DeepSeek Harness

Configure DeepSeek Harness for your enterprise and verify the request in your console logs.

Configuration

Use your enterprise HTTPS gateway URL, an API key scoped to this tool and a model ID that supports the protocol. The address below comes from this gateway’s public configuration. Find an eligible model

  1. In the Web UI, open Settings → Models and add a custom model API. Use token-pyxis as the provider ID.
  2. Choose OpenAI Chat Completions and supply the base URL ending in /v1, a project key, and at least one allowed model ID.
  3. For managed deployments, follow the official cordis.patch.yml instructions for your active profile and reference a process environment variable with apiKeyEnv.
API protocolAddress to enter
Chat CompletionsBase URLhttps://tokenpyxis.com/v1

Verification

Select your Token Pyxis model in the picker and verify a text response in a new session.

Check the model, timestamp and token usage in the enterprise console logs. If the tool shows a request ID, look it up directly. See reconciliation steps

Troubleshooting

Existing sessions may retain the previous model. Test in a new session after switching. For MISSING_CREDENTIAL, check the active profile’s credential source.

Business inquiries
Scan with WeChat to add the business team on WeCom