Compoid Completions API

openapi: 3.2.0
info:
  title: Compoid Com Completions API
  version: 0.1.0
  x-refined-note:
  - x-original-title differs across the merged source definitions and was not carried
  description: 'Operations tagged Completions across 2 of this provider''s published API definitions: compoid-com-openapi.json, compoid-com-openapi.yml. Each path carries the servers of the definition it was published in.'
servers:
- url: https://api.compoid.com
  description: Compoid AI inference host (paths carry the /v1 prefix)
tags:
- name: Completions
paths:
  /v1/completions:
    post:
      summary: Create Completion
      operationId: create_completion_v1_completions_post
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/CompletionRequest'
        required: true
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
            text/event-stream: {}
        '400':
          description: Bad Request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '404':
          description: Not Found
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '500':
          description: Internal Server Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      tags:
      - Completions
components:
  schemas:
    StructuredOutputsParams:
      properties:
        json:
          anyOf:
          - type: string
          - additionalProperties: true
            type: object
          - type: 'null'
          title: Json
        regex:
          anyOf:
          - type: string
          - type: 'null'
          title: Regex
        choice:
          anyOf:
          - items:
              type: string
            type: array
          - type: 'null'
          title: Choice
        grammar:
          anyOf:
          - type: string
          - type: 'null'
          title: Grammar
        json_object:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Json Object
        disable_any_whitespace:
          type: boolean
          title: Disable Any Whitespace
          default: false
        disable_additional_properties:
          type: boolean
          title: Disable Additional Properties
          default: false
        whitespace_pattern:
          anyOf:
          - type: string
          - type: 'null'
          title: Whitespace Pattern
        structural_tag:
          anyOf:
          - type: string
          - type: 'null'
          title: Structural Tag
        _backend:
          anyOf:
          - type: string
          - type: 'null'
          title: Backend
        _backend_was_auto:
          type: boolean
          title: Backend Was Auto
          default: false
      type: object
      title: StructuredOutputsParams
    LegacyStructuralTagResponseFormat:
      properties:
        type:
          type: string
          const: structural_tag
          title: Type
        structures:
          items:
            $ref: '#/components/schemas/LegacyStructuralTag'
          type: array
          title: Structures
        triggers:
          items:
            type: string
          type: array
          title: Triggers
      additionalProperties: true
      type: object
      required:
      - type
      - structures
      - triggers
      title: LegacyStructuralTagResponseFormat
    StreamOptions:
      properties:
        include_usage:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Include Usage
          default: false
        continuous_usage_stats:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Continuous Usage Stats
          default: false
      additionalProperties: true
      type: object
      title: StreamOptions
    StructuralTagResponseFormat:
      properties:
        type:
          type: string
          const: structural_tag
          title: Type
        format:
          title: Format
      additionalProperties: true
      type: object
      required:
      - type
      - format
      title: StructuralTagResponseFormat
    CompletionRequest:
      properties:
        model:
          anyOf:
          - type: string
          - type: 'null'
          title: Model
        prompt:
          anyOf:
          - items:
              type: integer
              minimum: 0.0
            type: array
          - items:
              items:
                type: integer
                minimum: 0.0
              type: array
            type: array
          - type: string
          - items:
              type: string
            type: array
          - type: 'null'
          title: Prompt
        echo:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Echo
          default: false
        frequency_penalty:
          anyOf:
          - type: number
          - type: 'null'
          title: Frequency Penalty
        logit_bias:
          anyOf:
          - additionalProperties:
              type: number
            type: object
          - type: 'null'
          title: Logit Bias
        logprobs:
          anyOf:
