Skip to content
FluxCDNFluxCDN
esc
On this page

DocsTools guide

Desktop chat apps: Cherry Studio, Chatbox and Jan

These apps install on your own computer and send requests straight from it. All three take an OpenAI-compatible “custom provider” and fetch the model list from FluxCDN.

Address (OpenAI-compatible):
https://ai.fluxcdn.cloud/api/v1

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.

Cherry Studio

Licence:
AGPL-3.0 (Community Edition)
Platforms:
Windows, macOS, Linux
The tool's own docs ↗
  1. Step 1: Add the provider

    Settings → Model Provider → Add Provider, name FluxCDN AI, type OpenAI. Enter the key and the address. The Preview line under the address should read https://ai.fluxcdn.cloud/api/v1/chat/completions. Press Check, then add models from Model management and turn the provider on.

    Settings → Model Provider → Add Provider
    Provider Type:  OpenAI
    API Key:        flux_live_YOUR_KEY
    API Host:       https://ai.fluxcdn.cloud/api/v1

Chatbox

Licence:
The Community Edition on GitHub is GPL-3.0
Platforms:
Windows, macOS, Linux, iOS, Android, web
The tool's own docs ↗
  1. Step 1: Add the provider

    Settings → Model Provider, then Add at the bottom. Name FluxCDN AI, type OpenAI API compatible. Enter the key and the address and leave API Path empty. Fetch the models from the server or add them by hand, press Save, then Check. Chatbox's web version works too.

    Settings → Model Provider → Add
    API type:  OpenAI API compatible
    API Key:   flux_live_YOUR_KEY
    API Host:  https://ai.fluxcdn.cloud/api/v1
    API Path:  (empty)

Jan

Licence:
Apache-2.0
Platforms:
Windows, macOS, Linux
The tool's own docs ↗
  1. Step 1: Add the provider

    Settings → Model Providers → Add Provider, name FluxCDN AI, format OpenAI-compatible, the address and key, then Create. Jan fetches the model list; if it doesn't, add the id by hand with +. To use tools, press the pencil next to the model and turn on Tools.

    Settings → Model Providers → Add Provider
    API format:  OpenAI-compatible
    Base URL:    https://ai.fluxcdn.cloud/api/v1
    API key:     flux_live_YOUR_KEY

Check it works

  1. Step 1: The check button, then a chat

    Cherry Studio and Chatbox have a Check button. Then pick a FluxCDN model in a new chat and send a message.

Troubleshooting

The model list is empty
Add the id by hand, such as anthropic/claude-sonnet-5.5. The address must include /v1 (Cherry Studio and Chatbox add it if missing; Jan doesn't).
Chatbox has the “OpenAI Responses” type and no answer comes
Set the type to OpenAI API compatible; that route sends every model the same way.
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.
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

  • The apps' knowledge bases need an embedding model; use another provider or a local model (such as Ollama).
  • Image sections (such as Cherry Studio's “Paintings”) call /images and don't work with FluxCDN.

What doesn't work this way →