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. | — | 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% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 65.7% | — |
IFBenchInstruction following — Tests whether the AI can follow detailed instructions and satisfy multiple constraints at once. Higher is better. | 40.8% | — |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | 76.8% | — |
MMMU-ProMultimodal reasoning — A tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. | 43.8% | — |
| Overview | ||
| Company | Mistral | Moonshot AI |
| Release date | Aug 12 2025 | Jun 12 2026 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Mistral Medium 3.1vsClaude Fable 5.2Kimi K2.7 CodevsClaude Fable 5.2Mistral Medium 3.1vsGPT-6.2 AstraKimi K2.7 CodevsGPT-6.2 AstraMistral Medium 3.1vsGemini 4 HydrogenKimi K2.7 CodevsGemini 4 HydrogenMistral Medium 3.1vsMuse EmberKimi K2.7 CodevsMuse EmberMistral Medium 3.1vsGrok 4.7Kimi K2.7 CodevsGrok 4.7Mistral Medium 3.1vsDeepSeek-V4.1-Flash-1017Kimi K2.7 CodevsDeepSeek-V4.1-Flash-1017Frequently asked questions
Mistral Medium 3.1 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 Mistral Medium 3.1. Mistral Medium 3.1 shipped 304 days before Kimi K2.7 Code, so benchmark comparisons should account for the intervening progress.
Context windows are 128k (Mistral Medium 3.1) vs 256k (Kimi K2.7 Code). Mistral Medium 3.1 is closed, while Kimi K2.7 Code is open weight.
Direct benchmark comparisons are unavailable — Mistral Medium 3.1 and Kimi K2.7 Code don't publish scores on any of the same benchmarks.