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. | 22B | 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. | 32k | 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. | — | $0.60Google |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | — | $2.50Google |
| — | $245Novita · bf16 | |
| These models have no shared benchmark scores. | ||
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. | — | 71.3% |
| Overview | ||
| Company | Mistral | Moonshot AI |
| Release date | May 29 2024 | Nov 6 2025 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Codestral 22BvsClaude Haiku 5.5Kimi K2 ThinkingvsClaude Haiku 5.5Codestral 22BvsGPT-6.1 SolKimi K2 ThinkingvsGPT-6.1 SolCodestral 22BvsGemini 4 ArgonKimi K2 ThinkingvsGemini 4 ArgonCodestral 22BvsMuse Spark OpenKimi K2 ThinkingvsMuse Spark OpenCodestral 22BvsGrok 4.7Kimi K2 ThinkingvsGrok 4.7Codestral 22BvsDeepSeek-V4.1-Flash-1017Kimi K2 ThinkingvsDeepSeek-V4.1-Flash-1017Frequently asked questions
Codestral 22B and Kimi K2 Thinking don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Codestral 22B shipped 526 days before Kimi K2 Thinking, so benchmark comparisons should account for the intervening progress.
Codestral 22B has 22B parameters, while Kimi K2 Thinking has 1T. Context windows are 32k (Codestral 22B) vs 256k (Kimi K2 Thinking). Codestral 22B is closed, while Kimi K2 Thinking is open weight.
Direct benchmark comparisons are unavailable — Codestral 22B and Kimi K2 Thinking don't publish scores on any of the same benchmarks.