Together AI Models API

openapi: 3.0.3
info:
  title: remediation.proto Audio Models API
  version: version not set
servers:
- url: https://api.together.xyz/v1
security:
- bearerAuth: []
tags:
- name: Models
paths:
  /models:
    get:
      tags:
      - Models
      summary: List all models
      description: Lists all of Together's open-source models
      x-codeSamples:
      - lang: Python
        label: Together AI SDK (v2)
        source: "# Docs for v1 can be found by changing the above selector ^\nfrom together import Together\nimport os\n\nclient = Together(\n    api_key=os.environ.get(\"TOGETHER_API_KEY\"),\n)\n\nmodels = client.models.list()\n\nfor model in models:\n    print(model.id)\n"
      - lang: Python
        label: Together AI SDK (v1)
        source: "from together import Together\nimport os\n\nclient = Together(\n    api_key=os.environ.get(\"TOGETHER_API_KEY\"),\n)\n\nmodels = client.models.list()\n\nfor model in models:\n    print(model.id)\n"
      - lang: TypeScript
        label: Together AI SDK (TypeScript)
        source: "import Together from \"together-ai\";\n\nconst client = new Together({\n  apiKey: process.env.TOGETHER_API_KEY,\n});\n\nconst models = await client.models.list();\n\nfor (const model of models) {\n  console.log(model.id);\n}\n"
      - lang: JavaScript
        label: Together AI SDK (JavaScript)
        source: "import Together from \"together-ai\";\n\nconst client = new Together({\n  apiKey: process.env.TOGETHER_API_KEY,\n});\n\nconst models = await client.models.list();\n\nfor (const model of models) {\n  console.log(model.id);\n}\n"
      - lang: Shell
        label: cURL
        source: "curl \"https://api.together.ai/v1/models\" \\\n     -H \"Authorization: Bearer $TOGETHER_API_KEY\" \\\n     -H \"Content-Type: application/json\"\n"
      operationId: models
      parameters:
      - name: dedicated
        in: query
        schema:
          description: Filter models to only return dedicated models
          type: boolean
      responses:
        '200':
          description: '200'
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ModelInfoList'
        '400':
          description: BadRequest
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorData'
        '401':
          description: Unauthorized
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorData'
        '404':
          description: NotFound
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorData'
        '429':
          description: RateLimit
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorData'
        '504':
          description: Timeout
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorData'
      deprecated: false
    post:
      tags:
      - Models
      summary: Upload a custom model or adapter
      description: Upload a custom model or adapter from Hugging Face or S3
      x-codeSamples:
      - lang: Python
        label: Together AI SDK (v2)
        source: "# Docs for v1 can be found by changing the above selector ^\nfrom together import Together\nimport os\n\nclient = Together(\n    api_key=os.environ.get(\"TOGETHER_API_KEY\"),\n)\n\nresponse = client.models.upload(\n    model_name=\"My-Fine-Tuned-Model\",\n    model_source=\"https://ml-models.s3.us-west-2.amazonaws.com/models/my-fine-tuned-model.tar.gz\",\n)\n\nprint(response.data.job_id)\n"
      - lang: Python
        label: Together AI SDK (v1)
        source: "from together import Together\nimport os\n\nclient = Together(\n    api_key=os.environ.get(\"TOGETHER_API_KEY\"),\n)\n\nresponse = client.models.upload(\n    \"My-Fine-Tuned-Model\",\n    \"https://ml-models.s3.us-west-2.amazonaws.com/models/my-fine-tuned-model.tar.gz\",\n)\n\nprint(response.job_id)\n"
      - lang: TypeScript
        label: Together AI SDK (TypeScript)
        source: "import Together from \"together-ai\";\n\nconst client = new Together({\n  apiKey: process.env.TOGETHER_API_KEY,\n});\n\nconst response = await client.models.upload({\n  model_name: \"My-Fine-Tuned-Model\",\n  model_source: \"https://ml-models.s3.us-west-2.amazonaws.com/models/my-fine-tuned-model.tar.gz\",\n})\n\nconsole.log(response);\n"
      - lang: JavaScript
        label: Together AI SDK (JavaScript)
        source: "import Together from \"together-ai\";\n\nconst client = new Together({\n  apiKey: process.env.TOGETHER_API_KEY,\n});\n\nconst response = await client.models.upload({\n  model_name: \"My-Fine-Tuned-Model\",\n  model_source: \"https://ml-models.s3.us-west-2.amazonaws.com/models/my-fine-tuned-model.tar.gz\",\n})\n\nconsole.log(response);\n"
      - lang: Shell
        label: cURL
        source: "curl -X POST \"https://api.together.ai/v1/models\" \\\n     -H \"Authorization: Bearer $TOGETHER_API_KEY\" \\\n     -H \"Content-Type: application/json\" \\\n     -d '{\n        \"model_name\": \"My-Fine-Tuned-Model\",\n        \"model_source\": \"https://ml-models.s3.us-west-2.amazonaws.com/models/my-fine-tuned-model.tar.gz\"\n      }'\n"
      operationId: uploadModel
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ModelUploadRequest'
      responses:
        '200':
          description: Model / adapter upload job created successfully
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ModelUploadSuccessResponse'
components:
  schemas:
    ModelInfo:
      type: object
      required:
      - id
      - object
      - created
      - type
      properties:
        id:
          type: string
          example: Austism/chronos-hermes-13b
        object:
          description: The object type, which is always `model`.
