> ## Documentation Index > Fetch the complete documentation index at: https://www.tryleap.ai/docs/llms.txt > Use this file to discover all available pages before exploring further. > ## Agent Instructions > Leap's API is at https://api.tryleap.ai. Send the key in the x-api-key header or as Authorization: Bearer; keys start with leap_. > Take model IDs and input schemas from GET /v1/models/{creator}/{name}, or from https://api.tryleap.ai/v1/public/models without a key. Never guess an input field: unknown fields are a 400. > Model inputs take uploaded file IDs (file_...), never URLs. > To give a coding agent the whole API, install the Leap skill: curl -fsSL https://www.tryleap.ai/install.sh | sh > The full OpenAPI 3.1 spec is at https://www.tryleap.ai/docs/openapi.json. # Retrieve a batch > A batch with every generation in it, each as `GET /v1/generations/{id}` would return it. Send `Prefer: wait=60` to hold the read until every run is final or 60 seconds pass. While any run isn't final, `Retry-After` says how many seconds to wait before the next read. Needs an API key with the `generations:read` scope. ## OpenAPI ````yaml /openapi.json get /v1/batches/{id} openapi: 3.1.0 info: title: Leap API version: 1.0.0 description: >- One API for the best image, video and audio models. Every request goes to `https://api.tryleap.ai` with your API key in the `x-api-key` header, or as `Authorization: Bearer leap_...`. Create a key at https://app.tryleap.ai/go/api. Guides, examples and the errors list are at https://www.tryleap.ai/docs. servers: - url: https://api.tryleap.ai security: - ApiKey: [] - Bearer: [] tags: - name: Models description: >- Every model and preset you can run, with its price and the JSON Schema of the input it takes. - name: Quotes description: >- The exact price of a run before you start it, with its input checked and its defaults filled in. - name: Generations description: >- A generation is one run of a model or preset: queued, then running, then succeeded, failed or canceled. Only a succeeded run is charged. - name: Batches description: >- Up to 50 generations priced and held together in one request, each then run as its own generation. - name: Webhooks description: >- URLs your workspace's events are POSTed to, signed following Standard Webhooks, and the default secret for the `webhook` URL a request names. - name: Events description: >- What happened in your workspace, kept 30 days, with each delivery to your webhooks and a way to send one again. - name: Files description: >- Photos, videos and sounds that models take as input. Upload one, then pass its `file_...` ID in the input field the model's schema names. - name: Credits description: Your workspace's balance in US dollars. externalDocs: url: https://www.tryleap.ai/docs paths: /v1/batches/{id}: get: tags: - Batches summary: Retrieve a batch description: >- A batch with every generation in it, each as `GET /v1/generations/{id}` would return it. Send `Prefer: wait=60` to hold the read until every run is final or 60 seconds pass. While any run isn't final, `Retry-After` says how many seconds to wait before the next read. Needs an API key with the `generations:read` scope. operationId: retrieveBatch parameters: - in: path name: id schema: type: string description: The batch's ID, `bat_...`. required: true description: The batch's ID, `bat_...`. - in: header name: Prefer schema: description: >- `wait=N` holds the request open for up to N seconds (at most 60) until the generation finishes, and `Preference-Applied` echoes the wait used. Most images finish inside the wait. If the run is still going when it ends, you get it back `queued` or `running`; poll it from there. Without this header the generation comes back queued at once. example: wait=60 type: string description: >- `wait=N` holds the request open for up to N seconds (at most 60) until the generation finishes, and `Preference-Applied` echoes the wait used. Most images finish inside the wait. If the run is still going when it ends, you get it back `queued` or `running`; poll it from there. Without this header the generation comes back queued at once. responses: '200': description: The batch, as it is now or when the wait ends. headers: X-Request-Id: $ref: '#/components/headers/X-Request-Id' RateLimit-Limit: $ref: '#/components/headers/RateLimit-Limit' RateLimit-Remaining: $ref: '#/components/headers/RateLimit-Remaining' RateLimit-Reset: $ref: '#/components/headers/RateLimit-Reset' Preference-Applied: schema: type: string description: The wait that was applied, such as `wait=60`. Retry-After: schema: type: integer minimum: 0 maximum: 9007199254740991 description: >- While a run is still `queued` or `running`: seconds to wait before you read it again, 2 for images and audio, 5 for video and 3D. A final answer has none. example: 5 content: application/json: example: id: bat_5Tq8Lm2Xv9Kr4Wn7Bc1Yd3Hp object: batch data: - id: gen_2Pk7Wd4Qx9Lm1Tn6Vb3Rc8Hy object: generation model: black-forest-labs/flux-2-pro modality: image status: queued provider: null revision: '2026-10-02' input: prompt: A fox in the snow, watercolor aspect_ratio: '1:1' 'n': 1 output: [] error: null usage: cost_usd: null source: api batch_id: bat_5Tq8Lm2Xv9Kr4Wn7Bc1Yd3Hp created_at: '2026-10-04T18:22:41.512Z' started_at: null completed_at: null - id: gen_9Rb3Hy6Tc1Vn8Lm4Qx7Wd2Pk object: generation model: black-forest-labs/flux-2-pro modality: image status: queued provider: null revision: '2026-10-02' input: prompt: A fox in the snow, linocut print aspect_ratio: '1:1' 'n': 1 output: [] error: null usage: cost_usd: null source: api batch_id: bat_5Tq8Lm2Xv9Kr4Wn7Bc1Yd3Hp created_at: '2026-10-04T18:22:41.512Z' started_at: null completed_at: null schema: $ref: '#/components/schemas/Batch' '400': $ref: '#/components/responses/ConflictingCredentials' '401': $ref: '#/components/responses/AuthenticationRequired' '403': $ref: '#/components/responses/PermissionDenied' '404': description: '`resource_not_found`' headers: X-Request-Id: $ref: '#/components/headers/X-Request-Id' RateLimit-Limit: $ref: '#/components/headers/RateLimit-Limit' RateLimit-Remaining: $ref: '#/components/headers/RateLimit-Remaining' RateLimit-Reset: $ref: '#/components/headers/RateLimit-Reset' content: application/json: schema: $ref: '#/components/schemas/Error' examples: resource_not_found: value: error: type: invalid_request_error code: resource_not_found message: That batch does not exist. param: null doc_url: null request_id: req_8kQ2vX9mR4tL6nB1cW3yZ5aD '429': $ref: '#/components/responses/RateLimitExceeded' components: headers: X-Request-Id: required: true description: >- This request's ID. Include it when you contact support; it's also `request_id` in an error. schema: type: string description: >- This request's ID. Include it when you contact support; it's also `request_id` in an error. example: req_01J9Z8Q4N2K7T5V3X6Y8B0C1D2 RateLimit-Limit: required: true description: Requests allowed per window from your client. schema: type: integer minimum: 0 maximum: 9007199254740991 description: Requests allowed per window from your client. example: 300 RateLimit-Remaining: required: true description: Requests left in the current window. schema: type: integer minimum: 0 maximum: 9007199254740991 description: Requests left in the current window. example: 299 RateLimit-Reset: required: true description: Seconds until the window resets. schema: type: integer minimum: 0 maximum: 9007199254740991 description: Seconds until the window resets. example: 42 Retry-After: required: true description: Seconds to wait before you retry. schema: type: integer minimum: 0 maximum: 9007199254740991 description: Seconds to wait before you retry. example: 42 schemas: Batch: type: object properties: id: type: string description: The batch's ID, `bat_...`. object: type: string const: batch data: type: array items: $ref: '#/components/schemas/Generation' description: Its generations, in the order you sent them. required: - id - object - data additionalProperties: false description: Up to 50 generations priced and held together, each run on its own. Error: type: object properties: error: type: object properties: type: type: string enum: - invalid_request_error - rate_limit_error - authentication_error - permission_error - conflict_error - billing_error - api_error description: >- The kind of error. Branch on `type` and `code`, never on `message`. code: type: string enum: - invalid_parameter - invalid_request - conflicting_credentials - placeholder_in_path - method_not_allowed - payload_too_large - unsupported_media_type - ip_rate_limit_exceeded - authentication_required - missing_api_key - invalid_api_key - permission_denied - not_found - resource_not_found - gone - conflict - rate_limit_exceeded - insufficient_credit - service_unavailable - internal_error description: >- A stable code for this error. Each one is explained at https://www.tryleap.ai/docs/errors. message: type: string description: >- What went wrong, written for a person. It can change; don't parse it. param: description: >- For a `400`, the field at fault, such as `input.prompt`; otherwise null. type: - string - 'null' doc_url: description: A page that explains this error, when there is one. type: - string - 'null' request_id: type: string description: >- This