> ## Documentation Index
> Fetch the complete documentation index at: https://docs.lavendly.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Chat and images

> OpenAI-compatible. Text models are free (daily allowance; 429 free_ops_cap). Image models charge credits.



## OpenAPI

````yaml https://lavendly.ai/openapi.json post /v1/chat/completions
openapi: 3.1.0
info:
  title: Lavendly API
  version: 1.1.0
  description: >-
    The Lavendly v1 API: build a video from shots, price it, generate the
    scenes, render the film, and publish it. Authenticate with a Bearer API key
    (lv_...) from Settings > API. Rate limits are per account per minute: 20
    writes, 60 render polls, 120 other reads; a 429 carries Retry-After and
    retry_after_ms. Errors are { error: { code, message } }; 5xx adds a ref. The
    same API is an MCP server at https://mcp.lavendly.ai/mcp and in the
    @lavendly/mcp npm package.
  contact:
    name: Lavendly
    email: hello@lavendly.ai
servers:
  - url: https://lavendly.ai/api
    description: Production
security:
  - bearerAuth: []
tags:
  - name: Create to publish
    description: The main loop, in order.
  - name: Workflows
  - name: Edit
  - name: Audio
  - name: Assets
  - name: Renders
  - name: Account
  - name: Single clips
paths:
  /v1/chat/completions:
    post:
      tags:
        - Single clips
      summary: Chat and images
      description: >-
        OpenAI-compatible. Text models are free (daily allowance; 429
        free_ops_cap). Image models charge credits.
      operationId: createChatCompletion
      parameters:
        - name: Idempotency-Key
          in: header
          required: false
          description: Replays the first response for 24 hours instead of charging twice.
          schema:
            type: string
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required:
                - messages
              properties:
                messages:
                  type: array
                  items:
                    type: object
                    properties:
                      role:
                        type: string
                      content:
                        type: string
                model:
                  type: string
                  description: Default openai/gpt-4o-mini
      responses:
        '200':
          description: Completion
          content:
            application/json:
              schema:
                type: object
                properties:
                  id:
                    type: string
                  choices:
                    type: array
                  usage:
                    type: object
        '400':
          $ref: '#/components/responses/E400'
        '401':
          $ref: '#/components/responses/E401'
        '402':
          $ref: '#/components/responses/E402'
        '429':
          $ref: '#/components/responses/E429'
components:
  responses:
    E400:
      description: Bad request (invalid_args, invalid_edits, invalid_split, video_too_long)
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
          example:
            error:
              code: invalid_args
              message: ...
    E401:
      description: Missing or revoked key
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
          example:
            error:
              code: unauthenticated
              message: ...
    E402:
      description: >-
        insufficient_credits, monthly_cost_cap, monthly_budget_exceeded,
        video_over_budget, seats_exceeded
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
          example:
            error:
              code: insufficient_credits
              message: ...
    E429:
      description: >-
        rate_limited (per minute; see Retry-After), publish_limit (monthly),
        free_ops_cap, render_busy
      headers:
        Retry-After:
          schema:
            type: integer
          description: Seconds to wait
        X-Lavendly-RateLimit-Limit:
          schema:
            type: integer
        X-Lavendly-RateLimit-Remaining:
          schema:
            type: integer
        X-Lavendly-RateLimit-Reset:
          schema:
            type: integer
          description: Unix seconds
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
          example:
            error:
              code: rate_limited
              message: Rate limit exceeded for mutation requests. Retry in ~12s.
              retry_after_ms: 11480
              limit: 20
              window_seconds: 60
              class: mutation
  schemas:
    Error:
      type: object
      required:
        - error
      properties:
        error:
          type: object
          required:
            - code
            - message
          properties:
            code:
              type: string
            message:
              type: string
            ref:
              type: string
              description: '5xx only: quote to support'
            retry_after_ms:
              type: integer
              description: 429 rate_limited only
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      description: API key from Settings > API, e.g. lv_...

````