FuriosaAI

FuriosaAI Models API

The Models API from FuriosaAI — 3 operation(s) for models.

GitHub OpenAPI

Operations 3

GET /v2/models/${MODEL_NAME}/versions/${MODEL_VERSION}/ready Model Ready #
GET /v2/models/${MODEL_NAME}/versions/${MODEL_VERSION} Model Metadata #
POST /v2/models/${MODEL_NAME}/versions/${MODEL_VERSION}/infer Inference #

Specifications

⚙
OpenAPI
https://raw.githubusercontent.com/api-evangelist/furiosa/refs/heads/main/openapi/furiosa-models-api-openapi.yml

Other Resources

🔗
Protobuf
https://raw.githubusercontent.com/api-evangelist/furiosa/refs/heads/main/grpc/furiosa-predict.proto
🔗
ErrorCatalog
https://raw.githubusercontent.com/api-evangelist/furiosa/refs/heads/main/errors/furiosa-problem-types.yml
🔗
DataModel
https://raw.githubusercontent.com/api-evangelist/furiosa/refs/heads/main/data-model/furiosa-data-model.yml
🔗
SourceCode
https://github.com/furiosa-ai/furiosa-sdk
🔗
Protobuf
https://raw.githubusercontent.com/api-evangelist/furiosa/refs/heads/main/grpc/furiosa-model-repository.proto

Work with this as data

Every API here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for apis

7 MCP tools reach this
  • find_apisBrowse and filter every API in the catalog.
  • get_api_artifactsOne API's artifacts, grouped by type.
  • get_openapiThe primary OpenAPI for this API.
  • find_similar_apisAPIs that look like this one.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools →

Call it yourself

curl for this page
This API 
curl "https://apis.io/api/v1/apis/furiosa-models-api"
All apis 
curl "https://apis.io/api/v1/apis?limit=25"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.

OpenAPI Specification

furiosa-models-api-openapi.yml Raw ↑ 
openapi: 3.2.0
info:
  title: Predict Models API
  version: '2.0'
  description: https://github.com/kubeflow/kfserving/blob/master/docs/predict-api/v2/required_api.md
  license:
    name: Apache 2.0
servers: []
tags:
- name: Models
paths:
  /v2/models/${MODEL_NAME}/versions/${MODEL_VERSION}/ready:
    parameters:
    - schema:
        type: string
      name: MODEL_NAME
      in: path
      required: true
    - schema:
        type: string
      name: MODEL_VERSION
      in: path
      required: true
    get:
      summary: Model Ready
      tags:
      - Models
      responses:
        '200':
          description: OK
      operationId: get-v2-models-$-modelName-versions-$-modelVersion-ready
      description: The “model ready” health API indicates if a specific model is ready for inferencing. The model name and (optionally) version must be available in the URL. If a version is not provided the server may choose a version based on its own policies.
  /v2/models/${MODEL_NAME}/versions/${MODEL_VERSION}:
    parameters:
    - schema:
        type: string
      name: MODEL_NAME
      in: path
      required: true
    - schema:
        type: string
      name: MODEL_VERSION
      in: path
      required: true
    get:
      summary: Model Metadata
      tags:
      - Models
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/metadata_model_response'
      operationId: get-v2-models-$-modelName-versions-$-modelVersion
      description: The per-model metadata endpoint provides information about a model. A model metadata request is made with an HTTP GET to a model metadata endpoint. In the corresponding response the HTTP body contains the [Model Metadata Response JSON Object](#model-metadata-response-json-object) or the [Model Metadata Response JSON Error Object](#model-metadata-response-json-error-object). The model name and (optionally) version must be available in the URL. If a version is not provided the server may choose a version based on its own policies or return an error.
  /v2/models/${MODEL_NAME}/versions/${MODEL_VERSION}/infer:
    parameters:
    - schema:
        type: string
      name: MODEL_NAME
      in: path
      required: true
    - schema:
        type: string
      name: MODEL_VERSION
      in: path
      required: true
    post:
      summary: Inference
      operationId: post-v2-models-$-MODEL_NAME-versions-$-MODEL_VERSION-infer
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/inference_response'
        '400':
          description: Bad Request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/inference_error_response'
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/inference_request'
      description: An inference request is made with an HTTP POST to an inference endpoint. In the request the HTTP body contains the [Inference Request JSON Object](#inference-request-json-object). In the corresponding response the HTTP body contains the [Inference Response JSON Object](#inference-response-json-object) or [Inference Response JSON Error Object](#inference-response-json-error-object). See [Inference Request Examples](#inference-request-examples) for some example HTTP/REST requests and responses.
      tags:
      - Models
components:
  schemas:
    inference_error_response:
      title: inference_error_response
      type: object
      properties:
        error:
          type: string
    inference_request:
      title: inference_request
      type: object
      x-examples:
        Example 1:
          id: '42'
          inputs:
          - name: input0
            shape:
            - 2
            - 2
            datatype: UINT32
            data:
            - 1
            - 2
            - 3
            - 4
          - name: input1
            shape:
            - 3
            datatype: BOOL
            data:
            - true
          outputs:
          - name: output0
        Example 2:
          id: '42'
          outputs:
          - name: output0
            shape:
            - 3
            - 2
            datatype: FP32
            data:
            - 1
            - 1.1
            - 2
            - 2.1
            - 3
            - 3.1
      properties:
        id:
          type: string
        parameters:
          $ref: '#/components/schemas/parameters'
        inputs:
          type: array
          items:
            $ref: '#/components/schemas/request_input'
        outputs:
          type: array
          items:
            $ref: '#/components/schemas/request_output'
      required:
      - inputs
    parameters:
      type: object
      title: parameters
      x-examples: {}
      additionalProperties: true
      properties:
        content_type:
          type: string
    metadata_model_response:
      title: metadata_model_response
      type: object
      properties:
        name:
          type: string
        versions:
          type: array
          items:
            type: string
        platform:
          type: string
        inputs:
          type: array
          items:
            $ref: '#/components/schemas/metadata_tensor'
        outputs:
          type: array
          items:
            $ref: '#/components/schemas/metadata_tensor'
      required:
      - name
      - platform
    metadata_tensor:
      title: metadata_tensor
      type: object
      properties:
        name:
          type: string
        datatype:
          type: string
        shape:
          type: array
          items:
            type: integer
        tags:
          type: object
          additionalProperties: true
          properties:
            content_type:
              type: string
      required:
      - name
      - datatype
      - shape
    response_output:
      title: response_output
      type: object
      properties:
        name:
          type: string
        shape:
          type: array
          items:
            type: integer
        datatype:
          type: string
        parameters:
          $ref: '#/components/schemas/parameters'
        data:
          $ref: '#/components/schemas/tensor_data'
      required:
      - name
      - shape
      - datatype
      - data
    tensor_data:
      title: tensor_data
    request_output:
      title: request_output
      type: object
      properties:
        name:
          type: string
        parameters:
          $ref: '#/components/schemas/parameters'
      required:
      - name
    inference_response:
      title: inference_response
      type: object
      properties:
        model_name:
          type: string
        model_version:
          type: string
        id:
          type: string
        parameters:
          $ref: '#/components/schemas/parameters'
        outputs:
          type: array
          items:
            $ref: '#/components/schemas/response_output'
      required:
      - model_name
      - outputs
    request_input:
      title: request_input
      type: object
      properties:
        name:
          type: string
        shape:
          type: array
          items:
            type: integer
        datatype:
          type: string
        parameters:
          $ref: '#/components/schemas/parameters'
        data:
          $ref: '#/components/schemas/tensor_data'
      required:
      - name
      - shape
      - datatype
      - data