OpenCode is an AI coding tool that supports custom providers. You can configure OpenCode with Novita’s OpenAI-compatible LLM API endpoint and use Novita models for coding, debugging, refactoring, and project Q&A.
Prerequisites
Before you begin, prepare the following values:
- API key: Create or copy an API key from Key Management.
- Base URL:
https://api.novita.ai/openai/v1
- Model ID: Copy the model ID you want to use from the Model Hub, such as
deepseek/deepseek-v3.1.
Install OpenCode
OpenCode provides command-line and desktop options. Choose one installation method.
Linux / macOS / WSL2
Use one of the following methods:
curl -fsSL https://opencode.ai/install | bash
brew install anomalyco/tap/opencode
Desktop
You can also download the desktop app from:
https://opencode.ai/download
Open the OpenCode settings page and find the provider settings. Depending on your OpenCode version, this is usually under Settings → Providers → Custom Provider.
Fill in the following values:
| Field | Value |
|---|
| Display name | Novita |
| Base URL | https://api.novita.ai/openai/v1 |
| API key | Your Novita API key |
| Model ID | For example, deepseek/deepseek-v3.1 |
Make sure the Model ID exactly matches the value in Novita’s Model Hub. Context length, pricing, and capabilities depend on the selected model.
Verify the model
After saving the provider, select your Novita model in OpenCode and send a test prompt:
In one sentence, tell me what programming tasks you can help with.
If the model responds, the integration is working. If verification fails, check that:
- Your API key is correct and your account has available balance.
- The Base URL is
https://api.novita.ai/openai/v1.
- The Model ID is correct.
- Your network can reach the Novita API endpoint.