Skip to content
FluxCDNFluxCDN
esc
On this page

DocsTools guide

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
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: 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_tokens means the context size.

    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.

    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 }
              }
            ]
          }
        }
      }
    }
  2. Step 2: Give the key

    Enter the key on the provider's page, or put it in the FLUXCDN_API_KEY variable. Don't write the key in settings.json.

    ~/.zshrc · ~/.bashrc
    export FLUXCDN_API_KEY="flux_live_YOUR_KEY"

Check it works

  1. 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, 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.
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

  • Edit predictions (Tab completion) don't use FluxCDN.

What doesn't work this way →