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. | 128k | 256k |
| 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. | — | $0.95 |
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. | — | $4.00 |
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. | — | $0.19 |
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. | — | $0.60CoreWeave |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | — | $3.00CoreWeave |
| — | $270CoreWeave · int4 | |
| These models have no shared benchmark scores. | ||
DeepSWE 1.1Agentic coding — Artificial Analysis' independent test of deep, agentic software-engineering work — the AI has to plan and carry out substantial coding tasks end to end. (Version 1.1 of the test.) Higher is better. | — | 31% |
Next.js EvalsNext.js coding — Vercel's open eval of how well AI coding agents build and migrate real Next.js apps — measured as the share of tasks the agent completes successfully. Higher is better. | — | 75% |
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. | 70.88% | — |
AIME 2024Reasoning — single-answer accuracy on the 2024 invitational mathematics exam without tools | 86.14% | — |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | 77.34% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 70.07% | — |
| Overview | ||
| Company | Mistral | Moonshot AI |
| Release date | Sep 17 2025 | Jun 12 2026 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
Magistral Small 1.2vsClaude Fable 5.2Kimi K2.7 CodevsClaude Fable 5.2Magistral Small 1.2vsGPT-6.2 AstraKimi K2.7 CodevsGPT-6.2 AstraMagistral Small 1.2vsGemini 4 HydrogenKimi K2.7 CodevsGemini 4 HydrogenMagistral Small 1.2vsMuse EmberKimi K2.7 CodevsMuse EmberMagistral Small 1.2vsGrok 4.7Kimi K2.7 CodevsGrok 4.7Magistral Small 1.2vsDeepSeek-V4.1-Flash-1017Kimi K2.7 CodevsDeepSeek-V4.1-Flash-1017Frequently asked questions
Magistral Small 1.2 and Kimi K2.7 Code don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Only Kimi K2.7 Code has a verified first-party price for an available API: $0.95 per million input tokens and $4.00 per million output tokens. No currently available pay-as-you-go API rate is tracked for Magistral Small 1.2. Magistral Small 1.2 shipped 268 days before Kimi K2.7 Code, so benchmark comparisons should account for the intervening progress.
Magistral Small 1.2 has 24B parameters, while Kimi K2.7 Code has 1T. Context windows are 128k (Magistral Small 1.2) vs 256k (Kimi K2.7 Code).
Direct benchmark comparisons are unavailable — Magistral Small 1.2 and Kimi K2.7 Code don't publish scores on any of the same benchmarks.