Mistral Medium 3.5 → Qwen3.8 Max: cost per request on six tasks
Qwen3.8 Max costs between 10% less and 30% more than Mistral Medium 3.5 per request on six common tasks. It costs no more per result that works if its results work first time at least 90% as often as Mistral Medium 3.5's on translation, and 31% more often on search re-ranking. Mistral has announced Mistral Medium 3.5's API shutdown for 2027-04-30.
List prices per million tokens
| Model | Input | Cached input | Output |
|---|---|---|---|
| Mistral Medium 3.5 | $1.50 | n/a | $7.50 |
| Qwen3.8 Max | $2.00 | n/a | $6.00 |
Prices checked 2026-11-12.
Cost per 1,000 requests
| Task | Mistral Medium 3.5 | Qwen3.8 Max | Change | Cheaper per result that works if it works first time at least |
|---|---|---|---|---|
| Support bot answerInstructions, three help-centre passages and the customer's question in; a short answer out. | $6.75 | $7.80 | 16% more | 16% more often than Mistral Medium 3.5 |
| Invoice field extractionInstructions and one invoice's text in; about 15 fields as JSON out. | $5.63 | $6.50 | 16% more | 16% more often than Mistral Medium 3.5 |
| Lead scoringScoring rules and one lead's form answers in; a score and a one-line reason out. | $2.55 | $3.00 | 18% more | 18% more often than Mistral Medium 3.5 |
| Email reply draftInstructions and the email thread so far in; a reply of about 300 words out. | $5.25 | $5.40 | 3% more | 3% more often than Mistral Medium 3.5 |
| TranslationInstructions and about 500 words of text in; the same text in another language out. | $7.35 | $6.60 | 10% less | 90% as often as Mistral Medium 3.5 |
| Search re-rankingA search query and 20 result snippets in; the ids of the best five, in order, out. | $6.38 | $8.30 | 30% more | 31% more often than Mistral Medium 3.5 |
Token counts are typical sizes, not measurements.
Mistral Medium 3.5 is being shut down
Mistral has announced Mistral Medium 3.5's API shutdown for 2027-04-30, with Mistral Large 4 as the replacement (source).
Test it on your own prompt
The model switch test runs your prompt on both models side by side with your own API key, in your browser.