Overshoot Chat API

openapi: 3.2.0
info:
  title: Overshoot Chat API
  version: '1.0'
  description: 'Operations tagged Chat across 2 of this provider''s published API definitions: overshoot-inference-service.json, overshoot-openapi.yaml. Each path carries the servers of the definition it was published in.'
servers:
- url: https://api.overshoot.ai/v1beta
tags:
- name: Chat
paths:
  /chat/completions:
    post:
      summary: Chat Completions
      operationId: chat_completions_chat_completions_post
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ChatCompletionRequest'
        required: true
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      security:
      - API Key: []
      tags:
      - Chat
components:
  schemas:
    ValidationError:
      properties:
        loc:
          items:
            anyOf:
            - type: string
            - type: integer
          type: array
          title: Location
        msg:
          type: string
          title: Message
        type:
          type: string
          title: Error Type
        input:
          title: Input
        ctx:
          type: object
          title: Context
      type: object
      required:
      - loc
      - msg
      - type
      title: ValidationError
    ChatCompletionRequest:
      properties:
        model:
          type: string
          title: Model
        messages:
          items:
            additionalProperties: true
            type: object
          type: array
          title: Messages
        response_format:
          anyOf:
          - additionalProperties: true
            type: object
          - type: 'null'
          title: Response Format
        max_completion_tokens:
          anyOf:
          - type: integer
          - type: 'null'
          title: Max Completion Tokens
        max_tokens:
          anyOf:
          - type: integer
          - type: 'null'
          title: Max Tokens
        thread_id:
          anyOf:
          - type: string
          - type: 'null'
          title: Thread Id
        tools:
          anyOf:
          - items:
              additionalProperties: true
              type: object
            type: array
          - type: 'null'
          title: Tools
        tool_choice:
          anyOf:
          - {}
          - type: 'null'
          title: Tool Choice
        parallel_tool_calls:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Parallel Tool Calls
      additionalProperties: true
      type: object
      required:
      - model
      - messages
      title: ChatCompletionRequest
      description: OpenAI-compatible chat completions request. Permissive — unknown fields are accepted and ignored.
    HTTPValidationError:
      properties:
        detail:
          items:
            $ref: '#/components/schemas/ValidationError'
          type: array
          title: Detail
      type: object
      title: HTTPValidationError
    TextPart:
      type: object
      properties:
        type:
          type: string
          enum:
          - text
        text:
          type: string
      required:
      - type
      - text
    ChatError:
      type: object
      description: 'Error envelope used by `/chat/completions`. The inner `error.code` identifies the

        specific failure (see the Errors guide for the full list of codes such as

        `stream_not_found`, `frame_evicted`, `upstream_http_<status>`, etc.).

        '
      properties:
        detail:
          type: object
          properties:
            error:
              type: object
              properties:
                message:
                  type: string
                  example: 'Stream not found: <stream_id>'
                type:
                  type: string
                  enum:
                  - stream_error
                  - validation_error
                  - provider_error
                  - upstream_error
                  - billing_error
                  - rate_limit_error
                  - internal_error
                  example: stream_error
                code:
                  type: string
                  description: 'Specific failure code. Known values include:

                    `stream_url_invalid`, `query_param_invalid`, `stream_not_found`,

                    `stream_unauthorized`, `segment_empty`, `segment_invalid`,

                    `frame_evicted`, `frame_not_yet_produced`, `model_unavailable`,

                    `model_video_unsupported`, `provider_safety_block`, `billing_denied`,

                    `upstream_http_<status>`, `upstream_timeout`,

                    `upstream_request_failed`.

                    '
                  example: stream_not_found
                upstream:
                  $ref: '#/components/schemas/UpstreamError'
              required:
              - message
              - type
              - code
          required:
          - error
    ContentPart:
      oneOf:
      - $ref: '#/components/schemas/TextPart'
      - $ref: '#/components/schemas/ImageUrlPart'
      - $ref: '#/components/schemas/VideoUrlPart'
    ChatCompletionRequest_2:
      type: object
      description: 'OpenAI-compatible. Permissive — unknown fields are accepted for SDK compatibility.

