Quick setup
Open the kRouter dashboard at http://localhost:20128
Go to Providers → click OpenCode Go
Paste your API key, click Save
Test the connection
Use in your IDE
Point any OpenAI-compatible client at kRouter using your local API key.
# Endpoint
http://localhost:20128/v1
# API key (from Dashboard → API Keys)
sk-krouter-XXXX
# Model
ocg/<model-id>How OpenCode Go billing works with kRouter
OpenCode Go is pay-per-token. You bring your own API key and kRouter routes to it, so you keep your own rate limits and billing relationship. kRouter authenticates it via apikey. 10 models are routable as opencode-go/<model>.
Through kRouter, OpenCode Go serves chat and code completion. Requests reach it through the same local OpenAI-compatible endpoint as every other provider, so switching to or from OpenCode Go is a one-line model change in your client rather than a rewrite.
OpenCode Go subscription: $5/mo (then $10/mo). Access to Kimi, GLM, Qwen, MiMo, MiniMax models.
OpenCode Go models & pricing
Prices are USD per 1M tokens, cheapest first. kRouter bills nothing on top; this is the provider's own rate.
| Model | Route as | Input /1M | Output /1M |
|---|---|---|---|
| Qwen 3.5 Plus | opencode-go/qwen3.5-plus | $0.50 | $2.00 |
| Qwen 3.6 Plus | opencode-go/qwen3.6-plus | $0.50 | $2.00 |
| MiniMax M2.7 | opencode-go/minimax-m2.7 | $0.50 | $2.00 |
| MiniMax M2.5 | opencode-go/minimax-m2.5 | $0.60 | $2.40 |
| GLM 5.1 | opencode-go/glm-5.1 | $1.00 | $4.00 |
| GLM 5 | opencode-go/glm-5 | $1.00 | $4.00 |
| Kimi K2.6 | opencode-go/kimi-k2.6 | $1.20 | $4.80 |
| Kimi K2.5 | opencode-go/kimi-k2.5 | $1.20 | $4.80 |
| MiMo V2 Pro | opencode-go/mimo-v2-pro | — | — |
| MiMo V2 Omni | opencode-go/mimo-v2-omni | — | — |
OpenCode Go links
OpenCode Go FAQ
Is OpenCode Go free through kRouter?
OpenCode Go is pay-per-token: you bring your own API key and are billed by OpenCode Go at their rates. kRouter adds nothing on top and is free and MIT-licensed.
How do I use OpenCode Go with Claude Code or Cursor?
Connect OpenCode Go in the kRouter dashboard, then point your tool at kRouter's local endpoint (http://localhost:20128/v1) with a kRouter API key. Any OpenAI-compatible client works, and models are addressed as opencode-go/<model>.
Which OpenCode Go models can kRouter route to?
10 models, including Kimi K2.6, Kimi K2.5, GLM 5.1. Every one is addressed as opencode-go/<model> from any client.
What happens when OpenCode Go is rate limited?
kRouter detects the limit, parks that account until its real reset time, and fails over to your next connected account or provider — so the request still completes instead of erroring.