glhf

glhf (glhf.chat) runs almost any open-source large language model on demand through an auto-scaling GPU scheduler built on vLLM. Any Hugging Face repository can be served by passing its identifier as hf:org/model to an OpenAI-compatible REST API, giving access to models like Llama, Qwen, and Mixtral without self-hosting.

2 APIs 0 Features

AILLMInferenceOpen Source ModelsHugging Face

APIs

glhf Chat Completions API

OpenAI-compatible chat completions endpoint that serves almost any open-source model from Hugging Face by passing the repository as hf:org/model. Supports streaming responses vi...

glhf Models API

OpenAI-compatible models endpoint that lists the models available to the account, using the same response shape as the OpenAI models API.

Collections

glhf API

OPEN

Pricing Plans

Glhf Chat Plans Pricing

2 plans

PLANS

Rate Limits

Glhf Chat Rate Limits

3 limits

RATE LIMITS

FinOps

Glhf Chat Finops

FINOPS

Event Specifications

glhf Chat Completions Streaming (HTTP + SSE)

AsyncAPI 2.6 description of glhf's (glhf.chat) **chat completion streaming** surface. glhf does not publish a WebSocket API. Its OpenAI-compatible REST API exposes chat completi...

ASYNCAPI

Resources

Sources

opencollection: 1.0.0
info:
  name: glhf 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://glhf.chat/api/openai/v1/chat/completions
      body:
        type: json
        data: "{\n  \"model\": \"hf:meta-llama/Llama-3.3-70B-Instruct\",\n  \"messages\": [\n    {\n      \"role\": \"user\"\
          ,\n      \"content\": \"Hello!\"\n    }\n  ],\n  \"stream\": false\n}"
    docs: Creates a model response for the given chat conversation. The model field must be a Hugging Face repository in the
      form hf:org/model. When stream is true, partial deltas are returned as Server-Sent Events.
- info:
    name: Models
    type: folder
  items:
  - info:
      name: List available models.
      type: http
    http:
      method: GET
      url: https://glhf.chat/api/openai/v1/models
    docs: Lists the models available to the account in the OpenAI models response shape.