Mistral OCR Latest API

mistral/mistral-ocr-latest
AI-powered OCR API with 94.89% accuracy, processing 2000 pages/min, excelling in multimodal document understanding.
Output
$0.001 / page
Released
Dec 16, 2025

How to use Mistral OCR Latest API

Install any OpenAI-compatible SDK, point it at api.aimlapi.com/v1, and set the model to mistral/mistral-ocr-latest.
import requests, time

headers = {"Authorization": "Bearer " + AIMLAPI_KEY}
job = requests.post(
    "https://api.aimlapi.com/v2/generate/audio",
    headers=headers,
    json={
      "model": "mistral/mistral-ocr-latest",
      "prompt": "Upbeat lofi background music"
    },
).json()
gid = job["generation_id"]

while True:
    res = requests.get(f"https://api.aimlapi.com/v2/generate/audio?generation_id={gid}", headers=headers).json()
    if res.get("status") in ("completed", "error", "failed"):
        break
    time.sleep(3)
print(res)
const headers = {
  Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
  "Content-Type": "application/json",
};
const job = await (await fetch("https://api.aimlapi.com/v2/generate/audio", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "model": "mistral/mistral-ocr-latest",
    "prompt": "Upbeat lofi background music"
  }),
})).json();

let res;
do {
  await new Promise((r) => setTimeout(r, 3000));
  res = await (await fetch(`https://api.aimlapi.com/v2/generate/audio?generation_id=${job.generation_id}`, { headers })).json();
} while (!["completed", "error", "failed"].includes(res.status));
console.log(res);
# submit the job — the response contains "generation_id"
curl -X POST https://api.aimlapi.com/v2/generate/audio \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"mistral/mistral-ocr-latest","prompt":"Upbeat lofi background music"}'

# then poll for the result until it is ready
curl "https://api.aimlapi.com/v2/generate/audio?generation_id={generation_id}" -H "Authorization: Bearer $AIMLAPI_KEY"

OpenAI-compatible — swap the base URL and it works with your existing SDK.

Mistral OCR Latest API Pricing

TypePrice
Input
Output
$0.001 / page

Mistral OCR Latest vs other models

ModelInputOutputContextBest for
$0.001 / page
Audio generation
$5.2 / 1K pages
Audio generation
$2.6 / 1K pages
Audio generation
$0.013 / page
Audio generation
$0.0078 / page
Audio generation

Frequently asked questions

Mistral OCR Latest takes document, image as input and returns text.

Mistral OCR Latest became available on December 16, 2025.

Mistral OCR Latest is priced at $0.001 / page.

Mistral OCR Latest is billed per generation — a fixed charge per output rather than by prompt length.

Mistral OCR Latest was built by Mistral AI.

Send a request to v1/ocr with mistral/mistral-ocr-latest as the model id.

Yes. Mistral OCR Latest is served through AI/ML API, so the same key and endpoint format used for other models applies.

The model id is mistral/mistral-ocr-latest.

Start building with Mistral OCR Latest

Get API Key
1000+ models, one API.