          - type: integer
          - type: 'null'
          title: Logprobs
        max_tokens:
          anyOf:
          - type: integer
          - type: 'null'
          title: Max Tokens
          default: 16
        n:
          type: integer
          title: N
          default: 1
        presence_penalty:
          anyOf:
          - type: number
          - type: 'null'
          title: Presence Penalty
        seed:
          anyOf:
          - type: integer
            maximum: 9.223372036854776e+18
            minimum: -9.223372036854776e+18
          - type: 'null'
          title: Seed
        stop:
          anyOf:
          - type: string
          - items:
              type: string
            type: array
            maxItems: 4
          - type: 'null'
          title: Stop
          default: []
        stream:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Stream
          default: false
        stream_options:
          anyOf:
          - $ref: '#/components/schemas/StreamOptions'
          - type: 'null'
        suffix:
          anyOf:
          - type: string
          - type: 'null'
          title: Suffix
        temperature:
          anyOf:
          - type: number
          - type: 'null'
          title: Temperature
        top_p:
          anyOf:
          - type: number
          - type: 'null'
          title: Top P
        user:
          anyOf:
          - type: string
          - type: 'null'
          title: User
        use_beam_search:
          type: boolean
          title: Use Beam Search
          default: false
        top_k:
          anyOf:
          - type: integer
          - type: 'null'
          title: Top K
        min_p:
          anyOf:
          - type: number
          - type: 'null'
          title: Min P
        repetition_penalty:
          anyOf:
          - type: number
          - type: 'null'
          title: Repetition Penalty
        watermarking:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Watermarking
        length_penalty:
          type: number
          title: Length Penalty
          default: 1.0
        stop_token_ids:
          anyOf:
          - items:
              type: integer
            type: array
          - type: 'null'
          title: Stop Token Ids
          default: []
        include_stop_str_in_output:
          type: boolean
          title: Include Stop Str In Output
          default: false
        ignore_eos:
          type: boolean
          title: Ignore Eos
          default: false
        min_tokens:
          type: integer
          title: Min Tokens
          default: 0
        skip_special_tokens:
          type: boolean
          title: Skip Special Tokens
          default: true
        spaces_between_special_tokens:
          type: boolean
          title: Spaces Between Special Tokens
          default: true
        truncate_prompt_tokens:
          anyOf:
          - type: integer
            maximum: 9.223372036854776e+18
            minimum: -1.0
          - type: 'null'
          title: Truncate Prompt Tokens
        truncation_side:
          anyOf:
          - type: string
            enum:
            - left
            - right
          - type: 'null'
          title: Truncation Side
          description: Which side to truncate from when truncate_prompt_tokens is active. 'right' keeps the first N tokens. 'left' keeps the last N tokens.
        allowed_token_ids:
          anyOf:
          - items:
              type: integer
            type: array
          - type: 'null'
          title: Allowed Token Ids
        prompt_logprobs:
          anyOf:
          - type: integer
          - type: 'null'
          title: Prompt Logprobs
        logprob_token_ids:
          anyOf:
          - items:
              type: integer
            type: array
          - type: 'null'
          title: Logprob Token Ids
          description: Specific vocab token IDs to return logprobs for at each generated position, in addition to the sampled token. More efficient than requesting the full vocab when only a small fixed label set is needed (e.g. multilabel scoring where each label corresponds to a known vocab id). When set, this explicit token selection takes precedence over the natural top-k selected by `logprobs`. Requires `logprobs` to be set.
        bad_words:
          items:
            type: string
          type: array
          title: Bad Words
        prompt_embeds:
          anyOf:
          - type: string
            contentMediaType: application/octet-stream
          - items:
              type: string
              contentMediaType: application/octet-stream
            type: array
          - type: 'null'
          title: Prompt Embeds
        add_special_tokens:
          type: boolean
          title: Add Special Tokens
          description: If true (the default), special tokens (e.g. BOS) will be added to the prompt.
