generated: '2026-08-26'
method: derived
source: openapi/_original/multiverse-computing-compactifai-openapi.json (fetched verbatim from https://api.compactif.ai/openapi.json)
summary:
  examples_in_spec: 6
  schemas_with_examples: 5
  operations_with_response_examples: 0
  note: Every example in the CompactifAI contract lives on a components.schemas entry, not on an operation
    request/response. No path item declares an example. Extracted verbatim here, unmodified.
defects:
- Four of the five examples name the model `cai-llama-3-1-8b-slim`, which was REMOVED from the API (the
  removals block in https://docs.compactif.ai/changelog/ withdraws llama-3-1-8b and cai-llama-3-3-70b-slim).
  Copy-pasting the published examples produces a 400 invalid_request_error.
- The ResponsesResult example names the model as `MultiverseComputingCAI/Hypernova-60B-2602`, a HuggingFace-style
  repo path, while every other surface (pricing page, models catalog, all other examples) uses the API
  model ID `hypernova-60b`. The contract is inconsistent with itself about what a model identifier looks
  like.
- The four operations with an empty 200 schema (chat completions, models list, model info, audio transcriptions)
  also carry no example, so the flagship endpoint of the product has neither a response type nor a sample
  response.
examples:
- schema: ChatCompletionRequest
  location: components.schemas.ChatCompletionRequest.examples
  example:
    max_tokens: 128
    messages:
    - content: You are a helpful assistant.
      role: system
    - content: Hello, I'm Camillo
      role: user
    - content: What is my name? What is the capital of Colombia?
      role: user
    model: cai-llama-3-1-8b-slim
    n: 1
    stop:
    - '###'
    temperature: 0.7
    tool_choice: auto
    tools:
    - function:
        description: Get the current weather in a given location.
        name: get_weather
        parameters:
          properties:
            location:
              type: string
            unit:
              enum:
              - celsius
              - fahrenheit
              type: string
          required:
          - location
          type: object
      type: function
    user: user-123
- schema: ChatCompletionRequest
  location: components.schemas.ChatCompletionRequest.examples
  example:
    max_tokens: 128
    messages:
    - content:
      - text: What do you see in this image? Describe it in detail.
        type: text
      - image_url:
          url: https://cdn.britannica.com/86/170586-120-7E23E561/Taj-Mahal-Agra-India.jpg
        type: image_url
      role: user
    model: mistral-small-3-1
    n: 1
    stop:
    - '###'
    temperature: 0.7
    user: user-123
- schema: CompletionRequest
  location: components.schemas.CompletionRequest.examples
  example:
    max_tokens: 128
    model: cai-llama-3-1-8b-slim
    prompt: What is the capital of France ?
    stop:
    - '###'
    temperature: 0.7
    top_p: 0.9
    user: user-123
- schema: CompletionResponse
  location: components.schemas.CompletionResponse.examples
  example:
    choices:
    - finish_reason: stop
      index: 0
      text: The capital of France is Paris.
    created: 1740395337
    id: 1861edc39ce648e3862a0b6ae9b7687b
    model: cai-llama-3-1-8b-slim
    object: text_completion
    usage:
      completion_tokens: 7
      prompt_tokens: 5
      total_tokens: 12
- schema: ResponsesRequest
  location: components.schemas.ResponsesRequest.examples
  example:
    input: Say hello in one short sentence.
    model: cai-llama-3-1-8b-slim
    reasoning: {}
    store: false
    text:
      format:
        type: text
- schema: ResponsesResult
  location: components.schemas.ResponsesResult.examples
  example:
    completed_at: 1773872348
    created_at: 1773872348
    id: resp_123
    model: MultiverseComputingCAI/Hypernova-60B-2602
    object: response
    output:
    - content:
      - text: Hello!
        type: output_text
      role: assistant
      type: message
    status: completed
    usage:
      input_tokens: 12
      output_tokens: 3
      total_tokens: 15