Model setup

Use qwen3.6-flash in Hermes Agent

Connect qwen3.6-flash with your ChineseModels API key and keep other providers in place.

Set up inCodex Kimi Code DeepSeek Harness Claude Code Hermes Agent OpenClaw DeepSeek guide

Copy the setup prompt

Paste into your coding assistant; enter your key only through a local secure prompt or secret store.

Set up qwen3.6-flash in Hermes Agent

A text-model listing does not establish agent compatibility. qwen-long rejected tools in repeated checks; keep it for plain-text API use and do not activate it for tool-based agent work. Review https://chinesemodels.ai/documentation#text-tools and validate the selected client/model combination.

Configure qwen3.6-flash from ChineseModels in Hermes Agent.
Guide: https://chinesemodels.ai/documentation/hermes-agent/models/qwen3.6-flash
Exact model ID: qwen3.6-flash

Detect my OS and client version; check the current official configuration reference. Back up existing config and preserve logins, providers, permissions and unrelated settings. Use a secure local key prompt or secret store; never print or commit the key.

Merge providers.chinesemodels into the active config.yaml: api https://chinesemodels.ai/v1, transport openai_chat, api_key as a secret/environment reference, discover_models false, and models containing the authenticated text list. Select /model <exact ID> --provider chinesemodels. Preserve other providers and auxiliary settings.

Fetch https://chinesemodels.ai/v1/models with my bearer key. Confirm this exact ID exists; do not silently substitute another model. Exclude image/video generators when importing more models. Test text, streaming, a tool call and a tool-result round trip. Only configure verified thinking parameters. Report what was tested, how to select this model, refresh the list and restore the backup. Do not change messaging channels, send messages or publish anything.

Manual setup

Back up the active config.yaml and merge the named provider below.
Supply CHINESEMODELS_API_KEY through the Hermes process environment or supported secret store.
Add more exact text IDs to models after fetching your authenticated /v1/models list. Leave discovery disabled to keep generators out.
Run hermes chat, then /model qwen3.6-flash --provider chinesemodels. Check hermes doctor if it is missing.

Configuration fragment: merge, do not replace the whole file

providers:
  chinesemodels:
    api: https://chinesemodels.ai/v1
    api_key: "${CHINESEMODELS_API_KEY}"
    transport: openai_chat
    discover_models: false
    models:
      - "qwen3.6-flash"

The usual config path is ~/.hermes/config.yaml; use your active profile's location if different.

Thinking and validation

Start with provider defaults. Only enable reasoning controls whose request fields match the chosen model. A visible effort menu does not establish that upstream thinking can be switched off.

Refresh from your authenticated /v1/models list and exclude image/video generators. Test a text reply, streaming and a tool-result round trip before using a model for agent work. Restore your configuration backup to undo the setup.

These additional client guides follow official configuration documentation. Complete end-to-end tests have not been performed for every client/model combination. Codex and Kimi guides document their own test results.

Official Hermes Agent configuration reference