          default: true
        response_format:
          anyOf:
          - $ref: '#/components/schemas/ResponseFormat'
          - $ref: '#/components/schemas/StructuralTagResponseFormat'
          - $ref: '#/components/schemas/LegacyStructuralTagResponseFormat'
          - type: 'null'
          title: Response Format
          description: 'Similar to chat completion, this parameter specifies the format of output. Only {''type'': ''json_object''}, {''type'': ''json_schema''}, {''type'': ''structural_tag''}, or {''type'': ''text'' } is supported.'
        structured_outputs:
          anyOf:
          - $ref: '#/components/schemas/StructuredOutputsParams'
          - type: 'null'
          description: Additional kwargs for structured outputs
        priority:
          type: integer
          maximum: 9.223372036854776e+18
          minimum: -9.223372036854776e+18
          title: Priority
          description: 'The priority of the request (lower means earlier handling; default: 0). Any priority other than 0 will raise an error if the served model does not use priority scheduling.'
          default: 0
        request_id:
          type: string
          title: Request Id
          description: The request_id related to this request. If the caller does not set it, a random_uuid will be generated. This id is used through out the inference process and return in response.
        session_id:
          anyOf:
          - type: string
          - type: 'null'
          title: Session Id
          description: Stable session identity shared by related requests. Unlike request_id, this value is expected to remain stable across multiple requests in the same conversation or agent session.
        return_tokens_as_token_ids:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Return Tokens As Token Ids
          description: If specified with 'logprobs', tokens are represented  as strings of the form 'token_id:{token_id}' so that tokens that are not JSON-encodable can be identified.
        return_token_ids:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Return Token Ids
          description: If specified, the result will include token IDs alongside the generated text. In streaming mode, prompt_token_ids is included only in the first chunk, and token_ids contains the delta tokens for each chunk. This is useful for debugging or when you need to map generated text back to input tokens.
        routed_experts_prompt_start:
          type: integer
          minimum: 0.0
          title: Routed Experts Prompt Start
          description: Skip the first N prompt tokens from returned routed-expert data.
          default: 0
        return_token_offsets:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Return Token Offsets
          description: If true, return char-level (start, end) offsets for each token relative to the tokenized source string in the `token_offsets` field of the rendered response. Only supported on the `/v1/completions/render` and `/v1/chat/completions/render` endpoints; ignored on regular generation endpoints. Honored only for Fast (Rust-backed) tokenizers; otherwise `token_offsets` is null. For chat requests, offsets are relative to the templated prompt string (after applying the chat template). Multimodal inputs and pre-tokenized inputs always yield null.
          default: false
        mm_payload:
          type: string
          enum:
          - tensors
          - none
          title: Mm Payload
          description: What the render response's `features` carry for multimodal items. 'tensors' serializes the processed tensors into `kwargs_data` and `mm_metadata`. 'none' sets both to null for callers that need only the token layout and item hashes, such as cache-aware routers. Do not send a 'none' response to `/inference/v1/generate` which reads a null `kwargs_data` as every item being cached. Only supported on the render endpoints. Ignored on regular generation endpoints.
          default: tensors
        return_mm_kwargs:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Return Mm Kwargs
          description: 'Deprecated alias: false is the same as `mm_payload=''none''`. Ignored when `mm_payload` is set.'
          deprecated: true
        cache_salt:
          anyOf:
          - type: string
            maxLength: 1024
            minLength: 1
          - type: 'null'
          title: Cache Salt
          description: If specified, the prefix cache will be salted with the provided string to prevent an attacker to guess prompts in multi-user environments. The salt should be random, protected from access by 3rd parties, and long enough to be unpredictable (e.g., 43 characters base64-encoded, corresponding to 256 bit).
        kv_transfer_params:
          anyOf:
          - additionalProperties: true
            type: object
          - type: 'null'
          title: Kv Transfer Params
          description: KVTransfer parameters used for disaggregated serving.
        ec_transfer_params:
          anyOf:
          - additionalProperties: true
            type: object
          - type: 'null'
          title: Ec Transfer Params
          description: ECTransfer parameters used for encoder-cache disaggregated serving.
