Compare AI models
| Specifications | ||
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 | 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. | $0.30 | $0.30 |
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 | $0.90 |
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 | $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 | — |
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 | — |
| $185Google list price | $105Mistral 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% | — |
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. | 63.5% | — |
Aider Polyglot (diff)Coding — editing code in six languages using the diff edit format | 44.2% | — |
Humanity's Last Exam · no toolsMultidisciplinary reasoning — Humanity's Last Exam — extremely hard expert questions across many subjects, written so you can't just look up the answer. “No tools” means the AI answers on its own. Higher is better. | 12.1% | — |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | 78% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 78.3% | — |
SimpleQAKnowledge — accuracy on short, fact-seeking questions in the original SimpleQA set | 29.7% | — |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | 76.7% | — |
| Overview | ||
| Company | Mistral | |
| Release date | Apr 17 2025 | Jul 30 2025 |
| Access | Closed | Closed |
| Model details | View model | View model |
Other comparisons
Gemini 2.5 FlashvsClaude Fable 5.2Codestral 25.08vsClaude Fable 5.2Gemini 2.5 FlashvsGPT-6.2 AstraCodestral 25.08vsGPT-6.2 AstraGemini 2.5 FlashvsMuse EmberCodestral 25.08vsMuse EmberGemini 2.5 FlashvsGrok 4.7Codestral 25.08vsGrok 4.7Gemini 2.5 FlashvsDeepSeek-V4.1-Flash-1017Codestral 25.08vsDeepSeek-V4.1-Flash-1017Gemini 2.5 FlashvsKimi K3.1 ProCodestral 25.08vsKimi K3.1 ProFrequently asked questions
Gemini 2.5 Flash and Codestral 25.08 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Both charge $0.30 per million input tokens. Codestral 25.08 is cheaper on output: $0.90 vs $2.50 per million tokens. Gemini 2.5 Flash shipped 104 days before Codestral 25.08, so benchmark comparisons should account for the intervening progress.
Context windows are 1M (Gemini 2.5 Flash) vs 128k (Codestral 25.08).
Direct benchmark comparisons are unavailable — Gemini 2.5 Flash and Codestral 25.08 don't publish scores on any of the same benchmarks.