ccapi-ai OpenAI LLM Integration API

openapi: 3.2.0
info:
  title: CCAPI OpenAI LLM Integration API
  description: CCAPI Model Gateway — OpenAI-compatible unified API
  version: 1.0.0
servers:
- url: https://api.ccapi.ai
  description: CCAPI API Gateway
tags:
- name: OpenAI LLM Integration
  description: 'Access OpenAI series LLMs via CCAPI proxy routing.


    ---


    ## Authentication


    Use `Authorization: Bearer `.


    ---


    ## Recommended Endpoints


    - `POST /v1/chat/completions`: Standard OpenAI Chat Completions API

    - `POST /v1/responses`: OpenAI Responses API


    ---


    ## Capabilities


    - Streaming output (SSE) supported

    - Tool calling supported

    - JSON output mode supported

    - Image input and reasoning models supported, depending on the enabled models


    ---


    ## Models


    Common model examples: `gpt-6-sol`, `gpt-5.5`, `gpt-6-astra`, `gpt-5.6-terra`, `gpt-6-luna`.


    Actually available models are determined by the `GET /v1/models` response and backend channel configuration.


    ---


    ## Pricing


    Visit the Pricing page to see full model pricing for this provider.'
paths:
  /v1/chat/completions:
    post:
      deprecated: false
      description: Unified OpenAI-compatible chat endpoint. Select the matching oneOf request schema branch by `model`; provider-specific parameters, examples, and response fields remain available in their corresponding branches.
      operationId: openai-compatible-chat-completion
      parameters:
      - description: CCAPI token, in the format `Bearer sk-...`.
        example: Bearer sk-xxxx
        in: header
        name: Authorization
        required: true
        schema:
          type: string
      requestBody:
        content:
          application/json:
            examples:
              basic_chat:
                summary: Basic conversation
                value:
                  messages:
                  - content: You are a concise assistant.
                    role: system
                  - content: Explain in three sentences why SSE is suitable for LLM streaming output.
                    role: user
                  model: gpt-6-sol
              deepseek-llm-integration_basic_chat:
                summary: Basic chat request
                value:
                  messages:
                  - content: Explain the trade-offs between Bloom filters and hash sets.
                    role: user
                  model: deepseek-v4-flash
                  reasoning_effort: high
                  thinking:
                    type: enabled
              deepseek-llm-integration_streaming_chat:
                description: Stream a response from deepseek-v4-flash for real-time output scenarios.
                summary: Streaming chat request
                value:
                  messages:
                  - content: Design a concurrency control strategy for inventory deduction.
                    role: user
                  model: deepseek-v4-flash
                  stream: true
                  stream_options:
                    include_usage: true
              minimax-llm-integration_basic_chat:
                summary: Basic chat
                value:
                  messages:
                  - content: Compare the trade-offs between message queues and database polling for async tasks.
                    role: user
                  model: minimax-m2.5
              minimax-llm-integration_highspeed_stream:
                summary: Highspeed streaming
                value:
                  messages:
                  - content: You are a concise DevOps assistant.
                    role: system
                  - content: Summarize the key differences between blue-green and canary deployments.
                    role: user
                  model: minimax-m2.5
                  stream: true
              tool_calling:
                summary: Tool calling
                value:
                  messages:
                  - content: Help me query today's weather in Shanghai.
                    role: user
                  model: gpt-5.5
                  tool_choice: auto
                  tools:
                  - function:
                      description: Query weather for a specified city
                      name: get_weather
                      parameters:
                        properties:
                          city:
                            type: string
                        required:
                        - city
                        type: object
                    type: function
            schema:
              oneOf:
              - properties:
                  max_completion_tokens:
                    description: Maximum output token field compatible with Responses/newer models.
                    type: integer
                  max_tokens:
                    description: Maximum number of output tokens.
                    type: integer
                  messages:
                    description: Conversation message list.
                    items:
                      properties:
                        content:
                          description: Message content, supports plain text or a multimodal content array.
                          oneOf:
                          - type: string
                          - items:
                              properties:
                                image_url:
                                  properties:
                                    url:
                                      type: string
                                  type: object
                                text:
                                  type: string
                                type:
                                  enum:
                                  - text
                                  - image_url
                                  type: string
                              type: object
                            type: array
                        role:
                          enum:
                          - system
                          - user
                          - assistant
                          - tool
                          type: string
                        tool_call_id:
                          type: string
                      required:
                      - role
                      - content
                      type: object
                    type: array
                  model:
                    description: Model name, e.g. `gpt-6-sol`, `gpt-5.5`, `gpt-6-astra`.
                    type: string
                  reasoning_effort:
                    description: Reasoning effort, e.g. `low`, `medium`, `high`.
                    type: string
                  response_format:
                    description: Response format, e.g. `{"type":"json_object"}`.
                    properties:
                      type:
                        enum:
                        - text
                        - json_object
                        type: string
                    type: object
                  stream:
                    default: false
                    description: Whether to enable streaming output.
                    type: boolean
                  temperature:
                    description: Sampling temperature.
                    type: number
                  tool_choice:
                    description: Tool calling strategy.
                    oneOf:
                    - enum:
                      - none
                      - auto
                      - required
                      type: string
                    - properties:
                        function:
                          properties:
                            name:
                              type: string
                          required:
                          - name
                          type: object
                        type:
