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

# Serverless Chat Completions

> OpenAI-compatible chat completions endpoint on the public Tensormesh Serverless host.

Use this page when you want the public serverless inference surface.

* Auth: `Authorization: Bearer <API_KEY>`
* Host: `https://serverless.tensormesh.ai`
* Compatibility: OpenAI-compatible chat completions
* Best for: the closest raw-HTTP match to an OpenAI-style chat request

If you have Control Plane access for the same Tensormesh environment, discover published serverless models with `tm billing pricing serverless list` and use the returned `pricing[].model` value in the request body. If you are targeting a different serverless host override, or you only have inference credentials, get the model name from your Tensormesh environment before sending the request. Start with [Choose A Serverless Model Name](/serverless-model-selection) if you do not already know the model name you need.

Other verified serverless reference pages:

* [List Models](/api-reference/serverless/models)
* [Create Completion](/api-reference/serverless/completions)
* [Create Response](/api-reference/serverless/responses)
* [Tokenize Text](/api-reference/serverless/tokenize)
* [Detokenize Tokens](/api-reference/serverless/detokenize)
* [Health Check](/api-reference/serverless/health)
* [Get Version](/api-reference/serverless/version)

For raw request setup, see [API Quickstart](/api-quickstart).


## OpenAPI

````yaml api-reference/serverless.openapi.yaml POST /v1/chat/completions
openapi: 3.1.0
info:
  title: Tensormesh Serverless Inference API
  version: 1.0.0
  description: |-
    OpenAI-compatible chat completions endpoint plus verified vLLM-compatible
    `/v1/models`, `/v1/completions`, `/v1/responses`, `/tokenize`,
    `/detokenize`, `/health`, and `/version` endpoints exposed through
    Tensormesh Serverless.

    Authentication: `Authorization: Bearer <API_KEY>` for `POST`
    inference requests. The public serverless host also serves
    `GET /v1/models`, `GET /health`, and `GET /version` without auth.

    If you have Control Plane access for the same Tensormesh environment,
    discover published serverless models with
    `tm billing pricing serverless list` and use the returned
    `pricing[].model` value in requests. If you are targeting a different
    serverless host override, or you only have inference credentials, get the
    model name from your Tensormesh environment before sending requests.
servers:
  - url: https://serverless.tensormesh.ai
    description: Tensormesh Serverless
security:
  - BearerAuth: []
tags:
  - name: inference.openapi_Inference
    x-displayName: Inference
paths:
  /v1/chat/completions:
    post:
      tags:
        - inference.openapi_Inference
      summary: Create Chat Completion
      description: Create a chat completion through the Serverless inference surface.
      operationId: create_serverless_chat_completion_v1_chat_completions_post
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ChatCompletionRequest'
            example:
              model: MiniMaxAI/MiniMax-M2.5
              max_tokens: 16384
              temperature: 0.6
              messages:
                - role: user
                  content: Hello, how are you?
              top_p: 1
              top_k: 40
              presence_penalty: 0
              frequency_penalty: 0
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ChatCompletionResponse'
            text/event-stream:
              schema:
                $ref: '#/components/schemas/ChatCompletionStreamResponse'
        '400':
          description: Bad Request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/OpenAIErrorResponse'
              examples:
                missing_model:
                  summary: Missing model
                  value:
                    error: 'Invalid request: missing ''model'' in request body.'
        '401':
          description: Unauthorized
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/OpenAIErrorResponse'
              examples:
                unauthorized:
                  summary: Missing or invalid API key
                  value:
                    error: Unauthorized
        '429':
          description: Rate Limited
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/OpenAIErrorResponse'
        '503':
          description: Service Unavailable
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/OpenAIErrorResponse'
      security:
        - BearerAuth: []
components:
  schemas:
    ChatCompletionRequest:
      type: object
      title: ChatCompletionRequest
      additionalProperties: true
      required:
        - model
        - messages
      properties:
        model:
          type: string
          title: Model
          description: |-
            Serverless model name to use.

