Telnyx OpenAI Chat API

openapi: 3.1.0
info:
  contact:
    email: support@telnyx.com
  description: Telnyx provides global communications and connectivity APIs for developers — including SIP trunking, programmable voice, SMS, MMS, WhatsApp Business Messaging, Call Control, Fax, Wireless (IoT & eSIM), Phone Numbers (DID provisioning & porting), Emergency Services, and Network APIs for private interconnects and edge connectivity. Build, scale, and manage voice, messaging, and data networks with Telnyx's carrier-grade global infrastructure and API-first platform.
  title: Telnyx Access Tokens OpenAI Chat API
  version: 2.0.0
  x-endpoint-cost: light
servers:
- description: Version 2.0.0 of the Telnyx API
  url: https://api.telnyx.com/v2
security:
- bearerAuth: []
tags:
- name: OpenAI Chat
paths:
  /ai/openai/chat/completions:
    post:
      description: Chat with a language model. This endpoint is consistent with the [OpenAI Chat Completions API](https://platform.openai.com/docs/api-reference/chat) and may be used with the OpenAI JS or Python SDK by setting the base URL to `https://api.telnyx.com/v2/ai/openai`.
      operationId: create_openai_chat_completion
      requestBody:
        content:
          application/json:
            example:
              messages:
              - content: You are a friendly chatbot.
                role: system
              - content: Hello, world!
                role: user
            schema:
              $ref: '#/components/schemas/ChatCompletionRequest'
        required: true
      responses:
        '200':
          content:
            application/json:
              schema:
                additionalProperties: true
                type: object
          description: Successful Response
        '422':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
          description: Validation Error
      summary: Create a chat completion (OpenAI-compatible)
      tags:
      - OpenAI Chat
      x-latency-category: responsive
  /ai/openai/models:
    get:
      description: 'This endpoint returns a list of Open Source and OpenAI models that are available for use. <br /><br /> **Note**: Model `id`''s will be in the form `{source}/{model_name}`. For example `openai/gpt-4` or `mistralai/Mistral-7B-Instruct-v0.1` consistent with HuggingFace naming conventions.'
      operationId: list_openai_models
      responses:
        '200':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ModelsResponse'
          description: Successful Response
        '422':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
          description: Validation Error
      summary: Get available models (OpenAI-compatible)
      tags:
      - OpenAI Chat
      x-latency-category: responsive
components:
  schemas:
    ModelMetadata:
      properties:
        created:
          title: Created
          type: integer
        id:
          title: Id
          type: string
        object:
          default: model
          title: Object
          type: string
        owned_by:
          title: Owned By
          type: string
      required:
      - id
      - created
      - owned_by
      title: ModelMetadata
      type: object
    BucketIds:
      properties:
        bucket_ids:
          description: List of [embedded storage buckets](https://developers.telnyx.com/api-reference/embeddings/embed-documents) to use for retrieval-augmented generation.
          items:
            type: string
          type: array
        max_num_results:
          description: The maximum number of results to retrieve as context for the language model.
          type: integer
      required:
      - bucket_ids
      title: BucketIds
      type: object
    ChatCompletionSystemMessageParam:
      properties:
        content:
          oneOf:
          - title: Content String
            type: string
          - items:
              additionalProperties: false
              properties:
                image_url:
                  type: string
                text:
                  type: string
                type:
                  enum:
                  - text
                  - image_url
                  type: string
              required:
              - type
              type: object
            title: Text and Image Array
            type: array
        role:
          enum:
          - system
          - user
          - assistant
          - tool
          type: string
      required:
      - content
      - role
      title: ChatCompletionSystemMessageParam
      type: object
    ValidationError:
      properties:
        loc:
          items:
            anyOf:
            - type: string
            - type: integer
          title: Location
          type: array
        msg:
          title: Message
          type: string
        type:
          title: Error Type
          type: string
      required:
      - loc
      - msg
      - type
      title: ValidationError
      type: object
    ChatCompletionRequest:
      properties:
        api_key_ref:
          description: If you are using an external inference provider like xAI or OpenAI, this field allows you to pass along a reference to your API key. After creating an [integration secret](https://developers.telnyx.com/api-reference/integration-secrets/create-a-secret) for you API key, pass the secret's `identifier` in this field.
          type: string
        best_of:
          description: This is used with `use_beam_search` to determine how many candidate beams to explore.
          type: integer
        early_stopping:
          default: false
          description: This is used with `use_beam_search`. If `true`, generation stops as soon as there are `best_of` complete candidates; if `false`, a heuristic is applied and the generation stops when is it very unlikely to find better candidates.
          type: boolean
        enable_thinking:
          default: true
          description: Whether to enable the thinking/reasoning phase for models that support it (e.g., QwQ, Qwen3). When set to false, the model will skip the internal reasoning step and respond directly, which can reduce latency. Defaults to true.
          type: boolean
        frequency_penalty:
          default: 0
          description: Higher values will penalize the model from repeating the same output tokens.
          type: number
        guided_choice:
          description: If specified, the output will be exactly one of the choices.
          items:
            type: string
          type: array
        guided_json:
          additionalProperties: true
          description: Must be a valid JSON schema. If specified, the output will follow the JSON schema.
          type: object
        guided_regex:
          description: If specified, the output will follow the regex pattern.
          type: string
        length_penalty:
          default: 1
          description: This is used with `use_beam_search` to prefer shorter or longer completions.
