Skip to content
FluxCDNFluxCDN
esc
On this page

DocsTools guide

LibreChat with FluxCDN AI

LibreChat runs on your own server. You give it FluxCDN as a “custom endpoint”; requests go from the LibreChat server. LibreChat's agents use the same connection.

Licence:
MIT, open source
Platforms:
Self-hosted (Docker, Node); any browser
Address (OpenAI-compatible):
https://ai.fluxcdn.cloud/api/v1
Address (Anthropic-compatible):
https://ai.fluxcdn.cloud/api
The tool's own docs ↗

Before you start

  • Create an API key. On the API keys page press “Create key” and copy the key right away. It starts with flux_live_ and is never shown in full again.
  • Give agents a key of their own and set a daily or monthly spending limit on it with “Limits”. Agents send request after request by themselves; the limit stops spending you didn't expect.
  • Have some credit in the account (Billing).
  • In the examples, put your own key where it says flux_live_YOUR_KEY.

Set it up

  1. Step 1: Put the key in .env

    .env
    FLUXCDN_API_KEY=flux_live_YOUR_KEY
  2. Step 2: Define the endpoint in librechat.yaml

    The file sits next to .env at the project root. fetch: true fetches the model list from FluxCDN, and default is used if that fails. A cheap model writes the chat titles. If you want Claude models to go in Anthropic's own format, also add the second tab's block under custom.

    librechat.yaml
    version: 1.3.18
    cache: true
    endpoints:
      custom:
        - name: 'FluxCDN AI'
          apiKey: '${FLUXCDN_API_KEY}'
          baseURL: 'https://ai.fluxcdn.cloud/api/v1'
          models:
            default: ['anthropic/claude-sonnet-5.5', 'openai/gpt-5.5', 'deepseek/deepseek-v4-pro', 'z-ai/glm-5.3']
            fetch: true
          titleConvo: true
          titleModel: 'deepseek/deepseek-v4-flash'
          modelDisplayLabel: 'FluxCDN AI'
  3. Step 3: With Docker: mount the file

    Copy docker-compose.override.yml.example to docker-compose.override.yml, enable this part in it, and run docker compose down && docker compose up -d.

    docker-compose.override.yml
    services:
      api:
        volumes:
          - type: bind
            source: ./librechat.yaml
            target: /app/librechat.yaml

Check it works

  1. Step 1: Open a chat

    Choose “FluxCDN AI” in the endpoint selector, pick a model and send a message. The chat's title should appear shortly after.

Troubleshooting

LibreChat won't start (exit code 1)
librechat.yaml is invalid, usually the indentation. docker compose logs api shows the error.
A model rejects a parameter
Add dropParams to the endpoint, for example dropParams: ['stop'].
Error 401 or invalid_api_key
The key wasn't copied whole, was revoked, or went in the wrong field. It starts with flux_live_ and has no spaces. If the tool reads it from an environment variable, open a new terminal or window after setting it.
Error 402, insufficient_credit (in Codex: insufficient_quota) although you have credit
Before each request, the most it could cost is set aside from your credit. When the answer ends, only the real cost is taken and the rest is released. A tool that asks for a very long output on every request sets aside a large amount. Lower the tool's output limit (for example to 32000 tokens) or add credit.
Error 404 or model_not_found
The model id must be exactly as on the models page, with the maker's prefix: anthropic/claude-sonnet-5.5, not claude-sonnet-5.5. Lower case and dots matter. Copy the id rather than typing it.
A 404 that doesn't mention the model
The base address is wrong. Most tools want https://ai.fluxcdn.cloud/api/v1 and add the rest themselves; don't write /chat/completions twice and don't leave out /v1. See the which address table.
Error 429: rate_limit_exceeded or budget_exceeded
Either requests per minute went over the limit (wait a little; most tools retry by themselves), or this key's spending today or this month reached its limit. See it on API keys under “Limits”.
Error 502, 503, 504 or 529
The model's service was briefly unavailable. Send again; most tools do it themselves. A request that fails before answering costs nothing. If it lasts, switch to another model for a while.

Limits

  • File search (the RAG API) needs a separate embedding model; FluxCDN has no embeddings.

What doesn't work this way →