Segmind

Segmind Inference API

Synchronous (v1) and asynchronous (v2) model inference. v2 is the current contract — submit a job, poll a lightweight status endpoint, fetch the result — and reports cost, remaining credits and timings in a metrics object on every completed request.

GitHub OpenAPI
Business capability
Artificial Intelligence Management BC-610.60

Operations 4

Each operation below carries the questions people ask an LLM about it and the instructions they give an agent to run it. Generated by API Evangelist overlay

POST /v1/{model_name} Run a model and wait for the output · Synchronous model inference #
Ask an LLM
“How do I call a model like fast-flux-schnell and get the result back in the same response?”
“Which way of calling a model returns the output immediately for jobs under about a minute?”
Tell an agent
Run {model_name} with the prompt {prompt} and wait for the result.
Call {model_name} synchronously and return the output directly.
POST /v2/{model_name} Queue a model request to run in the background · Asynchronous model inference #
Ask an LLM
“How do I submit a long-running model job and get a request ID to check on later?”
“Can I queue a prompt for a model asynchronously instead of waiting for it to finish?”
Tell an agent
Queue an async request to {model_name} with the prompt {prompt} and give me the request ID.
Submit a background job to {model_name} without waiting for the output.
GET /v2/requests/{request_id}/status Check whether an async request has finished · Get lightweight request status #
Ask an LLM
“Is my queued model request still processing or has it completed?”
“What's a quick way to poll the status of an async request without pulling the full output?”
Tell an agent
Check the status of async request {request_id}.
Tell me if request {request_id} is done yet.
GET /v2/requests/{request_id} Get the full output of an async request · Get full async result #
Ask an LLM
“Where do I fetch the generated output once my async model request completes?”
“Can I retrieve the complete result payload for a background request by its ID?”
Tell an agent
Fetch the full result of async request {request_id}.
Get me the generated output for request {request_id}.

Documentation

📖
APIReference
https://docs.segmind.com/docs/serverless-api

Specifications

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

Other Resources

🔗
Overlay
https://raw.githubusercontent.com/api-evangelist/segmind/refs/heads/main/overlays/segmind-inference-api-overlay.yaml
🔗
AgentSkill
https://raw.githubusercontent.com/api-evangelist/segmind/refs/heads/main/skills/segmind-async-inference.md

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/segmind:segmind-inference-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

segmind-inference-api-openapi.yml Raw ↑ 
openapi: 3.2.0
info:
  title: Segmind Inference API
  description: Segmind provides API access to top AI models for rapid prototyping and deployment, including synchronous and asynchronous model inference, fine-tuning, and asset upload. Authenticated with an API key header.
  version: '1'
  contact:
    name: Segmind
    url: https://www.segmind.com/
servers:
- url: https://api.segmind.com
  description: Segmind model inference and account API
- url: https://workflows-api.segmind.com
  description: Segmind workflows/storage API
security:
- apiKeyAuth: []
tags:
- name: Inference
  description: Synchronous and asynchronous model inference
paths:
  /v1/{model_name}:
    post:
      tags:
      - Inference
      summary: Synchronous model inference
      description: Submit a request to a model and wait for the response. Suitable for models that complete within roughly 60 seconds.
      operationId: invokeModelSync
      parameters:
      - in: path
        name: model_name
        required: true
        schema:
          type: string
        description: Model identifier, e.g. fast-flux-schnell
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              additionalProperties: true
              properties:
                prompt:
                  type: string
      responses:
        '200':
          description: Model inference response
  /v2/{model_name}:
    post:
      tags:
      - Inference
      summary: Asynchronous model inference
      description: Submit an async request; returns a request_id.
      operationId: invokeModelAsync
      parameters:
      - in: path
        name: model_name
        required: true
        schema:
          type: string
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              additionalProperties: true
              properties:
                prompt:
                  type: string
      responses:
        '200':
          description: Async request accepted
          content:
            application/json:
              schema:
                type: object
                properties:
                  request_id:
                    type: string
  /v2/requests/{request_id}/status:
    get:
      tags:
      - Inference
      summary: Get lightweight request status
      operationId: getRequestStatus
      parameters:
      - in: path
        name: request_id
        required: true
        schema:
          type: string
      responses:
        '200':
          description: Status payload
          content:
            application/json:
              schema:
                type: object
                properties:
                  status:
                    type: string
  /v2/requests/{request_id}:
    get:
      tags:
      - Inference
      summary: Get full async result
      operationId: getRequestResult
      parameters:
      - in: path
        name: request_id
        required: true
        schema:
          type: string
      responses:
        '200':
          description: Full async result
components:
  securitySchemes:
    apiKeyAuth:
      type: apiKey
      in: header
      name: x-api-key