            If you have Control Plane access for the same Tensormesh
            environment, discover published serverless models with `tm billing
            pricing serverless list` and use the returned `pricing[].model`
            value here. If you are targeting a different serverless host
            override, or you only have inference credentials, get the model
            name from your Tensormesh environment before sending requests.
          example: MiniMaxAI/MiniMax-M2.5
        messages:
          type: array
          title: Messages
          description: A list of messages comprising the conversation so far.
          items:
            $ref: '#/components/schemas/ChatMessage'
        temperature:
          anyOf:
            - type: number
            - type: 'null'
          title: Temperature
          description: |-
            Sampling temperature. Higher values make the output more random.

            Note: `temperature=0` is greedy sampling.
        top_p:
          anyOf:
            - type: number
            - type: 'null'
          title: Top P
          description: >-
            Nucleus sampling. We generally recommend altering this or
            temperature but not both.
        max_tokens:
          anyOf:
            - type: integer
            - type: 'null'
          title: Max Tokens
          description: >-
            The maximum number of tokens to generate in the completion.


            If set too low, the model may hit `finish_reason="length"` before
            producing useful `message.content`.
        max_completion_tokens:
          anyOf:
            - type: integer
            - type: 'null'
          title: Max Completion Tokens
          description: >-
            Alternative name for `max_tokens` (this inference surface accepts
            both; if both are set, behavior is runtime-dependent).
        'n':
          anyOf:
            - type: integer
            - type: 'null'
          title: 'N'
          default: 1
          description: >-
            How many choices to generate.


            Note: when using greedy sampling (`temperature=0`), `n` must be `1`
            (otherwise a 400 error).
        stop:
          anyOf:
            - type: string
            - type: array
              items:
                type: string
            - type: 'null'
          title: Stop
          description: Stop sequence(s) where the API will stop generating further tokens.
        top_k:
          anyOf:
            - type: integer
            - type: 'null'
          title: Top K
          description: >-
            Top-k sampling. Filters candidates to the K most likely tokens at
            each step.
        min_p:
          anyOf:
            - type: number
            - type: 'null'
          title: Min P
          description: >-
            Minimum probability threshold for token selection (alternative to
            `top_p` / `top_k`).
        typical_p:
          anyOf:
            - type: number
            - type: 'null'
          title: Typical P
          description: Typical-p sampling parameter.
        seed:
          anyOf:
            - type: integer
            - type: 'null'
          title: Seed
          description: >-
            Random seed for best-effort deterministic sampling (model/runtime
            dependent).
        repetition_penalty:
          anyOf:
            - type: number
            - type: 'null'
          title: Repetition Penalty
          description: Applies a penalty to repeated tokens to discourage repetition.
        mirostat_target:
          anyOf:
            - type: number
            - type: 'null'
          title: Mirostat Target
          description: Target perplexity for Mirostat sampling (if supported).
        mirostat_lr:
          anyOf:
            - type: number
            - type: 'null'
          title: Mirostat Lr
          description: Learning rate for Mirostat sampling (if supported).
        stream:
          anyOf:
            - type: boolean
            - type: 'null'
          title: Stream
          default: false
          description: >-
            Whether to stream back partial progress. If set, tokens will be sent
            as data-only server-sent events (SSE) as they become available, with
            the stream terminated by a `data: [DONE]` message.
        stream_options:
          anyOf:
            - $ref: '#/components/schemas/StreamOptions'
            - type: 'null'
          title: Stream Options
          description: Streaming options. Only valid when `stream=true`.
        response_format:
          anyOf:
            - $ref: '#/components/schemas/ResponseFormat'
            - type: 'null'
          title: Response Format
          description: >-
            Allows forcing the model to produce a specific output format.


            Supported values:


            - `{ "type": "json_object" }` (JSON mode)

            - `{ "type": "text" }`


            Note: extra keys inside `response_format` are rejected by this
            inference surface.
        tools:
          anyOf:
            - type: array
              items:
                $ref: '#/components/schemas/ChatCompletionTool'
            - type: 'null'
          title: Tools
          description: >-
            A list of tools the model may call. Currently, only functions are
            supported as a tool.
        tool_choice:
          anyOf:
            - type: string
              enum:
                - auto
                - none
                - required
            - $ref: '#/components/schemas/FunctionSelection'
            - type: 'null'
          title: Tool Choice
          default: auto
          description: >-
            Controls which (if any) tool is called by the model.