                          enum:
                          - function
                          type: string
                      type: object
                  tools:
                    description: OpenAI function calling format.
                    items:
                      properties:
                        function:
                          properties:
                            description:
                              type: string
                            name:
                              type: string
                            parameters:
                              type: object
                          required:
                          - name
                          type: object
                        type:
                          enum:
                          - function
                          type: string
                      required:
                      - type
                      - function
                      type: object
                    type: array
                  top_p:
                    description: Top-p sampling parameter.
                    type: number
                required:
                - model
                - messages
                title: OpenAI LLM Integration
                type: object
              - properties:
                  max_tokens:
                    description: Maximum number of tokens to generate.
                    type: integer
                  messages:
                    description: List of conversation messages.
                    items:
                      properties:
                        content:
                          description: Message content.
                          type: string
                        role:
                          enum:
                          - system
                          - user
                          - assistant
                          - tool
                          type: string
                        tool_call_id:
                          description: Tool call ID (used when role=tool).
                          type: string
                      required:
                      - role
                      - content
                      type: object
                    type: array
                  model:
                    description: Use Flash for high-throughput workloads and Pro for complex reasoning or agentic coding.
                    enum:
                    - deepseek-v4-flash
                    - deepseek-v4-pro
                    example: deepseek-v4-flash
                    type: string
                  reasoning_effort:
                    description: Reasoning effort used while thinking mode is enabled.
                    enum:
                    - high
                    - max
                    type: string
                  response_format:
                    description: Set type=json_object for JSON output and also request JSON in the prompt.
                    properties:
                      type:
                        enum:
                        - text
                        - json_object
                        type: string
                    type: object
                  stream:
                    default: false
                    description: Enable streaming response (SSE).
                    type: boolean
                  stream_options:
                    description: Only use with stream=true.
                    properties:
                      include_usage:
                        description: Emit total usage in a final chunk before [DONE].
                        type: boolean
                    type: object
                  temperature:
                    description: Sampling temperature, range 0-2.
                    maximum: 2
                    minimum: 0
                    type: number
                  thinking:
                    description: Thinking mode is enabled by default.
                    properties:
                      type:
                        default: enabled
                        enum:
                        - enabled
                        - disabled
                        type: string
                    type: object
                  tool_choice:
                    description: 'Tool selection mode: `none`, `auto`, `required`, or a specific tool object.'
                    oneOf:
                    - enum:
                      - none
                      - auto
                      - required
                      type: string
                    - type: object
                  tools:
                    description: List of tool/function definitions.
                    items:
                      properties:
                        function:
                          properties:
                            description:
                              type: string
                            name:
                              type: string
                            parameters:
                              type: object
                          type: object
                        type:
                          enum:
                          - function
                          type: string
                      type: object
                    type: array
                  top_p:
                    description: Nucleus sampling probability mass.
                    maximum: 1
                    minimum: 0
                    type: number
                required:
                - model
                - messages
                title: DeepSeek LLM Integration
                type: object
              - properties:
                  max_tokens:
                    description: Maximum number of tokens to generate.
                    type: integer
                  messages:
                    description: List of conversation messages.
                    items:
                      properties:
                        content:
                          description: Message content.
                          type: string
                        role:
                          enum:
                          - system
                          - user
                          - assistant
                          - tool
                          type: string
                        tool_call_id:
                          description: Tool call ID (used when role=tool).
                          type: string
                      required:
                      - role
                      - content
                      type: object
                    type: array
                  model:
                    description: Model name, e.g. `minimax-m2.5`.
                    example: minimax-m2.5
                    type: string
                  stream:
                    default: false
                    description: Enable streaming response (SSE).
                    type: boolean
                  temperature:
                    description: Sampling temperature, range 0-2.
                    maximum: 2
                    minimum: 0
                    type: number
                  tool_choice:
                    description: 'Tool selection mode: `none`, `auto`, `required`, or a specific tool object.'
                    oneOf:
                    - enum:
                      - none
                      - auto
                      - required
                      type: string
                    - type: object
                  tools:
                    description: List of tool/function definitions.
                    items:
                      properties:
                        function:
                          properties:
                            description:
                              type: string
                            name:
                              type: string
                            parameters:
                              type: object
                          type: object
