Mixtral 8x22B Instruct vs Pixtral Large 2502
Mixtral 8x22B Instruct (Mistral) and Pixtral Large 2502 (Mistral) have the same list price: $2.00 per 1M input tokens and $6.00 per 1M output tokens. Pixtral Large 2502 has the larger context window, 128,000 tokens against 65,536 for Mixtral 8x22B Instruct. Only Mixtral 8x22B Instruct supports tool calling. Mixtral 8x22B Instruct accepts text and files and produces text; Pixtral Large 2502 accepts text and images and produces text.
Mistral: Mixtral 8x22B Instruct accepts text and files, while Mistral: Pixtral Large 2502 accepts text and images; both produce text. Pixtral Large 2502 has a 128,000-token context, compared with 65,536 tokens for Mixtral 8x22B Instruct.
Compared from catalog data checked
Side by side
0.00 the better figure in a row| Specification | Mixtral 8x22B Instruct | Pixtral Large 2502 |
|---|---|---|
| Maker | Mistral | Mistral |
| Added to catalog | 17 Apr 2024 | 20 Nov 2026 |
| Input, per 1M tokens | $2.00 | $2.00 |
| Output, per 1M tokens | $6.00 | $6.00 |
| Cached input read, per 1M | $0.20 | n/a |
| Context windowTokens | 65,536 | 128,000 |
| Max outputTokens | 52,428 | 102,400 |
| Accepts | file, text | image, text |
| Produces | text | text |
| Tool calling | Yes | No |
| Structured outputs | Yes | No |
| Reasoning effort control | No | No |
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 | Mixtral 8x22B Instruct | Pixtral Large 2502 |
|---|---|---|
| Answer a short question500 in / 300 out | $0.0028 | $0.0028 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.055 | $0.055 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.072 | $0.072 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.309 | $0.309 |
Which to choose
Choose Mixtral 8x22B Instruct if
- Cached input costs less: $0.20 against n/a per 1M
- You need tool calling
- You need answers in a fixed JSON schema
Choose Pixtral Large 2502 if
- You need the larger context window: 128,000 tokens against 65,536
- You need longer answers in one response: 102,400 tokens against 52,428
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.