            - `none`: the model will not call any tool and instead generates a
            message.

            - `auto`: the model can pick between generating a message or calling
            tools.

            - `required`: the model is instructed to call one or more tools
            (model/runtime dependent).
        parallel_tool_calls:
          anyOf:
            - type: boolean
            - type: 'null'
          title: Parallel Tool Calls
          description: Enable parallel tool/function calling (if supported).
        presence_penalty:
          anyOf:
            - type: number
            - type: 'null'
          title: Presence Penalty
          description: >-
            Penalizes new tokens based on whether they appear in the text so
            far.
        frequency_penalty:
          anyOf:
            - type: number
            - type: 'null'
          title: Frequency Penalty
          description: >-
            Penalizes new tokens based on their existing frequency in the text
            so far.
        logprobs:
          anyOf:
            - type: boolean
            - type: 'null'
          title: Logprobs
          description: >-
            Include per-token log probabilities in the response (when supported
            by the model/runtime).
        top_logprobs:
          anyOf:
            - type: integer
            - type: 'null'
          title: Top Logprobs
          description: >-
            Number of most likely tokens to return at each position (requires
            `logprobs=true`).
        logit_bias:
          anyOf:
            - type: object
              additionalProperties:
                type: number
            - type: 'null'
          title: Logit Bias
          description: >-
            Modify the likelihood of specified tokens appearing in the
            completion.


            Maps token id (string) to bias (number).
        user:
          anyOf:
            - type: string
            - type: 'null'
          title: User
          description: A unique identifier representing your end-user.
        metadata:
          anyOf:
            - type: object
              additionalProperties: true
            - type: 'null'
          title: Metadata
          description: Additional metadata to store with the request for tracing.
        prompt_truncate_len:
          anyOf:
            - type: integer
            - type: 'null'
          title: Prompt Truncate Len
          description: >-
            Truncate chat prompts (in tokens) to this length by evicting older
            messages first.
        context_length_exceeded_behavior:
          anyOf:
            - type: string
              enum:
                - truncate
                - error
            - type: 'null'
          title: Context Length Exceeded Behavior
          description: What to do when prompt plus max tokens exceeds context window.
          default: truncate
        return_token_ids:
          anyOf:
            - type: boolean
            - type: 'null'
          title: Return Token Ids
          description: Return token IDs alongside text (populates `choices[].token_ids`).
          default: false
        prompt_cache_isolation_key:
          anyOf:
            - type: string
            - type: 'null'
          title: Prompt Cache Isolation Key
          description: >-
            Isolation key for prompt caching to separate cache entries (if
            supported).
        raw_output:
          anyOf:
            - type: boolean
            - type: 'null'
          title: Raw Output
          description: >-
            Return raw output from the model.


            Note: support is model/runtime dependent. Some deployments may
            return an error when enabled.
          default: false
        perf_metrics_in_response:
          anyOf:
            - type: boolean
            - type: 'null'
          title: Perf Metrics In Response
          description: >-
            Whether to include performance metrics in the response body.


            Note: this inference surface may accept the field but not include
            any extra metrics in the response body.
          default: false
        echo:
          anyOf:
            - type: boolean
            - type: 'null'
          title: Echo
          description: >-
            Echo back the prompt in addition to the completion.


            Note: support is model/runtime dependent. Some deployments may
            return an error when enabled.
          default: false
        echo_last:
          anyOf:
            - type: integer
            - type: 'null'
          title: Echo Last
          description: Echo back the last N tokens of the prompt (if supported).
        ignore_eos:
          anyOf:
            - type: boolean
            - type: 'null'
          title: Ignore Eos
          description: >-
            Whether the model should ignore the EOS token (model/runtime
            dependent).