                        type:
                          enum:
                          - function
                          type: string
                      type: object
                    type: array
                  top_p:
                    description: Nucleus sampling probability mass.
                    maximum: 1
                    minimum: 0
                    type: number
                required:
                - model
                - messages
                title: MiniMax LLM Integration
                type: object
        required: true
      responses:
        '200':
          content:
            application/json:
              example:
                choices:
                - finish_reason: stop
                  index: 0
                  message:
                    content: SSE allows the server to push content incrementally, reduces time-to-first-byte, and is well-suited for long text generation scenarios.
                    role: assistant
                created: 1741852800
                id: chatcmpl_example
                model: gpt-6-sol
                object: chat.completion
                usage:
                  completion_tokens: 25
                  prompt_tokens: 42
                  total_tokens: 67
              schema:
                oneOf:
                - properties:
                    choices:
                      items:
                        properties:
                          finish_reason:
                            type: string
                          index:
                            type: integer
                          message:
                            properties:
                              content:
                                type: string
                              role:
                                enum:
                                - assistant
                                type: string
                              tool_calls:
                                type: array
                            type: object
                        type: object
                      type: array
                    created:
                      type: integer
                    id:
                      type: string
                    model:
                      type: string
                    object:
                      enum:
                      - chat.completion
                      type: string
                    usage:
                      properties:
                        completion_tokens:
                          type: integer
                        prompt_tokens:
                          type: integer
                        total_tokens:
                          type: integer
                      type: object
                  title: OpenAI LLM Integration
                  type: object
                - properties:
                    choices:
                      items:
                        properties:
                          finish_reason:
                            type: string
                          index:
                            type: integer
                          message:
                            properties:
                              content:
                                type: string
                              reasoning_content:
                                description: Thinking content returned before the final answer.
                                type:
                                - string
                                - 'null'
                              role:
                                type: string
                              tool_calls:
                                items:
                                  properties:
                                    function:
                                      properties:
                                        arguments:
                                          type: string
                                        name:
                                          type: string
                                      type: object
                                    id:
                                      type: string
                                    type:
                                      type: string
                                  type: object
                                type: array
                            type: object
                        type: object
                      type: array
                    created:
                      type: integer
                    id:
                      type: string
                    model:
                      type: string
                    object:
                      enum:
                      - chat.completion
                      type: string
                    usage:
                      properties:
                        completion_tokens:
                          type: integer
                        prompt_cache_hit_tokens:
                          type: integer
                        prompt_cache_miss_tokens:
                          type: integer
                        prompt_tokens:
                          type: integer
                        total_tokens:
                          type: integer
                      type: object
                  title: DeepSeek LLM Integration
                  type: object
                - properties:
                    choices:
                      items:
                        properties:
                          finish_reason:
                            type: string
                          index:
                            type: integer
                          message:
                            properties:
                              content:
                                type: string
                              role:
                                type: string
                              tool_calls:
                                items:
                                  properties:
                                    function:
                                      properties:
                                        arguments:
                                          type: string
                                        name:
                                          type: string
                                      type: object
                                    id:
                                      type: string
                                    type:
                                      type: string
                                  type: object
                                type: array
                            type: object
                        type: object
                      type: array
                    created:
                      type: integer
                    id:
                      type: string
                    model:
                      type: string
                    object:
                      enum:
                      - chat.completion
                      type: string
                    usage:
                      properties:
                        completion_tokens:
                          type: integer
                        prompt_tokens:
                          type: integer
                        total_tokens:
                          type: integer
                      type: object
                  title: MiniMax LLM Integration
                  type: object
            text/event-stream:
              schema:
                description: Returns an SSE data stream when `stream=true`.
                type: string
          description: Success
        '401':
          description: Authentication failed
      summary: Create Chat Completion
      tags:
      - OpenAI LLM Integration
      x-apifox-folder: OpenAI
  /v1/responses:
    post:
      deprecated: false
      description: 'Request models that support the OpenAI Responses format.