        To reference a stream''s frames, include `video_url` or `image_url` content parts

        whose URL uses the `ovs://streams/{stream_id}?...` reference scheme.

        '
      additionalProperties: true
      properties:
        model:
          type: string
          description: Model identifier from `GET /models`. Must be `ready` at request time.
          example: google/gemma-4-26B-A4B-it
        messages:
          type: array
          items:
            $ref: '#/components/schemas/ChatMessage'
        max_completion_tokens:
          type:
          - integer
          - 'null'
          description: Optional output-token cap. OpenAI's preferred name.
        max_tokens:
          type:
          - integer
          - 'null'
          description: Legacy alias for `max_completion_tokens`.
        response_format:
          type: object
          additionalProperties: true
          description: Used when supported by the selected model/provider.
        stream:
          type: boolean
          default: false
          description: When `true`, the response is a server-sent event stream.
        stream_options:
          type: object
          description: 'Only meaningful when `stream: true`.'
          properties:
            include_usage:
              type: boolean
              description: When `true`, the stream may include a final usage chunk.
        tools:
          type: array
          items:
            type: object
            additionalProperties: true
          description: OpenAI-style tool definitions.
        tool_choice:
          oneOf:
          - type: string
          - type: object
            additionalProperties: true
          description: OpenAI-style tool choice.
        parallel_tool_calls:
          type: boolean
          description: OpenAI-style parallel tool-call setting.
        thread_id:
          type:
          - string
          - 'null'
          description: 'Optional key for prompt-cache reuse across related requests in the same user

            conversation and model. See the Prompt cache guide.

            '
      required:
      - model
      - messages
    ChatCompletionResponse:
      type: object
      properties:
        id:
          type: string
        object:
          type: string
          default: chat.completion
        created:
          type: integer
        model:
          type: string
        choices:
          type: array
          items:
            $ref: '#/components/schemas/ChatCompletionChoice'
        usage:
          $ref: '#/components/schemas/ChatCompletionUsage'
        overshoot:
          $ref: '#/components/schemas/OvershootMetadata'
      required:
      - id
      - object
      - created
      - model
      - choices
    ChatCompletionUsage:
      type: object
      properties:
        prompt_tokens:
          type: integer
          description: Tokens in the request — text plus visual tokens from any frames or segments.
        completion_tokens:
          type: integer
        total_tokens:
          type: integer
    VideoUrlPart:
      type: object
      properties:
        type:
          type: string
          enum:
          - video_url
        video_url:
          type: object
          properties:
            url:
              type: string
              description: 'HTTPS video URL, `data:` URL, or Overshoot stream segment reference like

                `ovs://streams/{stream_id}?start_offset_ms=-5000`. Required query:

                exactly one `start_*` anchor. Optional end anchor (defaults to live edge),

                optional `max_fps` (default `1.0`).

                '
          required:
          - url
      required:
      - type
      - video_url
    ChatCompletionStreamChunk:
      type: object
      description: 'A single `data:` payload in an SSE response. The stream is terminated by

        `data: [DONE]`. The final chunk (when `stream_options.include_usage: true`)

        carries `usage` and `overshoot.cache`.

        '
      properties:
        choices:
          type: array
          items:
            type: object
            properties:
              delta:
                type: object
                properties:
                  role:
                    type: string
                  content:
                    type: string
                  tool_calls:
                    type: array
                    items:
                      type: object
                      additionalProperties: true
              finish_reason:
                type:
                - string
                - 'null'
        usage:
          allOf:
          - $ref: '#/components/schemas/ChatCompletionUsage'
        overshoot:
          $ref: '#/components/schemas/OvershootMetadata'
    ValidationError_2:
      type: object
      description: Validation failure shape used by chat completions and billing.
      properties:
        error:
          type: string
          example: validation_error
        message:
          type: string
          example: Request validation failed
        details:
          type: array
          items:
            type: object
            properties:
              loc:
                type: array
                items:
                  type: string
              msg:
                type: string
              type:
                type: string
    ImageUrlPart:
      type: object
      properties:
        type:
          type: string
          enum:
          - image_url
        image_url:
          type: object
          properties:
            url:
              type: string
              description: 'Either an HTTPS image URL, a `data:` URL, or an Overshoot stream frame

                reference like `ovs://streams/{stream_id}?frame_index=-1`. The `ovs://`

                URI is a reference identifier the server parses, not a fetchable URL.

