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. | 3B | 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. | 256k | 128k |
| 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. | $0.10 | — |
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. | $0.10 | — |
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. | $0.10Mistral | $0.57Novita |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $0.10Mistral | $2.30Novita |
| $25.00Mistral list price | $229Novita · fp8 | |
| These models have no shared benchmark scores. | ||
BullshitBench v2Nonsense detection — Given a confidently-worded but nonsensical prompt, does the AI spot that it makes no sense and push back — instead of playing along and inventing an answer? The score is how often it clearly called out the nonsense. Higher is better. | — | 10% |
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% |
Humanity's Last Exam · with toolsMultidisciplinary reasoning — Humanity's Last Exam — extremely hard expert questions across many subjects. “With tools” means the AI is allowed to search the web or run code while answering. Higher is better. | — | 4.7% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 75.1% |
| Overview | ||
| Company | Mistral | Moonshot AI |
| Release date | Dec 2 2025 | Jul 11 2025 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
Ministral 3 3B-25-12vsClaude Haiku 5.5Kimi K2vsClaude Haiku 5.5Ministral 3 3B-25-12vsGPT-6.1 SolKimi K2vsGPT-6.1 SolMinistral 3 3B-25-12vsGemini 4 ArgonKimi K2vsGemini 4 ArgonMinistral 3 3B-25-12vsMuse Spark OpenKimi K2vsMuse Spark OpenMinistral 3 3B-25-12vsGrok 4.7Kimi K2vsGrok 4.7Ministral 3 3B-25-12vsDeepSeek-V4.1-Flash-1017Kimi K2vsDeepSeek-V4.1-Flash-1017Frequently asked questions
Ministral 3 3B-25-12 and Kimi K2 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Only Ministral 3 3B-25-12 has a verified first-party API price: $0.10 per million input tokens and $0.10 per million output tokens. No pay-as-you-go API rate is tracked for Kimi K2. Kimi K2 shipped 144 days before Ministral 3 3B-25-12, so benchmark comparisons should account for the intervening progress.
Ministral 3 3B-25-12 has 3B parameters, while Kimi K2 has 1T. Context windows are 256k (Ministral 3 3B-25-12) vs 128k (Kimi K2).
Direct benchmark comparisons are unavailable — Ministral 3 3B-25-12 and Kimi K2 don't publish scores on any of the same benchmarks.