List Available LLM Models

Retrieve a list of all available Large Language Models (LLMs) that can be used in Tasks. **Note**: This endpoint returns a plain array of models, not a paginated response. All available models are returned in a single request. By default, only active models available to the project are returned. Use `include_retired=true` to include retired models and `include_excluded=true` to include models excluded by organization or project rules. Optionally filter by vision (input) using one or more `vision` query parameters (e.g. `?vision=image&vision=pdf`). The model must support all listed: `image` (image input), `pdf` (PDF vision input). Use `output=image` to restrict to models that can generate images (supports_image_output). Each model entry includes standard fields like: - Unique identifier (`id`) - Provider information (`provider`) - Vendor information (`vendor`) - Model reference name (`name`) - Human-readable alias (`alias`) - Detailed description (`description`) - Vision support status (`supports_vision`) - Whether the model can process images - Image output support (`supports_image_output`) - Whether the model can generate images - PDF vision support (`supports_pdf_vision`) - Whether the model can process PDFs as visual input, with limits in `pdf_vision_config` - Tool calling support (`supports_tool_calling`) - Context caching support (`supports_context_caching`) - Price tier (`price`) - Coarse comparison tier: cheap, average, or expensive - Speed tier (`speed`) - Coarse comparison tier: standard, fast, or ultra fast - Knowledge cutoff (`knowledge_cutoff`) - Date of most recent training data, when known - Maximum context window (`max_context_window`) - Allowed model parameters (`model_params`) - JSON Schema for parameters this model accepts (e.g. `temperature`) - Creation and last-modified timestamps (`created`, `modified`) - Known issues logged against the model (`llm_model_comments`) - When the model was retired (`retired`) - The model that replaces it (`replaced_by`) Models may have different capabilities, performance characteristics, and cost structures. Choose models based on your specific needs.