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 ↗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.
Step 2: Pick a model and complete
chatLanguageModels.jsonVS Code opens
chatLanguageModels.json. Makemodelslook like this and keep theapiKeyline as VS Code wrote it. Add another block tomodelsfor each other model.toolCalling: trueis needed for the model to show in Agent mode.Price per million tokens. Free plan prices, in Toman at today's rate. Routers (
router/autoand 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": "${input:chat.lm.secret.…}", "apiType": "chat-completions", "models": [ { "id": "anthropic/claude-sonnet-5.5", "name": "Claude Sonnet 5.5 (FluxCDN)", "url": "https://ai.fluxcdn.cloud/api/v1/chat/completions", "toolCalling": true, "vision": true, "maxInputTokens": 1000000, "maxOutputTokens": 32000 } ] } ]The other types work too:
"apiType": "messages"withhttps://ai.fluxcdn.cloud/api/v1/messages, or"responses"withhttps://ai.fluxcdn.cloud/api/v1/responses. Chat Completions is the simplest.Step 3: Pick the model
Choose the model in the chat's model list. If it doesn't show, close and reopen VS Code once.
Cline
An open-source agent; with your own key no Cline account is needed.
- Licence:
- Apache-2.0
- Platforms:
- VS Code, JetBrains, CLI
Step 1: Set the provider
In the Cline panel press the gear (settings) and enter these values. Under Model Configuration set the Context Window to the model's; Cline uses it to decide when to condense the conversation.
SettingsAPI Provider: OpenAI Compatible Base URL: https://ai.fluxcdn.cloud/api/v1 API Key: flux_live_YOUR_KEY Model ID: anthropic/claude-sonnet-5.5
Kilo Code
- Licence:
- MIT
- Platforms:
- VS Code, JetBrains, CLI
Step 1: Add a custom provider
Settings → Providers, then Custom provider at the bottom: id
fluxcdn, display name FluxCDN AI, Provider API OpenAI Compatible, addresshttps://ai.fluxcdn.cloud/api/v1and the key. Kilo fetches the model list from FluxCDN (Fetch models). For the CLI or finer control, write the file below and put the key inFLUXCDN_API_KEY.~/.config/kilo/kilo.jsonc{ "$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
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.
SettingsAPI 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
Step 1: List the models in
config.yamlContinue reloads the file when you save it.
capabilities: [tool_use]is needed for Agent mode. Continue sendsgpt-5models to the Responses API by itself;useResponsesApi: falsekeeps everything on one route.~/.continue/config.yaml · Windows: %USERPROFILE%\.continue\config.yamlname: 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
embedorrerankroles; code indexing uses Continue's own local embedder.
Check it works
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.jsonneeds"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, notclaude-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/v1and add the rest themselves; don't write/chat/completionstwice and don't leave out/v1. See the which address table. - An error about
previous_response_idor 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 SDKopenai.chat(...), in LangChainuse_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_exceededorbudget_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.