request's ID, as in the `X-Request-Id` header. Include it when you contact support. required: - type - code - message - param - doc_url - request_id additionalProperties: false required: - error additionalProperties: false Generation: type: object properties: id: type: string description: The generation's ID, `gen_` and 24 letters and digits. object: type: string const: generation model: type: string description: The model or preset it runs, with a preset's version. modality: type: string enum: - image - video - audio - 3d - text description: 'What it makes: `image`, `video`, `audio`, `3d` or `text`.' status: type: string enum: - queued - running - succeeded - failed - canceled description: >- `queued`, then `running`, then one of `succeeded`, `failed` or `canceled`. Only `succeeded` is charged. provider: description: >- Which upstream ran it, once one did. Informational: the model ID and input stay the same whichever runs it. type: - string - 'null' revision: type: string pattern: ^\d{4}-\d{2}-\d{2}$ description: The model's schema and price revision the run used. input: type: object propertyNames: type: string additionalProperties: anyOf: - type: - string - number - boolean - type: object propertyNames: type: string additionalProperties: type: - string - number - boolean - type: array items: type: string description: The input as it runs, with the defaults filled in. output: type: array items: type: object properties: type: type: string enum: - image - video - audio - 3d - text description: 'What the file is: `image`, `video`, `audio`, `3d` or `text`.' url: type: string format: uri description: >- A signed link to the file. Download what you keep: links expire after 24 hours, and reading the generation again signs fresh ones. expires_at: type: string format: date-time pattern: >- ^(?:(?:\d\d[2468][048]|\d\d[13579][26]|\d\d0[48]|[02468][048]00|[13579][26]00)-02-29|\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\d|30)|(?:02)-(?:0[1-9]|1\d|2[0-8])))T(?:(?:[01]\d|2[0-3]):[0-5]\d:[0-5]\d(?:\.\d+)?(?:Z))$ description: When `url` stops working, 24 hours after it was signed. content_type: type: string description: The file's media type, such as `image/jpeg` or `video/mp4`. width: anyOf: - type: integer exclusiveMinimum: 0 maximum: 9007199254740991 - type: 'null' description: Width in pixels; null for a sound. height: anyOf: - type: integer exclusiveMinimum: 0 maximum: 9007199254740991 - type: 'null' description: Height in pixels; null for a sound. poster: description: >- For a video: a JPEG of a frame from its middle, about 720 pixels on the long side. Absent when none was made. type: object properties: url: type: string format: uri description: >- A signed link to the poster, which expires with the video's link. expires_at: type: string format: date-time pattern: >- ^(?:(?:\d\d[2468][048]|\d\d[13579][26]|\d\d0[48]|[02468][048]00|[13579][26]00)-02-29|\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\d|30)|(?:02)-(?:0[1-9]|1\d|2[0-8])))T(?:(?:[01]\d|2[0-3]):[0-5]\d:[0-5]\d(?:\.\d+)?(?:Z))$ width: type: integer exclusiveMinimum: 0 maximum: 9007199254740991 height: type: integer exclusiveMinimum: 0 maximum: 9007199254740991 required: - url - expires_at - width - height additionalProperties: false required: - type - url - expires_at - content_type - width - height additionalProperties: false preview: description: >- While a preset that makes a still first is running: that still, once it exists, before the video it becomes. Absent for every other run, and for a run whose video also reads words or a photo you sent, such as a line to say or a photo the clip starts from: that still comes with the video. type: object properties: url: type: string format: uri description: >- A signed link to the still, which expires after 24 hours like an output's. expires_at: type: string format: date-time pattern: >- ^(?:(?:\d\d[2468][048]|\d\d[13579][26]|\d\d0[48]|[02468][048]00|[13579][26]00)-02-29|\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\d|30)|(?:02)-(?:0[1-9]|1\d|2[0-8])))T(?:(?:[01]\d|2[0-3]):[0-5]\d:[0-5]\d(?:\.\d+)?(?:Z))$ width: anyOf: - type: integer exclusiveMinimum: 0 maximum: 9007199254740991 - type: 'null' height: anyOf: - type: integer exclusiveMinimum: 0 maximum: 9007199254740991 - type: 'null' required: - url - expires_at - width - height additionalProperties: false error: anyOf: - type: object properties: message: type: string required: - message additionalProperties: false - type: 'null' description: >- Why a `failed` run failed, such as a refused prompt or a provider error; null otherwise. A failed run isn't charged. usage: type: object properties: cost_usd: description: >- What the run cost, as an exact decimal string in US dollars; null until it's charged. type: - string - 'null' required: - cost_usd additionalProperties: false description: What the run cost your workspace. source: anyOf: - type: string enum: - studio - api - mcp - type: 'null' description: 'Where it was started: `api`, `mcp` or `studio`.' batch_id: description: The batch it belongs to, `bat_...