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

# gpt-oss-120b

> Model details for gpt-oss-120b. Function calling, batch tasks, and reasoning with a 131K context window.

> OpenAI's gpt-oss-120b is an open-weight Mixture-of-Experts model with 117B total parameters (5.1B active per token), served on ZeroGPU for general text generation. It reasons through a problem before answering and returns that reasoning trace alongside the final answer, and it supports function calling, batch tasks, and a 131,072-token context window. When a task needs frontier-level reasoning or tool use beyond what the smaller edge models cover, this is the model.

**References:** [Model docs](https://huggingface.co/openai/gpt-oss-120b) • [Terms](https://zerogpu.ai/terms) • [Privacy](https://zerogpu.ai/privacy-policy)


## OpenAPI

````yaml api-reference/openapi/playgrounds/gpt-oss-120b.openapi.json POST /responses
openapi: 3.1.0
info:
  title: gpt-oss-120b playground
  version: '1.0'
  description: >-
    Interactive playground for **gpt-oss-120b**.

    Model is always `gpt-oss-120b` on this page (shown in the form, not
    editable).

    Use the **request example** selector to switch use cases (JSON, NER, PII,
    etc.).

    Authentication: `x-api-key` (required) and `x-project-id` (optional).
servers:
  - url: https://api.zerogpu.ai/v1
    description: Production
security:
  - ApiKey: []
paths:
  /responses:
    post:
      tags:
        - gpt-oss-120b
      summary: 'gpt-oss-120b: Responses'
      operationId: createResponse_gpt-oss-120b
      parameters:
        - name: x-project-id
          in: header
          required: false
          schema:
            type: string
          description: >-
            Optional project identifier. Scopes the request to a specific
            project when provided.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              allOf:
                - $ref: '#/components/schemas/CreateResponseRequest'
                - type: object
                  properties:
                    model:
                      type: string
                      const: gpt-oss-120b
                      default: gpt-oss-120b
                      example: gpt-oss-120b
                      description: >-
                        Model identifier (fixed for this playground). Use
                        request examples to change use cases.
            examples:
              default:
                summary: Default
                value:
                  input: >-
                    Name my WiFi network something that will make my neighbors
                    laugh. Give me your top 3 with a one-line reason each.
                  model: gpt-oss-120b
                  max_tokens: 800
                  instructions: You are a witty naming consultant. Be brief.
      responses:
        '200':
          description: Success
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Response'
              examples:
                default:
                  summary: Default
                  value:
                    id: id-1784318124857
                    object: response
                    created_at: 1784318124
                    model: gpt-oss-120b
                    status: completed
                    instructions: You are a witty naming consultant. Be brief.
                    output:
                      - id: rs_8d4dc6f3f33d0d28
                        type: reasoning
                        content:
                          - type: reasoning_text
                            text: >-
                              We need to respond with a top 3 WiFi names that
                              will make neighbors laugh, each with a one-line
                              reason. Be witty. Keep brief.
                      - id: msg_9c3dfbf63445d80a
                        type: message
                        role: assistant
                        status: completed
                        content:
                          - type: output_text
                            text: >-
                              **1. “FBI Surveillance Van #42”** – Neighbors will
                              double-check the street before they even think
                              about streaming.


                              **2. “Drop It Like It’s Hotspot”** – A pun that’s
                              so cheesy it’ll have the whole block groaning and
                              giggling.


                              **3. “Tell My Wi-Fi I Love You”** – Because
                              nothing says “I’m caring” like a reminder that
                              even your router needs affection.
                    usage:
                      input_tokens: 0
                      output_tokens: 0
                      total_tokens: 0
        '400':
          description: Bad request
        '401':
          description: Unauthorized
        '403':
          description: Forbidden
        '420':
          description: Insufficient quota
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '500':
          description: Internal server error
components:
  schemas:
    CreateResponseRequest:
      type: object
      required:
        - model
        - input
      properties:
        model:
          type: string
          const: gpt-oss-120b
          default: gpt-oss-120b
          example: gpt-oss-120b
          description: >-
            Model identifier (fixed for this playground). Use request examples
            to change use cases.
        input:
          type: string
          minLength: 1
          format: textarea
          maxLength: 131072
          description: Multi-line text or document content to send to the model.
        instructions:
          type: string
        max_tokens:
          type: integer
          minimum: 1
          example: 800
          description: Maximum number of tokens to generate in the response.
        metadata:
          type: object
          additionalProperties: true
    Response:
      type: object
      additionalProperties: true
    ErrorResponse:
      type: object
      additionalProperties: true
  securitySchemes:
    ApiKey:
      type: apiKey
      in: header
      name: x-api-key

````