OpenCode with FluxCDN AI
OpenCode reads and changes code from the terminal (and its desktop app and editor extension). You add FluxCDN to it as an OpenAI-compatible provider.
- Licence:
- MIT, open source
- Platforms:
- macOS, Linux, Windows (it recommends WSL)
- 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: Give OpenCode the key
In OpenCode type
/connect, choose Other at the bottom of the list, enterfluxcdnas the provider id and paste the key. It is kept in~/.local/share/opencode/auth.json.Step 2: Pick a model setup and write
opencode.jsonFor every project in
~/.config/opencode/opencode.json, or for one project at its root. Every model you want must be listed undermodels; givelimittoo, as OpenCode doesn't know a custom provider's model sizes.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.~/.config/opencode/opencode.json{ "$schema": "https://opencode.ai/config.json", "provider": { "fluxcdn": { "npm": "@ai-sdk/openai-compatible", "name": "FluxCDN AI", "options": { "baseURL": "https://ai.fluxcdn.cloud/api/v1" }, "models": { "anthropic/claude-haiku-5.5": { "name": "Claude Haiku 5.5", "limit": { "context": 1000000, "output": 32000 } }, "anthropic/claude-sonnet-5.5": { "name": "Claude Sonnet 5.5", "limit": { "context": 1000000, "output": 32000 } } } } }, "model": "fluxcdn/anthropic/claude-sonnet-5.5", "small_model": "fluxcdn/anthropic/claude-haiku-5.5" }Instead of
/connect, the key can come from an environment variable: add"apiKey": "{env:FLUXCDN_API_KEY}"tooptions.Step 3: Pick the model
Type
/modelsin OpenCode and pick one of the FluxCDN models.
Check it works
Step 1: Try it from the terminal
The first lists the models you set up, the second sends one message. If it fails, add
--print-logs.Terminalopencode models fluxcdn opencode run "Say hello in one sentence"
Troubleshooting
- A 401 with the key from an environment variable
- When the variable isn't set,
{env:FLUXCDN_API_KEY}becomes empty and the request goes without a key. Set the variable in that terminal, or give the key with/connect. - The model isn't in
/models - Each model must be listed under
modelsinopencode.json. Its full name in OpenCode looks likefluxcdn/deepseek/deepseek-v4-pro. - 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
- OpenCode needs tool calling to work; pick a model with the Tools label.