        vllm_xargs:
          anyOf:
          - additionalProperties:
              anyOf:
              - type: string
              - type: integer
              - type: number
              - items:
                  anyOf:
                  - type: string
                  - type: integer
                  - type: number
                type: array
            type: object
          - type: 'null'
          title: Vllm Xargs
          description: Additional request parameters with (list of) string or numeric values, used by custom extensions.
        repetition_detection:
          anyOf:
          - $ref: '#/components/schemas/RepetitionDetectionParams'
          - type: 'null'
          description: Parameters for detecting repetitive N-gram patterns in output tokens. If such repetition is detected, generation will be ended early. LLMs can sometimes generate repetitive, unhelpful token patterns, stopping only when they hit the maximum output length (e.g. 'abcdabcdabcd...' or '\emoji \emoji \emoji ...'). This feature can detect such behavior and terminate early, saving time and tokens.
        thinking_token_budget:
          anyOf:
          - type: integer
          - type: 'null'
          title: Thinking Token Budget
          description: Maximum number of tokens allowed for thinking operations (reasoning models). Non-negative integer sets the limit; -1 means unlimited (treated as unset).
        stream_interval:
          anyOf:
          - type: integer
            minimum: 1.0
          - type: 'null'
          title: Stream Interval
          description: Number of tokens to batch into each streamed chunk. Raises the server's `--stream-interval` for this request. Values below the server setting are clamped up to it. The first and last chunks are always sent immediately. Ignored for non-streaming requests.
      additionalProperties: true
      type: object
      title: CompletionRequest
    ErrorInfo:
      properties:
        message:
          type: string
          title: Message
        type:
          type: string
          title: Type
        param:
          anyOf:
          - type: string
          - type: 'null'
          title: Param
        code:
          type: integer
          title: Code
      additionalProperties: true
      type: object
      required:
      - message
      - type
      - code
      title: ErrorInfo
    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
    ErrorResponse:
      properties:
        error:
          $ref: '#/components/schemas/ErrorInfo'
      additionalProperties: true
      type: object
      required:
      - error
      title: ErrorResponse
    RepetitionDetectionParams:
      properties:
        max_pattern_size:
          type: integer
          title: Max Pattern Size
          default: 0
        min_pattern_size:
          type: integer
          title: Min Pattern Size
          default: 0
        min_count:
          type: integer
          title: Min Count
          default: 0
      type: object
      title: RepetitionDetectionParams
      description: Parameters for detecting repetitive N-gram patterns in output tokens.
    HTTPValidationError:
      properties:
        detail:
          items:
            $ref: '#/components/schemas/ValidationError'
          type: array
          title: Detail
      type: object
      title: HTTPValidationError
    ResponseFormat:
      properties:
        type:
          type: string
          enum:
          - text
          - json_object
          - json_schema
          title: Type
        json_schema:
          anyOf:
          - $ref: '#/components/schemas/JsonSchemaResponseFormat'
          - type: 'null'
      additionalProperties: true
      type: object
      required:
      - type
      title: ResponseFormat
    JsonSchemaResponseFormat:
      properties:
        name:
          type: string
          title: Name
        description:
          anyOf:
          - type: string
          - type: 'null'
          title: Description
        schema:
          anyOf:
          - additionalProperties: true
            type: object
          - type: 'null'
          title: Schema
        strict:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Strict
      additionalProperties: true
      type: object
      required:
      - name
      title: JsonSchemaResponseFormat
    LegacyStructuralTag:
      properties:
        begin:
          type: string
          title: Begin
        schema:
          anyOf:
          - additionalProperties: true
            type: object
          - type: 'null'
          title: Schema
        end:
          type: string
          title: End
      additionalProperties: true
      type: object
      required:
      - begin
      - end
      title: LegacyStructuralTag
x-refined-from:
- compoid-com-openapi.json
- compoid-com-openapi.yml