Data verified: Aug 15, 2026, 11:13 AM · Prices sourced from official provider pages. Verify current rates before production use.
Data verified: Aug 15, 2026, 11:13 AM · Prices sourced from official provider pages. Verify current rates before production use.
Price, context and performance head to head. Data synced from the provider catalog.
Cheaper
MiniMax M2-her
Larger context
Mistral Medium 3.5
Faster
MiniMax M2-her
Higher quality
Mistral Medium 3.5
| Feature | MiniMax M2-her | Mistral Medium 3.5 |
|---|---|---|
| Provider | MiniMax | Mistral |
| Tier | Budget | Mid-tier |
| Input per 1M tokens | $0.3 | $1.5 |
| Output per 1M tokens | $1.2 | $7.5 |
| Cached input per 1M | $0.03 | $1.5 |
| Context window | 65.5K | 262.1K |
| Intelligence index | — | 30/100 |
| Coding index | — | 47/100 |
| Agentic index | — | 19/100 |
| GPQA Diamond | — | — |
| Tau-bench (airline) | — | — |
| Speed | Fast | Standard |
| Vision (image input) | No | Yes |
| Function calling | No | Yes |
| Batch API | No | No |
Enter how many requests per day you send with an average prompt (1K input + 1K output) and compare the monthly cost of both models.
MiniMax M2-her saves $22.5/mo vs Mistral Medium 3.5
Want us to build it for you?
We integrate MiniMax M2-her or Mistral Medium 3.5 into your product with caching, observability and continuous evaluation — typically 40-80% cheaper than the obvious first pick.
Other combinations developers frequently compare in 2026.
What people ask us when comparing GPT, Claude, Gemini and the rest.
A token is the unit an AI model processes: usually between half a word and a full word. Rule of thumb: 1,000 tokens ≈ 750 English words. A 20-word sentence is about 26 tokens; a 300-word email is around 400. Models charge for input tokens (your prompt) and output tokens (their answer) separately.