OpenCode API key setup
OpenCode Zen: curated open coding models with limited-time free models plus the $10/month Go plan. Built for coding agents with a rotating model lineup.
Get your key
- Open the OpenCode site: opencode.ai
- Create an account and generate an API key.
- Paste it into the Dracon BYOK provider keys, stored encrypted (AES-256-GCM), used browser-direct, works in every Dracon tool.
Use your key in every tab
Two free extensions take the key you just set up. Both read the page you are on and use your own provider key: free, no account, nothing stored on a server we run.
AI Auto Form Filler
Complete a web form from a short description, using a model you bring yourself.
All extensions · last checked 2026-10-22.
Free tier
Yes. Nine limited-time free models are listed in the OpenCode Zen docs (Jev 1.13, GLM-5.3-Flash, DeepSeek V4.1 Flash, Beam, Flint 40B, MiMo-V2.6-Flash, Nemotron 3 Ultra, Nemotron 3.5 Lightning, Nemotron 3.5 Super VL). Availability and terms can change as OpenCode tunes the program; check the provider source for current specifics. (2026-10-26 recheck: the docs listed seven free models on 2026-09-20 and nine on 2026-10-26.) no credit card required
Rate limits: Go publishes estimated requests per 5 hours and monthly usage by model; limits rotate and vary by model. Zen is pay-as-you-go with configurable workspace monthly limits and auto-reload.
Paid plans compared
Every tier OpenCode publishes, with the price and the limit as the vendor states them, last checked 2026-10-27. Confirm with the provider before you buy. You pay them directly, no Dracon markup.
| Plan | Price | Usage limit | What you get |
|---|---|---|---|
| Go | $10/mo | $10/month; the Go page publishes per-model estimated requests per 5 hours and monthly usage; Top up credit if needed; cancel any time |
|
| Go Plus | $40/mo | Everything in Go; Higher limits and fewer interruptions; Built for larger, demanding projects | not published |
Official plan source: opencode.ai/go
Connection details
- Env var
OPENCODE_API_KEY- Model lineup
- MiniMax M3, MiniMax M2.7, GLM 5.3 Flash, GLM 5.3, Kimi K2.7 Code, Kimi K3, Qwen3.8 Flash, Qwen3.7 Max, Qwen3.7 Plus, DeepSeek V4.1 Flash, DeepSeek V4 Pro, DeepSeek V4 Flash
Gotchas
Browser-direct chat is not available for this provider: We haven't verified its chat endpoints yet.. Dracon provider keys still cover it for tools that run elsewhere (for example a LiteLLM chain from the Dracon Router builder).
Our verdicts on this kind of provider
Independent comparisons we keep current as pricing and free tiers shift. A guide is setup; a verdict is whether it's worth setting up.