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 |
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. | 1M | 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. | $0.30 | $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. | $2.50 | $0.10 |
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. | $0.03 | — |
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. | $0.15Google AI Studio | $0.10Mistral |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $1.25Google AI Studio | $0.10Mistral |
| $185Google list price | $25.00Mistral list price | |
| 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. | 19% | — |
| Overview | ||
| Company | Mistral | |
| Release date | Apr 17 2025 | Dec 2 2025 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Gemini 2.5 FlashvsClaude Haiku 5.5Ministral 3 3B-25-12vsClaude Haiku 5.5Gemini 2.5 FlashvsGPT-6.1 SolMinistral 3 3B-25-12vsGPT-6.1 SolGemini 2.5 FlashvsMuse Spark OpenMinistral 3 3B-25-12vsMuse Spark OpenGemini 2.5 FlashvsGrok 4.7Ministral 3 3B-25-12vsGrok 4.7Gemini 2.5 FlashvsDeepSeek-V4.1-Flash-1017Ministral 3 3B-25-12vsDeepSeek-V4.1-Flash-1017Gemini 2.5 FlashvsKimi K3Ministral 3 3B-25-12vsKimi K3Frequently asked questions
Gemini 2.5 Flash and Ministral 3 3B-25-12 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Ministral 3 3B-25-12 is cheaper on both input and output: $0.10 vs $0.30 per million input tokens, and $0.10 vs $2.50 per million output tokens. Gemini 2.5 Flash shipped 229 days before Ministral 3 3B-25-12, so benchmark comparisons should account for the intervening progress.
Context windows are 1M (Gemini 2.5 Flash) vs 256k (Ministral 3 3B-25-12). Gemini 2.5 Flash is closed, while Ministral 3 3B-25-12 is open weight.
Direct benchmark comparisons are unavailable — Gemini 2.5 Flash and Ministral 3 3B-25-12 don't publish scores on any of the same benchmarks.