DeepSeek Harness

Add SupaNexus as a custom provider in DeepSeek Harness. The bundled DeepSeek card talks to DeepSeek’s own API; add a custom provider to use the endpoints on this page. The same key can call any model in the Models catalog, not only DeepSeek.

See DeepSeek for DeepSeek models and pricing.

Fill <BASE_URL> from Endpoints. Official Harness: deepseek.com/harness · GitHub.

How to use DeepSeek Harness with a custom API

1. Install DeepSeek Harness from the official developer preview. Pin a version you have tested — the preview still ships breaking changes.
2. Open Settings → Models and choose Add a custom provider. Official DeepSeek catalog cards will not use the endpoints on this page.
3. Set a lowercase Provider ID such as supanexus. The id is permanent for sessions and credentials.
4. Base URL: <BASE_URL>/v1. API protocol: OpenAI Chat Completions (openai-completions).
5. Paste a SupaNexus project API key.
6. Add models such as deepseek/deepseek-v4-pro and deepseek/deepseek-v4-flash, or choose Fetch available models (GET /v1/models) to pull the full catalog. Other Public API IDs (Qwen, Kimi, GLM, and so on) work the same way.
7. Save. For fields the form does not expose, edit $DSH_HOME/settings.yaml and restart.

llm-pi-ai:
  providers:
    supanexus:
      apiKeyEnv: SUPANEXUS_API_KEY
      api: openai-completions
      baseURL: "<BASE_URL>/v1"
      models:
        - id: deepseek/deepseek-v4-pro
        - id: deepseek/deepseek-v4-flash

Keep the key in SUPANEXUS_API_KEY. Do not commit it into YAML. You can replace the models list with any Public API ID from Models.

DeepSeek Harness recommended API

Use the official DeepSeek catalog card only when you intend to call DeepSeek’s own API.

If the rest of your tools already speak Anthropic, you can point Harness at Messages (POST /v1/messages) instead. For a greenfield Harness setup, stay on Chat Completions.

OpenAI SDK (same models)

The same Public API IDs work outside Harness:

from openai import OpenAI

client = OpenAI(
    base_url="<BASE_URL>/v1",
    api_key="sk-snx-...",
)

response = client.chat.completions.create(
    model="deepseek/deepseek-v4-pro",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)

See also OpenAI SDK Integration and Models.