Skip to content
FluxCDNFluxCDN
esc
On this page

DocsTools guide

VS Code with FluxCDN AI

VS Code gives you several ways, all with the same address and key: Copilot's own chat with the “Custom Endpoint” provider, or one of the open-source extensions. Those extensions also install in Cursor, Windsurf and other editors built on VS Code. Claude Code and Codex have VS Code extensions too; see their own pages.

Licence:
VS Code and the Copilot Chat extension: MIT; the Copilot service is proprietary
Platforms:
macOS, Linux, Windows
Address (OpenAI-compatible):
https://ai.fluxcdn.cloud/api/v1
Address (Full request address):
https://ai.fluxcdn.cloud/api/v1/chat/completions

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.

GitHub Copilot Chat

VS Code 1.122 or later. No GitHub account or Copilot plan is needed, and this use doesn't count against Copilot quotas.

The tool's own docs ↗
  1. Step 1: Add the Custom Endpoint provider

    From the Command Palette open Chat: Manage Language Models, then Add Models and Custom Endpoint. Give it a name (such as FluxCDN AI) and the key, and set the API type to Chat Completions. The key stays in VS Code's secret storage.

  2. Step 2: Pick a model and complete chatLanguageModels.json

    VS Code opens chatLanguageModels.json. Make models look like this and keep the apiKey line as VS Code wrote it. Add another block to models for each other model. toolCalling: true is needed for the model to show in Agent mode.

    Pick a setup; the settings below change with it. Any id from the models page works in their place too.

    Price per million tokens. Free plan prices, in Toman at today's rate. Routers (router/auto and the like) are not recommended for agents: an agent needs a model that is sure to support tools.

    chatLanguageModels.json
    [
      {
        "name": "FluxCDN AI",
        "vendor": "customendpoint",
        "apiKey": "${input:chat.lm.secret.…}",
        "apiType": "chat-completions",
        "models": [
          {
            "id": "anthropic/claude-sonnet-5.5",
            "name": "Claude Sonnet 5.5 (FluxCDN)",
            "url": "https://ai.fluxcdn.cloud/api/v1/chat/completions",
            "toolCalling": true,
            "vision": true,
            "maxInputTokens": 1000000,
            "maxOutputTokens": 32000
          }
        ]
      }
    ]

    The other types work too: "apiType": "messages" with https://ai.fluxcdn.cloud/api/v1/messages, or "responses" with https://ai.fluxcdn.cloud/api/v1/responses. Chat Completions is the simplest.

  3. Step 3: Pick the model

    Choose the model in the chat's model list. If it doesn't show, close and reopen VS Code once.

Cline

An open-source agent; with your own key no Cline account is needed.

Licence:
Apache-2.0
Platforms:
VS Code, JetBrains, CLI
The tool's own docs ↗
  1. Step 1: Set the provider

    In the Cline panel press the gear (settings) and enter these values. Under Model Configuration set the Context Window to the model's; Cline uses it to decide when to condense the conversation.

    Settings
    API Provider:  OpenAI Compatible
    Base URL:      https://ai.fluxcdn.cloud/api/v1
    API Key:       flux_live_YOUR_KEY
    Model ID:      anthropic/claude-sonnet-5.5

Kilo Code

Licence:
MIT
Platforms:
VS Code, JetBrains, CLI
The tool's own docs ↗
  1. Step 1: Add a custom provider

    Settings → Providers, then Custom provider at the bottom: id fluxcdn, display name FluxCDN AI, Provider API OpenAI Compatible, address https://ai.fluxcdn.cloud/api/v1 and the key. Kilo fetches the model list from FluxCDN (Fetch models). For the CLI or finer control, write the file below and put the key in FLUXCDN_API_KEY.

