Zed with FluxCDN AI
Zed takes an OpenAI-compatible provider directly. Its agent, inline assistant, commit messages and thread summaries use it. The key stays in the system keychain.
- Licence:
- GPL-3.0 (some parts Apache-2.0)
- Platforms:
- macOS, Linux, Windows
- 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.
Set it up
Step 1: Pick a model setup and write the settings
Zed → Settings → Open Settings File and add this section. Or enter the same values under Settings → AI → LLM Providers → Add Provider. In Zed
max_tokensmeans the context size.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.Zed: settings.json{ "language_models": { "openai_compatible": { "fluxcdn": { "api_url": "https://ai.fluxcdn.cloud/api/v1", "available_models": [ { "name": "anthropic/claude-sonnet-5.5", "display_name": "Claude Sonnet 5.5 (FluxCDN)", "max_tokens": 1000000, "max_output_tokens": 32000, "capabilities": { "tools": true, "images": true, "parallel_tool_calls": false, "prompt_cache_key": false } } ] } } } }Step 2: Give the key
Enter the key on the provider's page, or put it in the
FLUXCDN_API_KEYvariable. Don't write the key in settings.json.~/.zshrc · ~/.bashrcexport FLUXCDN_API_KEY="flux_live_YOUR_KEY"
Check it works
Step 1: Ask the agent to read a file
Open the Agent panel, choose the FluxCDN model and ask it to read a file. If a tool gets called, it works.
Troubleshooting
- The model isn't in Zed's model list
- Zed only shows the models listed in
available_models. Add a block per model and copy the id exactly from the models 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invalid_api_key - The key wasn't copied whole, was revoked, or went in the wrong field.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. - 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
- Edit predictions (Tab completion) don't use FluxCDN.

