Capabilities - Infery.ai

Each model declares capabilities as boolean flags. You can read them from each entry’s _infery object in GET /v1/models to branch feature-by-feature in your app.

Capability	Meaning
`supportsChat`	Accepts chat completions format
`supportsStreaming`	Can stream tokens via SSE
`supportsVision`	Accepts image inputs
`supportsPdf`	Accepts PDF natively (otherwise gateway auto-converts)
`supportsTools`	Honours `tools` array + `tool_choice`
`supportsJsonMode`	`response_format: {type: "json_object"}` or JSON schema
`supportsImages`	Generates images as output (different from Vision)
`isReasoning`	Chain-of-thought reasoning model (slower but more accurate on complex tasks)
`isFlagship`	Provider’s top-of-line model (highest quality + cost)

Reading the flags for a real model

These flags are per model, not per provider, and they move when a model is updated — so this page does not list them model by model. Two places do:

The catalog pages show streaming, tools, vision, pdf and json mode on every row, grouped by modality and sorted by owner.
GET /v1/models returns the full _infery object for each model, including isReasoning and isFlagship, which the catalog pages do not show.

Branch on the flag, never on the model name. A slug can gain supportsTools without changing its name, and a name-based check will not notice.

PDF fallback

If a model without supportsPdf receives a PDF, our gateway:

Extracts text via pdftotext
Renders pages to PNG (for vision models)
Injects text + images into the message
Bills a small pdf_extraction_per_page fee

You don’t lift a finger — works on Grok, DeepSeek, older models. The response behaves as if the model read the PDF natively.