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. | 128k | 400k |
| 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 | $1.25 |
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. | $0.90 | $10.00 |
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. | $0.03 | $0.125 |
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. | — | $0.625OpenAI |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | — | $5.00OpenAI |
| $105Mistral list price | $750OpenAI 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. | — | 25% |
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. | — | 76.3% |
τ²-bench · retailAgentic tasks — task success in the retail domain of the second-generation customer-service evaluation | — | 77.9% |
τ²-bench · airlineAgentic tasks — task success in the airline domain of the second-generation customer-service evaluation | — | 67% |
τ²-bench · telecom, adjusted promptAgentic tasks — telecom task success with an extra general instruction in the system prompt | — | 95.6% |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | — | 94% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 88.1% |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | — | 85.4% |
| Overview | ||
| Company | Mistral | OpenAI |
| Release date | Jul 30 2025 | Nov 12 2025 |
| Access | Closed | Closed |
| Model details | View model | View model |
Other comparisons
Codestral 25.08vsClaude Fable 5.2GPT-5.1vsClaude Fable 5.2Codestral 25.08vsGemini 4 HydrogenGPT-5.1vsGemini 4 HydrogenCodestral 25.08vsMuse EmberGPT-5.1vsMuse EmberCodestral 25.08vsGrok 4.7GPT-5.1vsGrok 4.7Codestral 25.08vsDeepSeek-V4.1-Flash-1017GPT-5.1vsDeepSeek-V4.1-Flash-1017Codestral 25.08vsKimi K3.1 ProGPT-5.1vsKimi K3.1 ProFrequently asked questions
Codestral 25.08 and GPT-5.1 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Codestral 25.08 is cheaper on both input and output: $0.30 vs $1.25 per million input tokens, and $0.90 vs $10.00 per million output tokens. Codestral 25.08 shipped 105 days before GPT-5.1, so benchmark comparisons should account for the intervening progress.
Context windows are 128k (Codestral 25.08) vs 400k (GPT-5.1).
Direct benchmark comparisons are unavailable — Codestral 25.08 and GPT-5.1 don't publish scores on any of the same benchmarks.