impulse

Mistral OCR 2512

OCR
API id mistral-ocr-2512
Input / 1M
-
not listed
Output / 1M
-
not listed
Context window
-
tokens
Max output
-
tokens per reply
Hosts
2
2 listings
Released
-
date not published

Where to run it

2 hosts serve Mistral OCR 2512. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
Mistral AILab API
mistral-ocr-2512
-
mistral-ocr-2512
-

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
Text
Produces
Text

Similar models

This model has no listed price, so these are current models with similar capabilities.

Smaller Mistral AI models

No similar Mistral AI model keeps its key capabilities.

Other frontier labs

No similar match from another frontier lab.

Open-weight picks

No similar open-weight match.

Model line

Newer and older versions, at each lab's own price.

  1. UndatedMistral OCR 2512LatestNot listed
  2. UndatedMistral OCR 2505Not listed
  3. UndatedMistral OCR 4.1Not listed
  4. UndatedMistral OCR 4Not listed
  5. UndatedMistral OCR 4.0Not listed
  6. UndatedMistral OCR 3Not listed
  7. UndatedMistral OCR 3.0Not listed

Call it

Using Mistral AI's API.

Python
from litellm import completion

response = completion(
    model="mistral/mistral-ocr-2512",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

Which APIs offer Mistral OCR 2512?

Mistral OCR 2512 runs on 2 APIs: Mistral AI and Azure AI Foundry.

Is Mistral OCR 2512 being retired?

No retirement date is scheduled for it on any API we track.

Is there a newer version of Mistral OCR 2512?

No. Mistral OCR 2512 is the newest model in its line.

What is Mistral OCR 2512's API model id?

Use mistral-ocr-2512 with Mistral AI.

Sources

Raw catalog entry for mistral-ocr-2512 on Mistral AI
{
  "litellm_provider": "mistral",
  "ocr_cost_per_page": 0.002,
  "ocr_cost_per_page_batches": 0.001,
  "annotation_cost_per_page": 0.003,
  "annotation_cost_per_page_batches": 0.0015,
  "mode": "ocr",
  "supported_endpoints": [
    "/v1/ocr",
    "/v1/batch"
  ],
  "source": "https://mistral.ai/pricing#api-pricing"
}