Continue integration
Configure DeepSeek in Continue with an OpenAI-Compatible Endpoint
Continue supports OpenAI-compatible providers through config.yaml. This setup keeps DeepSeek model names and Tokuse credentials outside your application code.
Settings
- Provider
- openai
- Model
- deepseek-flash
- API base
- https://tokuse.com/v1
Setup steps
- Open your Continue configuration file.
- Add an OpenAI provider model with apiBase set to the Tokuse OpenAI-compatible endpoint.
- Put the Tokuse key in a secret or environment variable, not directly in a shared repository.
- Reload the Continue extension and send a small test request.
Configuration
name: Tokuse DeepSeek
version: 0.0.1
schema: v1
models:
- name: DeepSeek Flash via Tokuse
provider: openai
model: deepseek-flash
apiBase: https://tokuse.com/v1
apiKey: ${{ secrets.TOKUSE_API_KEY }}
roles:
- chat
- editBefore production use
- Keep the Tokuse key on the server or in the tool's secret store.
- Use the base URL without appending /chat/completions.
- Verify the model alias in the current Tokuse catalog.
- Test errors, timeout behavior, and cost with a small workload first.