> ## Documentation Index > Fetch the complete documentation index at: https://docs.varg.ai/llms.txt > Use this file to discover all available pages before exploring further. # List a tool's models > The models of one tool, paginated by canonical model. Same route and pricing data as `GET /models`, plus a real generation `example` and the explicit per-model `input_schema` (JSON Schema). Auth is optional; `pipeline` models are visible only to callers granted access. ## OpenAPI ````yaml /openapi.yaml get /tools/{tool_key}/models openapi: 3.1.0 info: title: varg API version: 2.0.0 description: | Unified REST API for AI media generation at `api.varg.ai/v2`. One API key, ~80 models across 8 providers, async jobs, stable output URLs on `s3.varg.ai`, files with lineage, and transparent credit billing (1 credit = 1 cent = $0.01). **The async job pattern:** every generation request returns `202 Accepted` with a job object (`status: queued`). Poll `GET /jobs/{id}` until the job reaches a terminal status (`completed`, `failed`, or `cancelled`), then read `output.outputs[0].url`. Alternatively, set `options.webhook_url` in the request to receive an HMAC-signed callback when the job finishes. servers: - url: https://api.varg.ai/v2 security: - bearerAuth: [] tags: - name: Generation description: >- Create generation jobs (image, video, speech, music, transcription, ffmpeg, render, pipeline) - name: Tools description: Discover tools, their schemas, and call any tool generically - name: Jobs description: Poll and manage job lifecycle - name: Files description: Upload, import, probe, and manage files - name: Folders description: Group files into folders and file generated output automatically - name: Lineage description: Resolve which job produced a file - name: Presets description: Browse and apply reusable parameter values — voices, styles - name: Templates description: Browse, publish, use and render community templates - name: Pricing description: Estimate costs and browse the price catalog - name: Billing description: Balance, usage, and transaction history - name: Analytics description: >- Spend, runs and files over time — summaries, time series, breakdowns, activity - name: Account description: Identity and API key management paths: /tools/{tool_key}/models: get: tags: - Tools summary: List a tool's models description: | The models of one tool, paginated by canonical model. Same route and pricing data as `GET /models`, plus a real generation `example` and the explicit per-model `input_schema` (JSON Schema). Auth is optional; `pipeline` models are visible only to callers granted access. operationId: listToolModels parameters: - name: tool_key in: path required: true schema: type: string example: image description: Tool key (`image`, `video`, `speech`, ...). - name: page in: query schema: type: integer minimum: 1 default: 1 - name: limit in: query schema: type: integer minimum: 1 maximum: 50 default: 25 description: Models per page. Out-of-range values are clamped. responses: '200': description: A page of models content: application/json: schema: $ref: '#/components/schemas/ToolModelsResponse' '404': description: Unknown tool content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' examples: unknownTool: value: error: code: tool_not_found message: 'Unknown tool: imag' security: - {} - bearerAuth: [] components: schemas: ToolModelsResponse: type: object required: - version - page - limit - total - data properties: version: type: - string - 'null' page: type: integer limit: type: integer total: type: integer description: Total models for the tool. data: type: array items: $ref: '#/components/schemas/ToolModelEntry' ErrorResponse: type: object properties: error: type: object properties: code: type: string example: model_not_found message: type: string example: 'Unknown model: flux-shnell' details: {} ToolModelEntry: allOf: - $ref: '#/components/schemas/ModelEntry' - type: object required: - example - input_schema properties: example: type: - object - 'null' additionalProperties: true description: >- A real generation sample (`input` and `output`) from the priority route. input_schema: type: - object - 'null' additionalProperties: true description: JSON Schema for the model's request body. ModelEntry: type: object required: - model - tool - display_name - description - routes properties: model: type: string description: Canonical model name; pass as `model` for auto-routing. example: kling_v2_6 tool: type: string example: video display_name: type: - string - 'null' description: type: - string - 'null' routes: type: array items: $ref: '#/components/schemas/ModelRoute' ModelRoute: type: object required: - model_key - provider - modality - output_type - description - priority - accepts_files - pricing - ops - schema_url properties: model_key: type: string description: Exact route address; pass as `model` to pin this route. example: fal:kling_v2_6/text_to_video provider: type: string example: fal modality: type: - array - 'null' items: type: string example: - text-to-video output_type: type: - string - 'null' example: video description: type: - string - 'null' priority: type: integer description: Auto-routing order; lower is preferred. accepts_files: type: boolean description: Whether the route maps the unified `files` input. pricing: type: object required: - pricing_id - rule - user_price_estimate_cents - min_user_price_cents properties: pricing_id: type: - string - 'null' rule: type: - object - 'null' additionalProperties: true description: Pricing rule (shape varies by `type`). user_price_estimate_cents: type: - number - 'null' description: Worst-case price in cents. min_user_price_cents: type: - number - 'null' description: Cheapest case price in cents, null when the rule has no minimum. ops: type: object required: - delivery - poll_interval_ms - estimated_duration_ms - max_timeout_ms properties: delivery: type: - string - 'null' example: poll poll_interval_ms: type: - integer - 'null' estimated_duration_ms: type: - integer - 'null' max_timeout_ms: type: - integer - 'null' schema_url: type: string description: >- Path (relative to the API origin) of the input schema for this route. securitySchemes: bearerAuth: type: http scheme: bearer description: | varg API key (`varg_...`). Get one at [app.varg.ai](https://app.varg.ai) or run `bunx vargai login`. App sessions may alternatively send a Supabase JWT. ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.