          const: model
        created:
          type: integer
          example: 1692896905
        type:
          enum:
          - chat
          - language
          - code
          - image
          - embedding
          - moderation
          - rerank
          example: chat
        display_name:
          type: string
          example: Chronos Hermes (13B)
        organization:
          type: string
          example: Austism
        link:
          type: string
        license:
          type: string
          example: other
        context_length:
          type: integer
          example: 2048
        pricing:
          $ref: '#/components/schemas/Pricing'
    ErrorData:
      type: object
      required:
      - error
      properties:
        error:
          type: object
          properties:
            message:
              type: string
              nullable: false
            type:
              type: string
              nullable: false
            param:
              type: string
              nullable: true
              default: null
            code:
              type: string
              nullable: true
              default: null
          required:
          - type
          - message
    ModelUploadRequest:
      type: object
      required:
      - model_name
      - model_source
      properties:
        model_name:
          type: string
          description: The name to give to your uploaded model
          example: Qwen2.5-72B-Instruct
        model_source:
          type: string
          description: The source location of the model (Hugging Face repo or S3 path)
          example: unsloth/Qwen2.5-72B-Instruct
        model_type:
          type: string
          description: Whether the model is a full model or an adapter
          default: model
          enum:
          - model
          - adapter
          example: model
        hf_token:
          type: string
          description: Hugging Face token (if uploading from Hugging Face)
          example: hf_examplehuggingfacetoken
        description:
          type: string
          description: A description of your model
          example: Finetuned Qwen2.5-72B-Instruct by Unsloth
        base_model:
          type: string
          description: The base model to use for an adapter if setting it to run against a serverless pool.  Only used for model_type `adapter`.
          example: Qwen/Qwen2.5-72B-Instruct
        lora_model:
          type: string
          description: The lora pool to use for an adapter if setting it to run against, say, a dedicated pool.  Only used for model_type `adapter`.
          example: my_username/Qwen2.5-72B-Instruct-lora
    ModelUploadSuccessResponse:
      type: object
      required:
      - data
      - message
      properties:
        data:
          type: object
          required:
          - job_id
          - model_name
          - model_id
          - model_source
          properties:
            job_id:
              type: string
              example: job-a15dad11-8d8e-4007-97c5-a211304de284
            model_name:
              type: string
              example: necolinehubner/Qwen2.5-72B-Instruct
            model_id:
              type: string
              example: model-c0e32dfc-637e-47b2-bf4e-e9b2e58c9da7
            model_source:
              type: string
              example: huggingface
        message:
          type: string
          example: Processing model weights. Job created.
    Pricing:
      type: object
      required:
      - hourly
      - input
      - output
      - base
      - finetune
      properties:
        base:
          type: number
          example: 0
        finetune:
          type: number
          example: 0
        hourly:
          type: number
          example: 0
        input:
          type: number
          example: 0.3
        output:
          type: number
          example: 0.3
        cached_input:
          type: number
          example: 0.2
    ModelInfoList:
      type: array
      items:
        $ref: '#/components/schemas/ModelInfo'
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      x-bearer-format: bearer
      x-default: default