Compare AI models
| Specifications | ||
ParametersA rough measure of how big the model is. More parameters usually means more capable and more expensive to run, though it is a poor guide on its own — a smaller, newer model often beats a larger, older one. | 128B | — |
Context windowHow much text the model can hold in mind at once — your question, any documents you attach, the conversation so far, and its own reply. Go past it and the earliest part falls out of view. | 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. | $1.50 | $1.10 |
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. | $7.50 | $4.40 |
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. | — | $0.275 |
Cheapest inputLowest input rate across third-party providers, excluding the lab itself. The cheapest endpoint may run a quantised build or a shorter context — see "Available from" on the model page. | $1.50Mistral | $1.10OpenAI |
Cheapest outputLowest output rate across third-party providers, excluding the lab itself. May come from a different provider than the cheapest input. | $7.50Mistral | $4.40OpenAI |
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. | — | 8% |
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. | 77.6% | — |
| Overview | ||
| Company | Mistral | OpenAI |
| Release date | Apr 29 2026 | Apr 16 2025 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
Mistral Medium 3.5vsClaude Sonnet 5.5o4-minivsClaude Sonnet 5.5Mistral Medium 3.5vsGemini 4 Argono4-minivsGemini 4 ArgonMistral Medium 3.5vsMuse Spark 1.3o4-minivsMuse Spark 1.3Mistral Medium 3.5vsGrok 4.7o4-minivsGrok 4.7Mistral Medium 3.5vsDeepSeek-V4.1-Flasho4-minivsDeepSeek-V4.1-FlashMistral Medium 3.5vsKimi K3o4-minivsKimi K3Frequently asked questions
Mistral Medium 3.5 and o4-mini don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. o4-mini is cheaper on both input and output: $1.10 vs $1.50 per million input tokens, and $4.40 vs $7.50 per million output tokens. o4-mini shipped 378 days before Mistral Medium 3.5, so benchmark comparisons should account for the intervening progress.
Mistral Medium 3.5 is open weight, while o4-mini is closed.
Direct benchmark comparisons are unavailable — Mistral Medium 3.5 and o4-mini don't publish scores on any of the same benchmarks.