Mistral-Small-3.2-24B-Instruct is a drop-in upgrade over the 3.1 release, with markedly better instruction following, roughly half the infinite-generation errors, and a more robust function-calling interface—while otherwise matching or slightly improving on all previous text and vision benchmarks.
function_callinghttps://api.deepinfra.com/v1/openai/v1/chat/completions| Model | Context | Max out | Pricing |
|---|---|---|---|
| Mistral-Nemo-Instruct-2407 | 131K | — | $0.03$0.03 |
| Mistral-Small-24B-Instruct-2501 | 33K | — | $0.05$0.08 |
| Mistral-Small-3.2-24B-Instruct-2506 | 128K | — | $0.08$0.2 |
/v1/models/deepinfra/mistralai/Mistral-Small-3.2-24B-Instruct-2506Mistral-Small-3.2-24B-Instruct is a drop-in upgrade over the 3.1 release, with markedly better instruction following, roughly half the infinite-generation errors, and a more robust function-calling interface—while otherwise matching or slightly improving on all previous text and vision benchmarks.