            Note: support is model/runtime dependent. Some deployments may
            return an error when enabled.
          default: false
        speculation:
          anyOf:
            - type: string
            - type: array
              items:
                type: integer
            - type: 'null'
          title: Speculation
          description: Speculative decoding prompt or token IDs (if supported).
        prediction:
          anyOf:
            - $ref: '#/components/schemas/PredictedOutput'
            - type: string
            - type: 'null'
          title: Prediction
          description: >-
            OpenAI-compatible predicted output for speculative decoding (if
            supported).
        reasoning_effort:
          anyOf:
            - type: string
              enum:
                - low
                - medium
                - high
                - none
            - type: integer
            - type: boolean
            - type: 'null'
          title: Reasoning Effort
          description: >-
            Controls reasoning behavior for supported models (model/runtime
            dependent).
        reasoning_history:
          anyOf:
            - type: string
              enum:
                - disabled
                - interleaved
                - preserved
            - type: 'null'
          title: Reasoning History
          description: >-
            Controls how historical assistant reasoning content is included in
            the prompt (if supported).
        thinking:
          anyOf:
            - $ref: '#/components/schemas/ThinkingConfigEnabled'
            - $ref: '#/components/schemas/ThinkingConfigDisabled'
            - type: 'null'
          title: Thinking
          description: >-
            Alternative Anthropic-compatible config for reasoning (if
            supported).
        functions:
          anyOf:
            - type: array
              items:
                $ref: '#/components/schemas/ChatCompletionFunction'
            - type: 'null'
          title: Functions
          description: Deprecated (OpenAI). Use `tools` instead.
        function_call:
          anyOf:
            - type: string
              enum:
                - auto
                - none
            - $ref: '#/components/schemas/FunctionNameSpec'
            - type: 'null'
          title: Function Call
          description: Deprecated (OpenAI). Use `tool_choice` instead.
    ChatCompletionResponse:
      type: object
      title: ChatCompletionResponse
      additionalProperties: true
      required:
        - id
        - created
        - model
        - choices
      properties:
        id:
          type: string
          title: Id
          description: A unique identifier of the response.
        object:
          type: string
          title: Object
          description: The object type, which is always "chat.completion".
          default: chat.completion
        created:
          type: integer
          title: Created
          description: The Unix time in seconds when the response was generated.
        model:
          type: string
          title: Model
          description: The model used for the chat completion.
        choices:
          type: array
          title: Choices
          description: The list of chat completion choices.
          items:
            $ref: '#/components/schemas/ChatCompletionResponseChoice'
        usage:
          anyOf:
            - $ref: '#/components/schemas/UsageInfo'
            - type: 'null'
          default: null
        perf_metrics:
          anyOf:
            - type: object
              additionalProperties: true
            - type: 'null'
          default: null
          title: Perf Metrics
          description: Optional performance metrics (if enabled/supported).
        prompt_token_ids:
          anyOf:
            - type: array
              items:
                type: integer
            - type: 'null'
          default: null
          title: Prompt Token Ids
          description: Optional prompt token ids (when enabled/supported).
    ChatCompletionStreamResponse:
      type: object
      title: ChatCompletionStreamResponse
      additionalProperties: true
      required:
        - id
        - created
        - model
        - choices
      properties:
        id:
          type: string
          title: Id
        object:
          type: string
          title: Object
          default: chat.completion.chunk
        created:
          type: integer
          title: Created
        model:
          type: string
          title: Model
        choices:
          type: array
          title: Choices
          items:
            $ref: '#/components/schemas/ChatCompletionStreamChoice'
        usage:
          anyOf:
            - $ref: '#/components/schemas/UsageInfo'
            - type: 'null'
          default: null
    OpenAIErrorResponse:
      type: object
      title: OpenAIErrorResponse
      additionalProperties: true
      properties:
        error:
          anyOf:
            - $ref: '#/components/schemas/OpenAIError'
            - type: string
            - type: 'null'
          description: Error message (string) or structured error object.
    ChatMessage:
      type: object
      title: ChatMessage
      additionalProperties: true
      required:
        - role
      properties:
        role:
          type: string
          title: Role
          description: >-
            The role of the message author. One of `system`, `user`,
            `assistant`, or `tool`.
        content:
          anyOf:
            - type: string
            - type: 'null'
          title: Content
          description: Message text. May be null for assistant messages with tool calls.
        name:
          anyOf:
            - type: string
            - type: 'null'
          title: Name
          description: Optional name for the message author.
        reasoning_content:
          anyOf:
            - type: string
            - type: 'null'
          title: Reasoning Content
          description: Optional reasoning text (model/runtime dependent).
        tool_call_id:
          anyOf:
            - type: string
            - type: 'null'
          title: Tool Call Id
          description: Tool call id associated with a `tool` role message.
        tool_calls:
          anyOf:
            - type: array
              items:
                $ref: '#/components/schemas/ChatCompletionMessageToolCall'
            - type: 'null'
          title: Tool Calls
          description: Tool calls generated by the model (if any).
        reasoning:
          anyOf:
            - type: string
            - type: 'null'
          title: Reasoning
          description: Optional reasoning text for some models/runtimes.