                Required query: exactly one of `frame_index`, `timestamp_ms`, or

                `offset_ms`.

                '
          required:
          - url
      required:
      - type
      - image_url
    OvershootMetadata:
      type: object
      description: Overshoot-specific response metadata. Observability only.
      properties:
        cache:
          type: object
          properties:
            thread_id:
              type:
              - string
              - 'null'
              description: The `thread_id` you supplied, or `null`.
            cache_hit:
              type: boolean
              description: '`true` when cached prompt tokens were reported.'
            cached_input_tokens:
              type: integer
              description: Prompt tokens served from prefix cache.
    Error:
      type: object
      description: Standard error body used by stream-lifecycle and billing endpoints.
      properties:
        detail:
          type: string
      required:
      - detail
    UpstreamError:
      type:
      - object
      - 'null'
      description: Present on `upstream_*` codes. Preserves the provider status and a bounded response body when available.
      properties:
        provider:
          type: string
          example: google
        status:
          type: integer
          example: 400
        body:
          type: object
          additionalProperties: true
          description: Bounded provider response body.
        rate_limits:
          type:
          - object
          - 'null'
          additionalProperties: true
    ChatCompletionChoice:
      type: object
      properties:
        index:
          type: integer
        message:
          type: object
          properties:
            role:
              type: string
              example: assistant
            content:
              type:
              - string
              - 'null'
            tool_calls:
              type: array
              items:
                type: object
                additionalProperties: true
              description: OpenAI-style tool calls. Present when the model emits any.
          required:
          - role
        finish_reason:
          type:
          - string
          - 'null'
          enum:
          - stop
          - length
          - tool_calls
          - content_filter
      required:
      - index
      - message
    ChatMessage:
      type: object
      properties:
        role:
          type: string
          enum:
          - system
          - user
          - assistant
          - tool
        content:
          oneOf:
          - type: string
          - type: array
            items:
              $ref: '#/components/schemas/ContentPart'
      required:
      - role
      - content
  headers:
    RateLimitLimit:
      description: Current per-user request-per-second limit.
      schema:
        type: integer
    RateLimitReset:
      description: Epoch time when the current second window resets.
      schema:
        type: integer
    RetryAfter:
      description: Seconds to wait before retrying. Present on 429; currently `1`.
      schema:
        type: integer
    RegionResponseHeader:
      description: The region that served this request.
      schema:
        type: string
        enum:
        - us-west1
        - us-central1
    RateLimitRemaining:
      description: Remaining requests in the current second.
      schema:
        type: integer
  parameters:
    RegionHeader:
      name: X-Overshoot-Region
      in: header
      required: false
      schema:
        type: string
        enum:
        - us-west1
        - us-central1
      description: 'Optional hint to route the request to the region that owns the stream. If the

        request reaches the wrong region the API returns `409` with a `region_error` body.

        '
  securitySchemes:
    API_Key:
      type: http
      description: Bearer <api_key>
      scheme: bearer
    bearerAuth:
      type: http
      scheme: bearer
      bearerFormat: API key (e.g. `ovs_...`)
      description: "Every public HTTP request requires `Authorization: Bearer <api_key>`, except\n`GET /models` and the public `/billing/pricing` endpoints.\n\n- `401` means the key is missing, unknown, or revoked.\n- `403` means the key is valid but cannot access the requested resource.\n- The publish token returned by `POST /streams` is only for publishing media to\n  LiveKit. It does not replace the API key for HTTP calls.\n"
x-refined-from:
- overshoot-inference-service.json
- overshoot-openapi.yaml