Skip to main content
kRouter
All providers

Pay-per-token

ocg/

OpenCode Go

OpenCode Go — connect via API key.

opencode.ai

Quick setup

  1. Open the kRouter dashboard at http://localhost:20128/dashboard

  2. Go to Providers → click OpenCode Go

  3. Paste your API key, click Save

  4. Test the connection

Use in your IDE

Point any OpenAI-compatible client at kRouter. Clients on another machine need a kRouter API key.

ide configbash
# Endpoint
http://localhost:20128/v1

# API key (Dashboard → Endpoint → API Keys;
# optional for clients on the same machine)
<your-krouter-key>

# 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. 43 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: $10/mo, or $40/mo for Go Plus (higher limits). Access to Kimi, GLM, Qwen, DeepSeek, MiMo, MiniMax, Grok, GPT Luna, Muse Spark and more.

OpenCode Go models & pricing

Prices are USD per 1M tokens, cheapest first. kRouter bills nothing on top; this is the provider's own rate.

ModelRoute asInput /1MOutput /1M
DeepSeek V4.1 Flashopencode-go/deepseek-v4.1-flash$0.14$0.28
DeepSeek V4 Flashopencode-go/deepseek-v4-flash$0.30$1.20
DeepSeek V4 Flash Vision (Exp)opencode-go/deepseek-v4-flash-vision-exp$0.30$1.20
DeepSeek Flashopencode-go/deepseek-flash$0.30$1.20
Qwen 3.8 Maxopencode-go/qwen3.8-max$0.50$2.00
Qwen 3.8 Flashopencode-go/qwen3.8-flash$0.50$2.00
Qwen 3.7 Maxopencode-go/qwen3.7-max$0.50$2.00
Qwen 3.7 Plusopencode-go/qwen3.7-plus$0.50$2.00
Qwen 3.6 Plusopencode-go/qwen3.6-plus$0.50$2.00
Qwen 3.5 Plusopencode-go/qwen3.5-plus$0.50$2.00
MiniMax M3opencode-go/minimax-m3$0.50$2.00
MiniMax M2.7opencode-go/minimax-m2.7$0.50$2.00
Grok 4.7opencode-go/grok-4.7$0.50$2.00
Grok 4.6opencode-go/grok-4.6$0.50$2.00
Grok 4.5opencode-go/grok-4.5$0.50$2.00
MiniMax M2.5opencode-go/minimax-m2.5$0.60$2.40
Kimi K3opencode-go/kimi-k3$1.00$4.00
GLM 5.3opencode-go/glm-5.3$1.00$4.00
GLM 5.3 Flash (Vision)opencode-go/glm-5.3-flash$1.00$4.00
GLM 5.2opencode-go/glm-5.2$1.00$4.00
GLM 5.1opencode-go/glm-5.1$1.00$4.00
GLM 5opencode-go/glm-5$1.00$4.00
DeepSeek V4 Proopencode-go/deepseek-v4-pro$1.32$3.96
Kimi K2.6opencode-go/kimi-k2.6$1.20$4.80
Kimi K2.7 Codeopencode-go/kimi-k2.7-code$1.20$4.80
Kimi K2.5opencode-go/kimi-k2.5$1.20$4.80
MiMo V2.6 Proopencode-go/mimo-v2.6-pro——
MiMo V2.6 Flashopencode-go/mimo-v2.6-flash——
MiMo V2.5 Proopencode-go/mimo-v2.5-pro——
MiMo V2.5opencode-go/mimo-v2.5——
MiMo V2 Proopencode-go/mimo-v2-pro——
MiMo V2 Omniopencode-go/mimo-v2-omni——
LongCat 2.0opencode-go/longcat-2.0——
LongCat 2.5 Preview (Free)opencode-go/longcat-2.5-preview-free——
Hy4 Previewopencode-go/hy4-preview——
Hy3opencode-go/hy3——
Hy3 Previewopencode-go/hy3-preview——
Space Bunnyopencode-go/space-bunny——
Omen Alphaopencode-go/omen-alpha——
GPT 6 Lunaopencode-go/gpt-6-luna——

Showing 40 of 43. The full list is in your dashboard once OpenCode Go is connected.

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?

43 models, including Kimi K2.6, Kimi K3, Kimi K2.7 Code. 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.