/v1/chat/completions
Chat Completions for messages, tools, and streaming output.
Use Grok 4.6 through a drop-in OpenAI-compatible API. Bring your Claudible key and start with one configuration.
https://groknova.claudible.io/v1
Copy this into ~/.config/opencode/opencode.json or your project opencode.json, then replace your_api_key_here with your Claudible key.
{
"$schema": "https://opencode.ai/config.json",
"lsp": true,
"provider": {
"grok": {
"npm": "@ai-sdk/openai-compatible",
"name": "Claudible Grok",
"options": {
"apiKey": "your_api_key_here",
"baseURL": "https://groknova.claudible.io/v1"
},
"models": {
"xai/grok-4.6": {
"id": "xai/grok-4.6",
"name": "Grok 4.6",
"provider": {
"npm": "@ai-sdk/openai-compatible",
"api": "https://groknova.claudible.io/v1"
}
}
}
}
},
"model": "grok/xai/grok-4.6"
}
baseURL must end with /v1. The configured model is xai/grok-4.6.
curl https://groknova.claudible.io/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"xai/grok-4.6","messages":[{"role":"user","content":"Say hello"}],"max_tokens":64}'
Use Chat Completions with the same Claudible key for messages, tools, and streaming output.
/v1/chat/completions
Chat Completions for messages, tools, and streaming output.
| Model | Input miss | Cache hit | Output |
|---|---|---|---|
xai/grok-4.6 | 40 | 10 | 120 |
Credits per 1M tokens. These fixed rates apply at every supported context length.