    StreamOptions:
      type: object
      title: StreamOptions
      additionalProperties: true
      properties:
        include_usage:
          anyOf:
            - type: boolean
            - type: 'null'
          title: Include Usage
          description: Include final usage statistics in the stream.
    ResponseFormat:
      type: object
      title: ResponseFormat
      additionalProperties: false
      required:
        - type
      properties:
        type:
          type: string
          enum:
            - json_object
            - text
          title: Type
    ChatCompletionTool:
      type: object
      title: ChatCompletionTool
      additionalProperties: true
      required:
        - type
        - function
      properties:
        type:
          type: string
          enum:
            - function
          title: Type
        function:
          $ref: '#/components/schemas/ChatCompletionFunction'
    FunctionSelection:
      type: object
      title: FunctionSelection
      additionalProperties: true
      required:
        - type
      properties:
        type:
          type: string
          const: function
          title: Type
        function:
          anyOf:
            - $ref: '#/components/schemas/FunctionNameSpec'
            - type: 'null'
    PredictedOutput:
      type: object
      title: PredictedOutput
      additionalProperties: true
      required:
        - content
      properties:
        content:
          anyOf:
            - type: string
            - type: array
              items:
                type: object
                additionalProperties: true
          title: Content
        type:
          type: string
          const: content
          title: Type
          default: content
    ThinkingConfigEnabled:
      type: object
      title: ThinkingConfigEnabled
      additionalProperties: true
      required:
        - type
      properties:
        type:
          type: string
          const: enabled
          title: Type
        budget_tokens:
          anyOf:
            - type: integer
            - type: 'null'
          title: Budget Tokens
          description: Token budget for internal reasoning (if supported).
    ThinkingConfigDisabled:
      type: object
      title: ThinkingConfigDisabled
      additionalProperties: true
      required:
        - type
      properties:
        type:
          type: string
          const: disabled
          title: Type
    ChatCompletionFunction:
      type: object
      title: ChatCompletionFunction
      additionalProperties: true
      required:
        - name
      properties:
        name:
          type: string
          title: Name
          description: The name of the function to be called.
        description:
          type: string
          title: Description
          description: A description of what the function does.
        parameters:
          anyOf:
            - type: object
              additionalProperties: true
            - type: 'null'
          title: Parameters
          description: Parameters the function accepts, described as a JSON Schema object.
        strict:
          anyOf:
            - type: boolean
            - type: 'null'
          title: Strict
          description: Whether to enable strict argument schema adherence (if supported).
    FunctionNameSpec:
      type: object
      title: FunctionNameSpec
      additionalProperties: true
      required:
        - name
      properties:
        name:
          type: string
          title: Name
    ChatCompletionResponseChoice:
      type: object
      title: ChatCompletionResponseChoice
      additionalProperties: true
      required:
        - index
        - message
      properties:
        index:
          type: integer
          title: Index
        message:
          $ref: '#/components/schemas/ChatCompletionMessage'
        finish_reason:
          anyOf:
            - type: string
            - type: 'null'
          default: null
          title: Finish Reason
        logprobs:
          anyOf:
            - type: object
              additionalProperties: true
            - type: 'null'
          default: null
          title: Logprobs
        raw_output:
          anyOf:
            - type: object
              additionalProperties: true
            - type: 'null'
          default: null
          title: Raw Output
          description: Optional raw model output (if enabled/supported).
