LibreChat

These examples use the website API host, which currently lists their recommended models. The direct API host can have a different catalog during rollouts. For larger requests or longer runtimes, use https://api.nano-gpt.com/api/v1 with a model from that host’s catalog. See API Hosts for limits and availability checks.

Setup Instructions

Get your API key from nano-gpt.com/api

Locate your LibreChat installation’s librechat.example.yml file

Create a copy named librechat.yml

Add the following configuration to your librechat.yml:

# NanoGPT Example
- name: 'NanoGPT'
  apiKey: '${NANO_GPT_API_KEY}'
  baseURL: 'https://nano-gpt.com/api/v1/'
  models:
      default: [
        "openai/gpt-6.1-sol",
        "anthropic/claude-opus-5.5",
        "google/gemini-flash-latest",
        ]
      fetch: true
  addParams:
    reasoning_content_compat: true
  titleConvo: true
  titleModel: 'openai/gpt-6.1-sol'
  modelDisplayLabel: 'NanoGPT'
  iconUrl: https://nano-gpt.com/logo.png

LibreChat currently streams internal thinking from the legacy reasoning_content field. The addParams block above enables NanoGPT’s compatibility shim so LibreChat can render thoughts without additional changes. If you would rather not send the compatibility flag, you can instead point LibreChat at https://nano-gpt.com/api/v1legacy/ which keeps the legacy response shape by default.

Set your API key in your environment variables:

export NANO_GPT_API_KEY='your-api-key-here'

That’s it! Restart LibreChat, and you’ll have access to all NanoGPT models through the interface.

Get Started

Endpoint Examples

API Reference

Miscellaneous

Partner

Integrations

Using LibreChat with NanoGPT

Setup Instructions

Available Models

​Using LibreChat with NanoGPT

​Setup Instructions

​Available Models

Using LibreChat with NanoGPT

Setup Instructions

Available Models