mistralai logo
mistralai

Mistral: Pixtral Large 2502

Source description (English)

Pixtral Large 2502 is the February 2025 version of Mistral AI's large multimodal model, following Pixtral Large 2411. It accepts text and image input, including documents, charts, and natural images,...

Overview

Model specifications

Context
128,000 tokens
Maximum output
102,400 tokens
Architecture
text+image->text
Tokenizer
Mistral
Knowledge cutoff
Not provided
Moderated
Yes
OPENROUTER

Complete pricing

Synchronized OpenRouter rates. Token prices are shown per one million tokens.

Input
$2
per 1M tokens
Output
$6
per 1M tokens
API

Quick start

Set OPENROUTER_API_KEY locally. Python requires requests; JavaScript runs in Node.js. Keep the key on the server.

API documentation

curl --fail-with-body https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"mistralai/pixtral-large-2502","messages":[{"role":"user","content":"Hello!"}]}'
Capabilities

Input → Output

Input
textimage
Output
text
API

Supported API parameters

max_tokensstoptemperaturetop_ktop_p
Available providers

1 Provider

Checked: November 21, 2026

Live providers on OpenRouter

Provider availability, latency, throughput and routing can change continuously. Open the source page for current operational data.

OpenRouter

Amazon Bedrock

Not provided
Context
128K
Maximum output
102K
Input
$2
Output
$6
Cache read
Not provided
Cache write
Not provided
mistralai

4 models

All models