Pixtral Large 2502 overview
Pixtral Large 2502 by Mistral AI
Pixtral Large 2502 is the February 2025 version of Mistral AI's large multimodal model, following Pixtral Large 2411. It has a 128K-token context window.
Pixtral Large 2502 specs
- Model ID
mistralai/pixtral-large-2502- Developer
- Mistral AI
- Context window
- 128,000 tokens
- Max output
- 102,400 tokens
- Input
- Image, Text
- Output
- Text
- API
- OpenAI-compatible, base URL
https://api.aimlapi.com/v1
Ask about an image in the same conversation
Text and images travel in one chat request, so a question can point at a chart, a scanned page or a photo that you send with it. The reply is always text. The model describes, extracts and explains what it sees, and it does not return images.
Put the question next to the image and say what form the answer should take, such as a list of values or a short summary. Then check any numbers the model reads from a chart against the source.
Streaming and long answers
Streaming is available for this model. The maximum output is 102,400 tokens, so a detailed answer can run long. Turn streaming on when a user waits for the reply, so the text appears as it is generated.
Start with a narrow question on one document to see the format of the answer. Widen the request once that output looks right.
Pixtral Large 2502 or 2411
Pixtral Large 2502 follows Pixtral Large 2411 as the newer release. Run both on the same set of your own documents and charts before you switch, and compare the extracted values side by side.
Use cases
Answer questions about a scanned document by sending the page image with your question.
Read values from a chart image and return them as text.
Describe a natural photo for a catalog entry or an accessibility caption.
Stream a long written explanation of an image to a user in a chat interface.
Capabilities
- Streaming
- Vision
Pixtral Large 2502 API pricing
| Usage | Price | Unit |
|---|---|---|
| Input | $2.116 | 1M tokens |
| Output | $6.348 | 1M tokens |
Prices from the AI/ML API price list, checked on Nov 20, 2026.
Pixtral Large 2502 vs other models: token prices
AI/ML API input and output rates for 5 models, per million tokens.
| Model | Input | Output |
|---|---|---|
| $2.116 | $6.348 | |
| $0.198375 | $0.7935 | |
| $1.36 | $4.18 | |
| Palmyra X5 | $0.6348 | $6.348 |
| $1.587 | $7.935 |
How to use the Pixtral Large 2502 API
View docsBuild with your agent
Give your agent the model details, code and documentation.
1Get your API key
Create API keyexport AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"2Make your first request
curl 'https://api.aimlapi.com/v1/chat/completions' \
-H "Authorization: Bearer $AIMLAPI_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "mistralai/pixtral-large-2502",
"messages": [
{
"role": "user",
"content": "Write a haiku about the ocean."
}
]
}'import os
import requests
headers = {
"Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
"Content-Type": "application/json",
}
payload = {
"model": "mistralai/pixtral-large-2502",
"messages": [
{
"role": "user",
"content": "Write a haiku about the ocean."
}
]
}
response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())const response = 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/pixtral-large-2502",
"messages": [
{
"role": "user",
"content": "Write a haiku about the ocean."
}
]
}),
});
if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());Pixtral Large 2502 FAQ
How much does Pixtral Large 2502 cost?
Pixtral Large 2502 costs $2.116 / 1M tokens for input and $6.348 / 1M tokens for output on AI/ML API.
What inputs does Pixtral Large 2502 accept?
It accepts text and image input. The images can be documents, charts or natural images.
Can it generate images?
No. The output is text only, so it describes or analyzes images and does not create them.
Does it support streaming?
Yes. Streaming is listed among its capabilities, next to vision. The maximum output is 102,400 tokens.
How does it differ from Pixtral Large 2411?
Pixtral Large 2502 is the February 2025 version that follows Pixtral Large 2411. Test both on your own documents to see how the answers differ for your task.
What is the Pixtral Large 2502 model ID?
Use mistralai/pixtral-large-2502 as the model parameter. Requests go to the OpenAI-compatible endpoint with your AI/ML API key.
What is the context window of Pixtral Large 2502?
Pixtral Large 2502 accepts up to 128,000 tokens of context and returns up to 102,400 output tokens.