Pixtral Large 2411

Provider: Mistral AI EU

No longer listed on OpenRouter since 2026-05-31. The figures below are the last recorded values.
Input price
$2.00
/ 1M tokens
Output price
$6.00
/ 1M tokens
Cache price
$0.20
/ 1M tokens (read)
Context
131K tokens
Max output Unknown

Overview

Pixtral Large 2411 is a flagship multimodal model from Mistral AI (EU), designed for complex reasoning tasks that require understanding both text and images. With support for vision, function-calling, and JSON mode, it targets advanced applications needing structured outputs and interaction capabilities.

Strengths

  • Integrates vision capabilities for understanding and processing image inputs alongside text.
  • Supports robust function-calling, enabling complex agentic workflows and tool integrations.
  • Offers a dedicated JSON mode for reliable generation of structured data outputs.
  • Provides a very large 131072 token context window suitable for extensive inputs.
  • Competitive output pricing at $6/1M tokens compared to similarly-priced peers.

Best use cases

  • Multimodal analysis and content generation from combined text and image data.
  • Automating complex workflows by integrating with external tools via function-calling.
  • Building intelligent agents that require structured JSON outputs for automation.
  • Processing and summarizing extensive documents, codebases, or long-form conversations.
  • Applications benefiting from cost savings through its efficient cache read pricing.

Pricing position

Pixtral Large 2411 is positioned at the premium end of Mistral AI's portfolio, with input pricing at $2/1M tokens and output pricing at $6/1M tokens. While significantly more expensive than siblings like Mistral Nemo ($0.02/M in), its input price aligns with peers like GPT-4.1 and Sonar Reasoning Pro, but its output price of $6/M is notably lower than most, including GPT-4.1 ($8/M) and Gemini 3.1 Pro Preview ($12/M).

Caveats

The maximum output token limit for Pixtral Large 2411 is currently unknown, which could be a consideration for applications requiring very long generations. There is no free tier available for this model. For purely text-based tasks or applications with smaller context needs, other Mistral models like Mistral Small 3.2 24B ($0.075/M in) offer significantly more cost-effective solutions.

Notes drafted by an LLM from the figures on this page (2026-05-21) and rewritten when the price changes.

Key facts

Max output
Unknown
Tracked since
2026-05-08
Last updated
2026-05-31

Features

Image inputFunction callingJSON output

Price history

  • 2026-05-31 No longer listed

Monthly cost estimate

Scale Input (M) Output (M) Monthly
0.1M (hobby) 0.1 0.05 $0.50
1M (small app) 1 0.5 $5.00
10M (mid scale) 10 5 $50.00
100M (large) 100 50 $500.00

※ Cache and batch discounts not factored in. Detailed calculator

Official resources

Other models from Mistral AI

Similar-priced models

Source: OpenRouter API