Voxtral Small 24B 2507 API

mistralai/voxtral-small-24b-2507
Voxtral Small 24B 2507 on AIMLAPI.
Context
32K tokens
Input
$0.13754 / 1M tokens
Output
$0.41262 / 1M tokens

How to use Voxtral Small 24B 2507 API

Install any OpenAI-compatible SDK, point it at api.aimlapi.com/v1, and set the model to mistralai/voxtral-small-24b-2507.
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.

Voxtral Small 24B 2507 API Pricing

TypePrice
Input
$0.13754 / 1M tokens
Output
$0.41262 / 1M tokens
Cached input
$0.013754 / 1M tokens

Voxtral Small 24B 2507 Benchmarks

BenchmarkScoreWhat it measuresSourceRetrieved
FLEURS WER
5.1% (avg, lower better)
WER on multilingual speech (102 languages)SourceJuly 12, 2026
LibriSpeech WER
1.53% (test-clean, lower better)
Word Error Rate on read English speech (lower better)SourceJuly 12, 2026

Voxtral Small 24B 2507 vs other models

ModelInputOutputContextBest for
$0.13754 / 1M tokens
$0.41262 / 1M tokens
32K tokens
Reasoning + agents
$6.5 / 1M tokens
$39 / 1M tokens
1.05M tokens
Reasoning + agents
$2.6 / 1M tokens
$13 / 1M tokens
1M tokens
Balanced coding + agents
$3.9 / 1M tokens
$19.5 / 1M tokens
1M tokens
Long-context, multimodal & agentic workflows
$0.65 / 1M tokens
$3.9 / 1M tokens
1.05M tokens
Reasoning + agents

Frequently asked questions

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.

Start building with Voxtral Small 24B 2507

Get API Key
1000+ models, one API.