        This endpoint is suitable for unified text, tool calling, and reasoning output.'
      operationId: openai-create-response
      parameters:
      - description: CCAPI token, in the format `Bearer sk-...`.
        example: Bearer sk-xxxx
        in: header
        name: Authorization
        required: true
        schema:
          type: string
      requestBody:
        content:
          application/json:
            examples:
              basic_response:
                summary: Basic Responses request
                value:
                  input: Summarize the main trade-offs between monolithic and microservice architectures.
                  model: gpt-6-sol
              reasoning_response:
                summary: Responses request with reasoning parameters
                value:
                  input: Design a rate limiting scheme suitable for high-concurrency chat APIs.
                  model: gpt-6-luna
                  reasoning:
                    effort: medium
            schema:
              properties:
                input:
                  description: Input content.
                  oneOf:
                  - type: string
                  - items:
                      type: object
                    type: array
                model:
                  description: Model name, e.g. `gpt-6-sol`, `gpt-5.5`, `gpt-6-luna`.
                  type: string
                reasoning:
                  properties:
                    effort:
                      enum:
                      - low
                      - medium
                      - high
                      type: string
                  type: object
                stream:
                  default: false
                  type: boolean
                text:
                  properties:
                    format:
                      properties:
                        type:
                          enum:
                          - text
                          - json_schema
                          type: string
                      type: object
                  type: object
                tools:
                  items:
                    type: object
                  type: array
              required:
              - model
              - input
              type: object
        required: true
      responses:
        '200':
          content:
            application/json:
              example:
                id: resp_example
                model: gpt-6-sol
                object: response
                output:
                - content:
                  - text: Monolithic architecture is simpler to deploy but weaker in scaling and independent evolution; microservices are more flexible but have higher governance costs.
                    type: output_text
                  role: assistant
                  type: message
                status: completed
                usage:
                  input_tokens: 28
                  output_tokens: 31
                  total_tokens: 59
              schema:
                properties:
                  id:
                    type: string
                  model:
                    type: string
                  object:
                    enum:
                    - response
                    type: string
                  output:
                    items:
                      type: object
                    type: array
                  status:
                    type: string
                  usage:
                    properties:
                      input_tokens:
                        type: integer
                      output_tokens:
                        type: integer
                      total_tokens:
                        type: integer
                    type: object
                type: object
            text/event-stream:
              schema:
                description: Returns an SSE data stream when `stream=true`.
                type: string
          description: Success
        '401':
          description: Authentication failed
      summary: Create Response
      tags:
      - OpenAI LLM Integration
      x-apifox-folder: OpenAI
components:
  securitySchemes:
    bearer:
      description: 'CCAPI API Key. Format: `Bearer sk-xxx`'
      scheme: bearer
      type: http
x-tagGroups:
- name: Integration Guides
  tags:
  - OpenClaw Integration
  - Hermes Integration
  - Claude Code Integration
  - Codex CLI Integration
  - Gemini CLI Integration
- name: Chat
  tags:
  - Claude / Anthropic LLM Integration
  - OpenAI LLM Integration
  - Google Gemini LLM Integration
  - DeepSeek LLM Integration
  - MiniMax LLM Integration
- name: Image
  tags:
  - GPT Image 2 Per-Call Image Generation
  - Midjourney Imagine API
  - Gemini Per-Call Image Generation
  - CCAPI Image Upscale
  - Z-Image Turbo
  - Doubao Seedream Official Image API
- name: Video
  tags:
  - Gemini Video (Veo 3.1 / Omni Flash)
  - Grok Imagine Video
  - MiniMax H3 Family Video Generation
  - Seedance Trusted Asset Library
  - Seedance 2.5 / 2.0 Video Generation
  - Vidu Video Generation API
- name: Audio
  tags:
  - Producer Task API
  - Suno Task API