import requests r = requests.post( "https://api.aimlapi.com/v1/chat/completions", headers={"Authorization": "Bearer " + AIMLAPI_KEY}, json={ "model": "mistralai/voxtral-small-24b-2507", "messages": [ { "role": "user", "content": "Hello!" } ] }, ) print(r.json())
const r = await fetch("https://api.aimlapi.com/v1/chat/completions", { method: "POST", headers: { Authorization: `Bearer ${process.env.AIMLAPI_KEY}`, "Content-Type": "application/json", }, body: JSON.stringify({ "model": "mistralai/voxtral-small-24b-2507", "messages": [ { "role": "user", "content": "Hello!" } ] }), }); console.log(await r.json());
curl -X POST https://api.aimlapi.com/v1/chat/completions \ -H "Authorization: Bearer $AIMLAPI_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"mistralai/voxtral-small-24b-2507","messages":[{"role":"user","content":"Hello!"}]}'
OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Input | |
| Output | |
| Cached input |
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
Voxtral Small 24B 2507 This page | Reasoning + agents | |||
| Reasoning + agents | ||||
| Balanced coding + agents | ||||
| Long-context, multimodal & agentic workflows | ||||
| Reasoning + agents |
Voxtral Small 24B 2507 has a 32,000 tokens context window.
Voxtral Small 24B 2507 takes image, text as input and returns text.
Use mistralai/voxtral-small-24b-2507 as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.
Voxtral Small 24B 2507 is priced at input $0.13754 / 1M tokens, output $0.41262 / 1M tokens, cached input $0.013754 / 1M tokens.
Yes, Voxtral Small 24B 2507 can stream responses as they are generated.
Yes, Voxtral Small 24B 2507 accepts image input alongside text.
Voxtral Small 24B 2507 was built by Mistral AI.
Yes, it supports function calling, including parallel tool calls, as well as structured outputs and web search.