llmintel-ai Models API

openapi: 3.2.0
info:
  title: Llmintel Ai Models API
  version: 1.0.0
  contact:
    name: LLMIntel
    url: https://llmintel.ai
    email: support@llmintel.ai
  description: 'Operations tagged Models across 2 of this provider''s published API definitions: llmintel-ai-openapi.json, llmintel-ai-openapi.json. Each path carries the servers of the definition it was published in.'
servers:
- url: https://llmintel.ai
  description: Production
security:
- bearerAuth: []
tags:
- name: Models
  description: Tracked models and their current canonical lifecycle state.
paths:
  /v1/models:
    get:
      tags:
      - Models
      summary: List models
      description: All tracked models with their current canonical lifecycle state. **No API key required.** Anonymous callers share a stricter per-IP rate-limit budget; sending a key raises it to that key's tier.
      operationId: listModels
      security:
      - {}
      - bearerAuth: []
      parameters:
      - name: provider
        in: query
        required: false
        schema:
          type: string
          enum:
          - openai
          - anthropic
          - azure
          - bedrock
          - google
          - vertex
          - mistral
          - cohere
        description: Filter by provider.
      - name: state
        in: query
        required: false
        schema:
          type: string
          enum:
          - announced
          - active
          - legacy
          - deprecated
          - retiring
          - retired
        description: Filter by canonical lifecycle state.
      - name: limit
        in: query
        required: false
        schema:
          type: integer
          minimum: 0
          default: 100
      - name: offset
        in: query
        required: false
        schema:
          type: integer
          minimum: 0
          default: 0
      responses:
        '200':
          description: A page of models.
          headers:
            X-RateLimit-Limit:
              schema:
                type: integer
              description: Requests allowed per window.
            X-RateLimit-Remaining:
              schema:
                type: integer
              description: Requests remaining in the current window.
            X-RateLimit-Reset:
              schema:
                type: integer
              description: Unix epoch seconds when the window resets.
          content:
            application/json:
              schema:
                type: object
                properties:
                  data:
                    type: array
                    items:
                      $ref: '#/components/schemas/Model'
                  count:
                    type: integer
        '400':
          description: Invalid query parameter.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '401':
          description: Missing, invalid, or revoked API key.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '429':
          description: Rate limit exceeded.
          headers:
            X-RateLimit-Limit:
              schema:
                type: integer
              description: Requests allowed per window.
            X-RateLimit-Remaining:
              schema:
                type: integer
              description: Requests remaining in the current window.
            X-RateLimit-Reset:
              schema:
                type: integer
              description: Unix epoch seconds when the window resets.
            Retry-After:
              schema:
                type: integer
              description: Seconds until the window resets.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
    servers:
    - url: https://llmintel.ai
      description: Production
  /v1/models/{id}:
    get:
      tags:
      - Models
      summary: Get a model
      description: Full record for a canonical model id, including lifecycle history and the migration payload. The id contains a slash (e.g. `anthropic/claude-opus-4-1`) and is matched as a path, so request `/v1/models/anthropic/claude-opus-4-1`. **No API key required.** Anonymous callers share a stricter per-IP rate-limit budget; sending a key raises it to that key's tier.
      operationId: getModel
      security:
      - {}
      - bearerAuth: []
      parameters:
      - name: id
        in: path
        required: true
        schema:
          type: string
        example: anthropic/claude-opus-4-1
        description: Canonical model id (may contain a slash).
      responses:
        '200':
          description: The model detail.
          headers:
            X-RateLimit-Limit:
              schema:
                type: integer
              description: Requests allowed per window.
            X-RateLimit-Remaining:
              schema:
                type: integer
              description: Requests remaining in the current window.
            X-RateLimit-Reset:
              schema:
                type: integer
              description: Unix epoch seconds when the window resets.
          content:
            application/json:
              schema:
                type: object
                properties:
                  data:
                    $ref: '#/components/schemas/ModelDetail'
        '401':
          description: Missing, invalid, or revoked API key.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '404':
          description: No model with that id.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '429':
          description: Rate limit exceeded.
          headers:
            X-RateLimit-Limit:
              schema:
                type: integer
              description: Requests allowed per window.
            X-RateLimit-Remaining:
              schema:
                type: integer
              description: Requests remaining in the current window.
            X-RateLimit-Reset:
              schema:
                type: integer
              description: Unix epoch seconds when the window resets.
            Retry-After:
              schema:
                type: integer
              description: Seconds until the window resets.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
    servers:
    - url: https://llmintel.ai
      description: Production
components:
  schemas:
    Model:
      type: object
      required:
      - id
      - provider
      - displayName
      - aliases
      - lifecycleState
      - sourceUrl
      - sourceTerm
      properties:
        id:
          type: string
          example: openai/gpt-4o-2024-05-13
          description: Canonical model id (provider/model).
        provider:
          type: string
          enum:
          - openai
          - anthropic
          - azure
          - bedrock
          - google
          - vertex
          - mistral
          - cohere
        displayName:
          type: string
          example: GPT-4o (2024-05-13)
        aliases:
          type: array
          items:
            type: string
          example:
          - gpt-4o
          - gpt-4o-2024-05-13
        lifecycleState:
          type: string
          enum:
          - announced
          - active
          - legacy
          - deprecated
          - retiring
          - retired
          description: '- `announced` — Model has been announced by the provider but is not yet generally available.

