Pixtral Large is Mistral AI's native multimodal model with a 128K context window and equal 128K max output, natively supporting both text and image inputs — meaning developers can feed in screenshots, scanned documents, or photos alongside text prompts without relying on separate vision adapters.
https://api.mistral.ai/v1 pixtral-large Pixtral Large is listed for chat, vision workloads and supports a 128K context window.
Check Mistral AI's current endpoint status before integrating this listing. Use the alternatives table if the provider listing is unavailable.
We only found this pixtral listing on Mistral AI in the current catalog. Use the related models section for nearby alternatives.
| Provider | Model listing | Access | Context | API | Limits |
|---|---|---|---|---|---|
| | Pixtral Large | Check provider | 128K | OpenAI-style | ~1 RPS, 500K TPM |
| Model | Provider | Context | Access |
|---|---|---|---|
| Mistral 7B | Mistral AI | 33K | Free tier |
| Mixtral 8x7B | Mistral AI | 33K | Free tier |
| Mistral Medium 3.5 (128B) | Mistral AI | 256K | Free tier |
| Mistral Small 4 | Mistral AI | 256K | Free tier |
| Mistral Large 3 | Mistral AI | 256K | Free tier |
Pixtral Large is tagged for chat in this catalog and works with OpenAI-compatible client libraries.
Pixtral Large is tagged for vision in this catalog and works with OpenAI-compatible client libraries.
Pixtral Large appears in the free model catalog for Mistral AI, but its current endpoint availability should be confirmed with the provider before use.
The model ID shown in this catalog is pixtral-large.
The listed free tier limit is ~1 RPS, 500K TPM. Limits can change per account tier, so confirm against the provider dashboard.
The listed context window is 128K tokens with up to 128K output tokens.
Pixtral Large is Mistral AI's native multimodal model with a 128K context window and equal 128K max output, natively supporting both text and image inputs — meaning developers can feed in screenshots, scanned documents, or photos alongside text prompts without relying on separate vision adapters. Its 128K output ceiling makes it practical for tasks that demand long-form generation, such as detailed report writing or full-document analysis from visual inputs. Available on Mistral's free Experiment plan with no credit card required, the main constraint is the ~1 request/second rate limit, making it better suited for interactive use and prototyping rather than batch processing or high-throughput pipelines.
For API keys, setup steps, and provider-level limits, see the Mistral AI provider page.