`; null if none. type: - string - 'null' created_at: type: string format: date-time pattern: >- ^(?:(?:\d\d[2468][048]|\d\d[13579][26]|\d\d0[48]|[02468][048]00|[13579][26]00)-02-29|\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\d|30)|(?:02)-(?:0[1-9]|1\d|2[0-8])))T(?:(?:[01]\d|2[0-3]):[0-5]\d:[0-5]\d(?:\.\d+)?(?:Z))$ description: When it was created. started_at: anyOf: - type: string format: date-time pattern: >- ^(?:(?:\d\d[2468][048]|\d\d[13579][26]|\d\d0[48]|[02468][048]00|[13579][26]00)-02-29|\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\d|30)|(?:02)-(?:0[1-9]|1\d|2[0-8])))T(?:(?:[01]\d|2[0-3]):[0-5]\d:[0-5]\d(?:\.\d+)?(?:Z))$ - type: 'null' description: When it started running; null while queued. completed_at: anyOf: - type: string format: date-time pattern: >- ^(?:(?:\d\d[2468][048]|\d\d[13579][26]|\d\d0[48]|[02468][048]00|[13579][26]00)-02-29|\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\d|30)|(?:02)-(?:0[1-9]|1\d|2[0-8])))T(?:(?:[01]\d|2[0-3]):[0-5]\d:[0-5]\d(?:\.\d+)?(?:Z))$ - type: 'null' description: When it reached a final status; null before. required: - id - object - model - modality - status - provider - revision - input - output - error - usage - source - batch_id - created_at - started_at - completed_at additionalProperties: false description: >- One run of a model or preset, with its status, its outputs and what it cost. responses: ConflictingCredentials: description: '`conflicting_credentials`' headers: X-Request-Id: $ref: '#/components/headers/X-Request-Id' RateLimit-Limit: $ref: '#/components/headers/RateLimit-Limit' RateLimit-Remaining: $ref: '#/components/headers/RateLimit-Remaining' RateLimit-Reset: $ref: '#/components/headers/RateLimit-Reset' content: application/json: schema: $ref: '#/components/schemas/Error' examples: conflicting_credentials: value: error: type: invalid_request_error code: conflicting_credentials message: Send one API key. param: null doc_url: null request_id: req_8kQ2vX9mR4tL6nB1cW3yZ5aD AuthenticationRequired: description: '`authentication_required`' headers: X-Request-Id: $ref: '#/components/headers/X-Request-Id' RateLimit-Limit: $ref: '#/components/headers/RateLimit-Limit' RateLimit-Remaining: $ref: '#/components/headers/RateLimit-Remaining' RateLimit-Reset: $ref: '#/components/headers/RateLimit-Reset' content: application/json: schema: $ref: '#/components/schemas/Error' examples: authentication_required: value: error: type: authentication_error code: authentication_required message: Authentication is required. param: null doc_url: null request_id: req_8kQ2vX9mR4tL6nB1cW3yZ5aD PermissionDenied: description: '`permission_denied`' headers: X-Request-Id: $ref: '#/components/headers/X-Request-Id' RateLimit-Limit: $ref: '#/components/headers/RateLimit-Limit' RateLimit-Remaining: $ref: '#/components/headers/RateLimit-Remaining' RateLimit-Reset: $ref: '#/components/headers/RateLimit-Reset' content: application/json: schema: $ref: '#/components/schemas/Error' examples: permission_denied: value: error: type: permission_error code: permission_denied message: Permission denied. param: null doc_url: null request_id: req_8kQ2vX9mR4tL6nB1cW3yZ5aD RateLimitExceeded: description: '`rate_limit_exceeded`' headers: X-Request-Id: $ref: '#/components/headers/X-Request-Id' RateLimit-Limit: $ref: '#/components/headers/RateLimit-Limit' RateLimit-Remaining: $ref: '#/components/headers/RateLimit-Remaining' RateLimit-Reset: $ref: '#/components/headers/RateLimit-Reset' Retry-After: $ref: '#/components/headers/Retry-After' content: application/json: schema: $ref: '#/components/schemas/Error' examples: rate_limit_exceeded: value: error: type: rate_limit_error code: rate_limit_exceeded message: Too Many Requests param: null doc_url: null request_id: req_8kQ2vX9mR4tL6nB1cW3yZ5aD securitySchemes: ApiKey: type: apiKey in: header name: x-api-key description: >- Your workspace API key, `leap_...`. Create one at https://app.tryleap.ai/go/api, and keep it on your server. Bearer: type: http scheme: bearer description: >- The same API key as `Authorization: Bearer leap_...`, the way most HTTP clients and coding agents send one. Send one header or the other; two different keys are a `400`. ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.