Pixtral Large (25.02) (US)
Mistral vision-language model for image understanding and multimodal chat
Model facts
- Context window
- 128K tokens
- Maximum output
- 8K tokens
- Cheapest paid input
- $2 per 1M tokens
- Cheapest paid output
- $6 per 1M tokens
- Open weights
- no
- Providers
- 1
Capabilities and modalities
tool calling, attachments, temperature control, text, image.
Observed price history
- 2026-09-09: $2 input / $6 output per 1M tokens
API providers
- Amazon Bedrock — model id us.mistral.pixtral-large-2502-v1:0; $2 input / $6 output per 1M tokens; provider documentation