        stop_reason:
          anyOf:
            - type: string
            - type: 'null'
          default: null
          title: Stop Reason
        token_ids:
          anyOf:
            - type: array
              items:
                type: integer
            - type: 'null'
          default: null
          title: Token Ids
    UsageInfo:
      type: object
      title: UsageInfo
      additionalProperties: true
      required:
        - prompt_tokens
        - total_tokens
      properties:
        prompt_tokens:
          type: integer
          title: Prompt Tokens
        total_tokens:
          type: integer
          title: Total Tokens
        completion_tokens:
          anyOf:
            - type: integer
            - type: 'null'
          default: null
          title: Completion Tokens
        prompt_tokens_details:
          anyOf:
            - type: object
              additionalProperties: true
            - type: 'null'
          default: null
          title: Prompt Tokens Details
    ChatCompletionStreamChoice:
      type: object
      title: ChatCompletionStreamChoice
      additionalProperties: true
      required:
        - index
        - delta
      properties:
        index:
          type: integer
          title: Index
        delta:
          $ref: '#/components/schemas/DeltaMessage'
        finish_reason:
          anyOf:
            - type: string
            - type: 'null'
          default: null
          title: Finish Reason
        logprobs:
          anyOf:
            - type: object
              additionalProperties: true
            - type: 'null'
          default: null
          title: Logprobs
        token_ids:
          anyOf:
            - type: array
              items:
                type: integer
            - type: 'null'
          default: null
          title: Token Ids
    OpenAIError:
      type: object
      title: OpenAIError
      additionalProperties: true
      properties:
        message:
          anyOf:
            - type: string
            - type: 'null'
          title: Message
        type:
          anyOf:
            - type: string
            - type: 'null'
          title: Type
        param:
          anyOf:
            - type: string
            - type: 'null'
          title: Param
        code:
          anyOf:
            - type: string
            - type: integer
            - type: 'null'
          title: Code
    ChatCompletionMessageToolCall:
      type: object
      title: ChatCompletionMessageToolCall
      additionalProperties: true
      required:
        - type
        - function
      properties:
        id:
          anyOf:
            - type: string
            - type: 'null'
          title: Id
        type:
          type: string
          title: Type
          default: function
        function:
          $ref: '#/components/schemas/ChatCompletionMessageToolCallFunction'
    ChatCompletionMessage:
      type: object
      title: ChatCompletionMessage
      additionalProperties: true
      required:
        - role
      properties:
        role:
          type: string
          title: Role
        content:
          anyOf:
            - type: string
            - type: 'null'
          title: Content
        refusal:
          anyOf:
            - type: string
            - type: 'null'
          default: null
          title: Refusal
        annotations:
          anyOf:
            - type: array
              items:
                type: object
                additionalProperties: true
            - type: 'null'
          default: null
          title: Annotations
        audio:
          anyOf:
            - type: object
              additionalProperties: true
            - type: 'null'
          default: null
          title: Audio
        function_call:
          anyOf:
            - type: object
              additionalProperties: true
            - type: 'null'
          default: null
          title: Function Call
        tool_calls:
          anyOf:
            - type: array
              items:
                $ref: '#/components/schemas/ChatCompletionMessageToolCall'
            - type: 'null'
          default: null
          title: Tool Calls
        reasoning:
          anyOf:
            - type: string
            - type: 'null'
          default: null
          title: Reasoning
    DeltaMessage:
      type: object
      title: DeltaMessage
      additionalProperties: true
      properties:
        role:
          anyOf:
            - type: string
            - type: 'null'
          default: null
          title: Role
        content:
          anyOf:
            - type: string
            - type: 'null'
          default: null
          title: Content
        reasoning:
          anyOf:
            - type: string
            - type: 'null'
          default: null
          title: Reasoning
        tool_calls:
          anyOf:
            - type: array
              items:
                $ref: '#/components/schemas/ChatCompletionMessageToolCall'
            - type: 'null'
          default: null
          title: Tool Calls
    ChatCompletionMessageToolCallFunction:
      type: object
      title: ChatCompletionMessageToolCallFunction
      additionalProperties: true
      properties:
        name:
          anyOf:
            - type: string
            - type: 'null'
          title: Name
        arguments:
          anyOf:
            - type: string
            - type: object
              additionalProperties: true
            - type: 'null'
          title: Arguments
          description: Arguments as generated by the model (often a JSON string).
  securitySchemes:
    BearerAuth:
      type: http
      scheme: bearer
      bearerFormat: API_KEY
      description: >-
        Bearer authentication using your serverless API key. Format: Bearer
        <API_KEY>

````