Mistral Large vs Mistral Medium 3.5
Mistral Large (Mistral) and Mistral Medium 3.5 (Mistral) are listed at different prices. Mistral Medium 3.5 costs less for input, $1.50 per 1M tokens against $2.00; Mistral Large costs less for output, $6.00 per 1M tokens against $7.50. Mistral Medium 3.5 has the larger context window, 262,144 tokens against 128,000 for Mistral Large. Only Mistral Medium 3.5 supports a reasoning effort setting. Mistral Large accepts text and files and produces text; Mistral Medium 3.5 accepts text, images and files and produces text.
Mistral Large accepts text and file inputs, while Mistral: Mistral Medium 3.5 also accepts images. Both produce text and support tools, structured outputs, and response formats; Medium 3.5 additionally lists reasoning and has a 262,144-token context window versus Large’s 128,000.
Compared from catalog data checked
Side by side
0.00 the better figure in a row| Specification | Mistral Large | Mistral Medium 3.5 |
|---|---|---|
| Maker | Mistral | Mistral |
| Added to catalog | 26 Feb 2024 | 30 Apr 2026 |
| Input, per 1M tokens | $2.00 | $1.50 |
| Output, per 1M tokens | $6.00 | $7.50 |
| Cached input read, per 1M | $0.20 | n/a |
| Context windowTokens | 128,000 | 262,144 |
| Max outputTokens | 102,400 | 209,715 |
| Accepts | file, text | file, image, text |
| Produces | text | text |
| Tool calling | Yes | Yes |
| Structured outputs | Yes | Yes |
| Reasoning effort control | No | Yes |
List prices through OpenRouter, in US dollars. Each model's page has its variants, price history and sample outputs.
What the same task costs
List price for one request, from the token counts shown. The same four tasks are priced on every model page.
| Task | Mistral Large | Mistral Medium 3.5 |
|---|---|---|
| Answer a short question500 in / 300 out | $0.0028 | $0.0030 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.055 | $0.044 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.072 | $0.060 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.309 | $0.236 |
Which to choose
Choose Mistral Large if
- Output tokens cost less: $6.00 against $7.50 per 1M
- Cached input costs less: $0.20 against n/a per 1M
Choose Mistral Medium 3.5 if
- Input tokens cost less: $1.50 against $2.00 per 1M
- You need the larger context window: 262,144 tokens against 128,000
- You need longer answers in one response: 209,715 tokens against 102,400
- It has to read images, which the other model does not
- You want to set how much it reasons before it answers
Neither maker's quality claims are repeated here. The reliable test is your own task: ask both the same question and read the two answers.