TokenRate

Pixtral 12B Pricing

Fast

Mistral · 128K tokens context

Pixtral 12B from Mistral costs $0.100 per 1 million input tokens and $0.100 per 1 million output tokens as of June 2026. The model supports a 128,000-token context window (approximately 96,000 words) with a 4K-token maximum output. A typical 1,000-token request costs $0.0001 in input charges; a 10,000-token request costs $0.0010.

Pixtral 12B pricing and capability summary
Input price$0.100 / 1M tokens
Output price$0.100 / 1M tokens
Output / input ratio1.0×
Context window128,000 tokens (~96,000 words)
Maximum output4,096 tokens
Cost per 1K tokens (input)$0.0001
TierFast
Last verified

Pixtral 12B is Mistral's multimodal model — a 12B vision-language model designed for image understanding at a very low price. Self-hostable and capable of document and image analysis tasks.

Reference pricing · updated 2026-06-10

Input Price

$0.100

per 1 million tokens

Output Price

$0.100

per 1 million tokens

Context Window

128K tokens

max 4K output

Cost Examples

Request TypeTokensInput CostOutput Cost
1,000 word article1,333$0.000133$0.00004
10-page document (2,500 words)3,333$0.000333$0.0001
1,000 lines of code5,000$0.0005$0.00015
100K token document100,000$0.01$0.003

Output cost estimated at 30% of input token count. Use the calculator for exact figures.

Strengths

  • Multimodal at $0.10/1M — extremely cheap for vision
  • Open weights
  • Good document and chart understanding

Limitations

  • Not for complex visual reasoning
  • Smaller than GPT-4o Vision

Best Use Cases

Budget image classification
Document OCR
Visual data extraction

Calculate Pixtral 12B Costs

Use the TokenRate calculator to convert any budget, token count, or text into exact Pixtral 12B costs — and compare across all models.

Open Calculator →

Pixtral 12B — FAQ

Related Models

Related Guides