench VerifiedCoding — Real coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better. | — | 65.8% |
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% | — |
| Overview | ||
| Company | Mistral | Moonshot AI |
| Release date | Jul 24 2025 | Sep 5 2025 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
Magistral Small 1.1vsClaude Fable 5.2Kimi K2 (0905)vsClaude Fable 5.2Magistral Small 1.1vsGPT-6.2 AstraKimi K2 (0905)vsGPT-6.2 AstraMagistral Small 1.1vsGemini 4 HydrogenKimi K2 (0905)vsGemini 4 HydrogenMagistral Small 1.1vsMuse EmberKimi K2 (0905)vsMuse EmberMagistral Small 1.1vsGrok 4.7Kimi K2 (0905)vsGrok 4.7Magistral Small 1.1vsDeepSeek-V4.1-Flash-1017Kimi K2 (0905)vsDeepSeek-V4.1-Flash-1017Frequently asked questions
Kimi K2 (0905) leads Magistral Small 1.1 on 1 of the 1 benchmark they both report (GPQA Diamond). Magistral Small 1.1 shipped 43 days before Kimi K2 (0905), so benchmark comparisons should account for the intervening progress.
Magistral Small 1.1 has 24B parameters, while Kimi K2 (0905) has 1T. Context windows are 40k (Magistral Small 1.1) vs 256k (Kimi K2 (0905)).
On GPQA Diamond, Kimi K2 (0905) leads at 75.1% vs Magistral Small 1.1 at 65.78%.