            - `active` — Generally available. API calls succeed; recommended for new workloads.

            - `legacy` — Still callable, but superseded and no longer recommended for new workloads.

            - `deprecated` — No new customers/usage onboarding; existing API calls still succeed.

            - `retiring` — A hard retirement date is scheduled and imminent; calls still succeed until then.

            - `retired` — Shut down. API calls fail.'
        announcedDate:
          type:
          - string
          - 'null'
          format: date
          example: '2024-05-13'
        deprecatedDate:
          type:
          - string
          - 'null'
          format: date
          example: null
        retirementDate:
          type:
          - string
          - 'null'
          format: date
          example: '2025-10-02'
        sourceUrl:
          type: string
          format: uri
          description: Primary provider source the record was verified against.
        sourceTerm:
          type: string
          description: Verbatim provider term that mapped to the canonical state.
        openWeights:
          type: boolean
          description: 'The model ships downloadable weights and can be self-hosted. Use this to tell a null `inputUsdPerMillion` that means "no per-token rate exists" apart from one that means "not in our data yet". Independent of pricing: a model may have public weights and a published per-token rate at the same time.'
        lastVerifiedAt:
          type:
          - string
          - 'null'
          format: date-time
    ModelSpec:
      type:
      - object
      - 'null'
      properties:
        inputUsdPerMillion:
          type:
          - number
          - 'null'
        outputUsdPerMillion:
          type:
          - number
          - 'null'
        contextWindowTokens:
          type:
          - integer
          - 'null'
        maxOutputTokens:
          type:
          - integer
          - 'null'
        source:
          type:
          - string
          - 'null'
        updatedAt:
          type:
          - string
          - 'null'
          format: date-time
        capabilityClass:
          type:
          - string
          - 'null'
          enum:
          - flagship
          - balanced
          - lite
          - null
          description: Benchmark-derived capability tier (paid keys only).
        tokensPerSecond:
          type:
          - number
          - 'null'
          description: Median output tokens/sec (paid keys only).
        timeToFirstTokenSeconds:
          type:
          - number
          - 'null'
          description: Median TTFT in seconds (paid keys only).
        benchmarkSource:
          type:
          - string
          - 'null'
          description: Attribution for performance fields (paid keys only).
    Event:
      type: object
      required:
      - id
      - modelId
      - toState
      properties:
        id:
          type: string
          format: uuid
        modelId:
          type: string
          example: anthropic/claude-3-opus-20240229
        fromState:
          type:
          - string
          - 'null'
          enum:
          - announced
          - active
          - legacy
          - deprecated
          - retiring
          - retired
          - null
        toState:
          type: string
          enum:
          - announced
          - active
          - legacy
          - deprecated
          - retiring
          - retired
        detectedAt:
          type:
          - string
          - 'null'
          format: date-time
        verifiedAt:
          type:
          - string
          - 'null'
          format: date-time
    ModelDetail:
      allOf:
      - $ref: '#/components/schemas/Model'
      - type: object
        properties:
          spec:
            $ref: '#/components/schemas/ModelSpec'
          history:
            type: array
            items:
              $ref: '#/components/schemas/Event'
          migration:
            type:
            - object
            - 'null'
            properties:
              recommendedReplacementIds:
                type: array
                items:
                  type: string
              resolvedReplacementIds:
                type: array
                items:
                  type: string
              pricingDelta:
                type:
                - object
                - 'null'
              contextWindowDelta:
                type:
                - integer
                - 'null'
              breakingNotes:
                type:
                - string
                - 'null'
              confidence:
                type: string
              replacementSpec:
                $ref: '#/components/schemas/ModelSpec'
          optimization:
            type:
            - object
            - 'null'
            description: Advisory 'you could switch to…' suggestions (paid keys only; null otherwise). Editorial, with checkable reasons; never asserts equivalence beyond capability class.
            properties:
              confidence:
                type: string
                example: editorial
              analysisSource:
                type: string
                example: Artificial Analysis
              candidates:
                type: array
                items:
                  type: object
                  properties:
                    candidateId:
                      type: string
                    candidateDisplayName:
                      type: string
                    candidateProvider:
                      type: string
                      example: anthropic
                    capabilityClass:
                      type:
                      - string
                      - 'null'
                      enum:
                      - flagship
                      - balanced
                      - lite
                      - null
                    reasons:
                      type: array
                      items:
                        type: string
                      example:
                      - input −80%
                      - context 2×
                      - switch to anthropic
                    pricingDeltaPct:
                      type: object
                    contextWindowDelta:
                      type:
                      - integer
                      - 'null'
                    speedDelta:
                      type:
                      - number
                      - 'null'
                    crossProvider:
                      type: boolean
                      description: True when adopting this candidate means switching provider (extra migration effort).
    Error:
      type: object
      required:
      - error
      - message
      properties:
        error:
          type: string
          example: unauthorized
        message:
          type: string
          example: 'Provide an API key as ''Authorization: Bearer <key>''.'
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      description: API key as a bearer token. Create one from your dashboard.
x-refined-from:
- llmintel-ai-openapi.json
- llmintel-ai-openapi.json