          type: number
        logprobs:
          default: false
          description: Whether to return log probabilities of the output tokens or not. If true, returns the log probabilities of each output token returned in the `content` of `message`.
          type: boolean
        max_tokens:
          description: Maximum number of completion tokens the model should generate.
          type: integer
        messages:
          description: A list of the previous chat messages for context.
          example:
          - content: You are a friendly chatbot.
            role: system
          - content: Hello, world!
            role: user
          items:
            $ref: '#/components/schemas/ChatCompletionSystemMessageParam'
          type: array
        min_p:
          description: This is an alternative to `top_p` that [many prefer](https://github.com/huggingface/transformers/issues/27670). Must be in [0, 1].
          type: number
        model:
          default: meta-llama/Meta-Llama-3.1-8B-Instruct
          description: The language model to chat with.
          type: string
        n:
          description: This will return multiple choices for you instead of a single chat completion.
          type: number
        presence_penalty:
          default: 0
          description: Higher values will penalize the model from repeating the same output tokens.
          type: number
        response_format:
          $ref: '#/components/schemas/ChatCompletionResponseFormatParam'
          description: Use this is you want to guarantee a JSON output without defining a schema. For control over the schema, use `guided_json`.
        seed:
          description: If specified, the system will make a best effort to sample deterministically, such that repeated requests with the same `seed` and parameters should return the same result.
          type: integer
        stop:
          description: Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.
          oneOf:
          - type: string
          - items:
              type: string
            maxItems: 4
            type: array
        stream:
          default: false
          description: Whether or not to stream data-only server-sent events as they become available.
          type: boolean
        temperature:
          default: 0.1
          description: Adjusts the "creativity" of the model. Lower values make the model more deterministic and repetitive, while higher values make the model more random and creative.
          type: number
        tool_choice:
          enum:
          - none
          - auto
          - required
          type: string
        tools:
          description: The `function` tool type follows the same schema as the [OpenAI Chat Completions API](https://platform.openai.com/docs/api-reference/chat). The `retrieval` tool type is unique to Telnyx. You may pass a list of [embedded storage buckets](https://developers.telnyx.com/api-reference/embeddings/embed-documents) for retrieval-augmented generation.
          items:
            oneOf:
            - $ref: '#/components/schemas/ChatCompletionToolParam'
            - $ref: '#/components/schemas/Retrieval'
          type: array
        top_logprobs:
          description: This is used with `logprobs`. An integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability.
          type: integer
        top_p:
          description: An alternative or complement to `temperature`. This adjusts how many of the top possibilities to consider.
          type: number
        use_beam_search:
          default: false
          description: Setting this to `true` will allow the model to [explore more completion options](https://huggingface.co/blog/how-to-generate#beam-search). This is not supported by OpenAI.
          type: boolean
      required:
      - messages
      title: ChatCompletionRequest
      type: object
    Retrieval:
      properties:
        retrieval:
          $ref: '#/components/schemas/BucketIds'
        type:
          enum:
          - retrieval
          type: string
      required:
      - type
      - retrieval
      title: Retrieval
      type: object
    ModelsResponse:
      properties:
        data:
          items:
            $ref: '#/components/schemas/ModelMetadata'
          title: Data
          type: array
        object:
          default: list
          title: Object
          type: string
      required:
      - data
      title: ModelsResponse
      type: object
    HTTPValidationError:
      properties:
        detail:
          items:
            $ref: '#/components/schemas/ValidationError'
          title: Detail
          type: array
      title: HTTPValidationError
      type: object
    ChatCompletionResponseFormatParam:
      properties:
        type:
          enum:
          - text
          - json_object
          type: string
      required:
      - type
      title: ChatCompletionResponseFormatParam
      type: object
    ChatCompletionToolParam:
      properties:
        function:
          $ref: '#/components/schemas/FunctionDefinition'
        type:
          enum:
          - function
          type: string
      required:
      - function
      - type
      title: Function
      type: object
    FunctionDefinition:
      properties:
        description:
          type: string
        name:
          type: string
        parameters:
          additionalProperties: true
          type: object
      required:
      - name
      title: FunctionDefinition
      type: object
  securitySchemes:
    bearerAuth:
      scheme: bearer
      type: http
    branded-calling_bearerAuth:
      description: API key passed as a Bearer token in the Authorization header
      scheme: bearer
      type: http
    oauthClientAuth:
      description: OAuth 2.0 authentication for Telnyx API and MCP integrations
      flows:
        authorizationCode:
          authorizationUrl: https://api.telnyx.com/v2/oauth/authorize
          refreshUrl: https://api.telnyx.com/v2/oauth/token
          scopes:
            admin: Administrative access to Telnyx resources
          tokenUrl: https://api.telnyx.com/v2/oauth/token
        clientCredentials:
          scopes:
            admin: Administrative access to Telnyx resources
          tokenUrl: https://api.telnyx.com/v2/oauth/token
      type: oauth2
    outbound-voice-profiles_bearerAuth:
      bearerFormat: JWT
      scheme: bearer
      type: http
    pronunciation-dicts_bearerAuth:
      description: Telnyx API v2 key. Obtain from https://portal.telnyx.com
      scheme: bearer
      type: http
    stored-payment-transactions_bearerAuth:
      bearerFormat: JWT
      scheme: bearer
      type: http