Targon

Targon is a decentralized AI inference platform operated as Bittensor Subnet 4 by Manifold Labs. It serves popular open models through an OpenAI-compatible REST API at https://api.targon.com/v1, where a marketplace of miners runs the inference and validators verify responses, giving developers chat, completions, image, and search endpoints over confidential, decentralized compute.

5 APIs 0 Features

AILLMInferenceDecentralizedBittensor

APIs

Targon Chat Completions API

OpenAI-compatible chat completions across open models (Llama, DeepSeek, and other community-added models) served by Bittensor Subnet 4 miners, with streaming, temperature, and m...

Targon Completions API

OpenAI-compatible legacy text completion endpoint that takes a prompt string and returns generated text from decentralized miner inference.

Targon Models API

Lists the open models currently live on Targon, which can be extended permissionlessly by the community, with OpenAI-compatible model metadata.

Targon Images API

OpenAI-compatible image generation endpoint that returns images from a text prompt using image models served across the Subnet 4 miner marketplace.

Targon Search API

Search endpoint that returns relevant results for a query string, usable to ground model responses with retrieved context.

Collections

Targon API

OPEN

Pricing Plans

Targon Plans Pricing

2 plans

PLANS

Rate Limits

Targon Rate Limits

3 limits

RATE LIMITS

FinOps

Targon Finops

FINOPS

Event Specifications

Targon Chat Completions Streaming (HTTP + SSE)

AsyncAPI 2.6 description of Targon's **chat completion streaming** surface. Targon is a decentralized AI inference platform operated as Bittensor Subnet 4 by Manifold Labs. It d...

ASYNCAPI

Resources

👥

GitHubOrganization

Sources

opencollection: 1.0.0
info:
  name: Targon API
  version: '1.0'
request:
  auth:
    type: bearer
    token: '{{bearerToken}}'
items:
- info:
    name: Chat
    type: folder
  items:
  - info:
      name: Create a chat completion
      type: http
    http:
      method: POST
      url: https://api.targon.com/v1/chat/completions
      body:
        type: json
        data: "{\n  \"model\": \"deepseek-ai/DeepSeek-R1\",\n  \"messages\": [\n    { \"role\": \"user\", \"content\": \"\
          Hello\" }\n  ],\n  \"stream\": false\n}"
    docs: Generates a model response for the given chat conversation. Set stream to true for Server-Sent Events.
- info:
    name: Completions
    type: folder
  items:
  - info:
      name: Create a completion
      type: http
    http:
      method: POST
      url: https://api.targon.com/v1/completions
      body:
        type: json
        data: "{\n  \"model\": \"deepseek-ai/DeepSeek-R1\",\n  \"prompt\": \"Once upon a time\",\n  \"stream\": false\n}"
    docs: Generates a text completion for the provided prompt.
- info:
    name: Models
    type: folder
  items:
  - info:
      name: List models
      type: http
    http:
      method: GET
      url: https://api.targon.com/v1/models
    docs: Lists the models currently available on Targon.
  - info:
      name: Retrieve a model
      type: http
    http:
      method: GET
      url: https://api.targon.com/v1/models/{{model}}
    docs: Retrieves metadata for a single model by id.
- info:
    name: Images
    type: folder
  items:
  - info:
      name: Create an image
      type: http
    http:
      method: POST
      url: https://api.targon.com/v1/images/generations
      body:
        type: json
        data: "{\n  \"prompt\": \"A photo of a butterfly\",\n  \"n\": 1,\n  \"size\": \"1024x1024\"\n}"
    docs: Generates one or more images from a text prompt.
- info:
    name: Search
    type: folder
  items:
  - info:
      name: Search
      type: http
    http:
      method: POST
      url: https://api.targon.com/v1/search
      body:
        type: json
        data: "{\n  \"query\": \"latest AI inference news\",\n  \"max_results\": 10\n}"
    docs: Returns relevant results for a query string.