    ~/.config/kilo/kilo.jsonc
    {
      "$schema": "https://app.kilo.ai/config.json",
      "model": "fluxcdn/anthropic/claude-sonnet-5.5",
      "provider": {
        "fluxcdn": {
          "npm": "@ai-sdk/openai-compatible",
          "name": "FluxCDN AI",
          "options": {
            "baseURL": "https://ai.fluxcdn.cloud/api/v1",
            "apiKey": "{env:FLUXCDN_API_KEY}"
          },
          "models": {
            "anthropic/claude-sonnet-5.5": { "name": "Claude Sonnet 5.5", "tool_call": true, "limit": { "context": 1000000, "output": 32000 } },
            "qwen/qwen3-coder": { "name": "Qwen3 Coder", "tool_call": true, "limit": { "context": 262144, "output": 32000 } }
          }
        }
      }
    }

    {env:…} is ignored in a project's config file; keep the key in the global one.

Zoo Code

The continuation of Roo Code, which was archived on 15 May 2026. It is set up the same way.

Licence:
Apache-2.0
Platforms:
VS Code and editors built on it
The tool's own docs ↗
  1. Step 1: Set the provider

    Enter the same values from the settings icon. Zoo Code only works with native tool calling; pick a model with the Tools label.

    Settings
    API Provider:  OpenAI Compatible
    Base URL:      https://ai.fluxcdn.cloud/api/v1
    API Key:       flux_live_YOUR_KEY
    Model ID:      anthropic/claude-sonnet-5.5

Continue

Licence:
Apache-2.0
Platforms:
VS Code, JetBrains, CLI
The tool's own docs ↗
  1. Step 1: List the models in config.yaml

    Continue reloads the file when you save it. capabilities: [tool_use] is needed for Agent mode. Continue sends gpt-5 models to the Responses API by itself; useResponsesApi: false keeps everything on one route.

    ~/.continue/config.yaml · Windows: %USERPROFILE%\.continue\config.yaml
    name: FluxCDN
    version: 1.0.0
    schema: v1
    models:
      - name: Claude Sonnet 5.5 (FluxCDN)
        provider: openai
        model: anthropic/claude-sonnet-5.5
        apiBase: https://ai.fluxcdn.cloud/api/v1
        apiKey: flux_live_YOUR_KEY
        roles: [chat, edit, apply]
        capabilities: [tool_use, image_input]
      - name: GPT-5.5 (FluxCDN)
        provider: openai
        model: openai/gpt-5.5
        apiBase: https://ai.fluxcdn.cloud/api/v1
        apiKey: flux_live_YOUR_KEY
        useResponsesApi: false
        roles: [chat, edit, apply]
        capabilities: [tool_use, image_input]
      - name: Qwen3 Coder (FluxCDN)
        provider: openai
        model: qwen/qwen3-coder
        apiBase: https://ai.fluxcdn.cloud/api/v1
        apiKey: flux_live_YOUR_KEY
        roles: [chat, edit, apply]
        capabilities: [tool_use]

    Don't give FluxCDN models the embed or rerank roles; code indexing uses Continue's own local embedder.

Check it works

  1. Step 1: Ask the agent for something

    Choose a FluxCDN model in the chat panel and ask “list the files in this folder”. If a tool gets called, all is well. Copilot's errors show under Output → GitHub Copilot Chat.

Troubleshooting

The model doesn't show in Agent mode
chatLanguageModels.json needs "toolCalling": true, and the model must support tools.
Cline condenses too early or complains about the context
Set the context window under Model Configuration to the model's (shown on each model's page).
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.
An error about previous_response_id or OpenAI's built-in tools (web search, file search, code interpreter)
Some tools switch to the Responses API without saying so. FluxCDN has it, but without memory (the whole conversation is sent each time) and without the tools that run on OpenAI's servers. Set the tool to Chat Completions: in n8n turn off Use Responses API, in Continue useResponsesApi: false, in the Vercel AI SDK openai.chat(...), in LangChain use_responses_api=False.
The agent calls no tools, or the model is missing from the agent's list
Pick a model that supports tools; it has the Tools label on the models page. Some tools need that switched on for the model (the steps above). Routers are not recommended for agents.
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

  • Copilot's grey suggestions while typing (code completion), semantic search and embedding features still come from GitHub and need a GitHub account.

What doesn't work this way →