Connect Hermes Agent to the gateway
Start a DeepSeek Flash session, read a project file, then switch to another gateway model. Follow the numbered steps below with your delivered Multi-Model Gateway key and address.
Configure once · switch models inside the Agent
Includes the eight-model configuration and setup instructions. Merge into your existing settings and replace the key or path placeholders locally.
Individual files remain available in the numbered steps below.
Before you begin
- Have your activated gateway key and its confirmed endpoint ready.
- Choose a local project with a README.md for the first conversation.
- Run shell commands in Terminal on macOS / Linux, or inside WSL on Windows. Paste prompts and slash commands inside the Agent.
Use the gateway credentials and model IDs in this guide. A direct DeepSeek Platform key, endpoint or setup script configures a different service.
1. Install and check your version
Install the Agent using its official guide below. Terminal examples use macOS / Linux or Windows WSL. If already installed, check your version and continue.
If hermes is not found, complete the official installer first, then open a new terminal.
Run in Terminal ·Terminal
hermes --version2. Save your key
Add this line to ~/.hermes/.env. Create the directory and file if needed. Use the same user home or profile that runs Hermes.
Replace the placeholder on your computer and keep the file private. Restart the Agent after saving.
Configuration ·~/.hermes/.env
MULTI_MODEL_API_KEY=REPLACE_WITH_YOUR_DELIVERED_GATEWAY_KEY3. Configure the gateway and models
If the file already exists, merge these fields and keep your other settings. Add to existing JSON objects or YAML sections; do not paste a second top-level object.
This configuration includes the complete model list. DeepSeek Flash is the starting model; choose a different one inside the Agent later.
Use config.yaml and .env from the same Hermes profile. Remove a stale model.base_url override if it points to a different provider.
Merge agent.reasoning_overrides as well as the provider and model sections. These eight defaults keep the first request valid for each backend; without them a custom endpoint can receive Hermes's Medium default, which Kimi K3 and both GLM routes do not accept. Empty model entries register names; they are not effort settings.
Configuration ·~/.hermes/config.yaml · merge with existing settings
Merge providers, model and agent.reasoning_overrides into the active Hermes profile's config.yaml. Preserve the other agent settings. Keep your key in that profile's .env file.
providers:
multi-model-gateway:
name: "Multi-Model Gateway"
api: "https://multi-api.deepseekv4pro.com/v1"
key_env: MULTI_MODEL_API_KEY
transport: chat_completions
default_model: "deepseek-flash"
models:
deepseek-flash: {}
glm-5.3-flash: {}
mimo-flash: {}
mimo-pro: {}
glm-5.3: {}
kimi-k3: {}
qwen3.8-max: {}
minimax-m3: {}
agent:
reasoning_overrides:
"deepseek-flash": "high"
"glm-5.3-flash": "max"
"mimo-flash": "high"
"mimo-pro": "high"
"glm-5.3": "max"
"kimi-k3": "max"
"qwen3.8-max": "xhigh"
"minimax-m3": "high"
model:
provider: custom:multi-model-gateway
default: "deepseek-flash"
4. Start Hermes
Start Hermes from your project directory, then use /model in chat to see the named provider and its models.
Check separately configured auxiliary models or fallbacks before using extra tools; they may use another provider.
Run in Terminal ·Terminal
hermes5. Choose reasoning effort
Start on DeepSeek Flash. Choose Low, send a short file-reading task, then choose High and repeat. Check the current setting after each change. A longer answer by itself does not prove the effort changed.
Effort means how much reasoning to request. Kimi K3, GLM 5.3 and GLM 5.3 Flash offer Low / High / Max with thinking always enabled. Choose Low for shorter reasoning; there is no Off option. Their model default is Max, but a client setting can override it. DeepSeek and Qwen have their own intensity levels listed below.
MiMo has an On / Off switch; High is the client's label for On. MiniMax M3 supports Off / Auto / On through thinking.type (disabled / adaptive / enabled). Its effort-only menus expose Off and High (On); Auto needs a native thinking control. These modes are not separate Low / High / Max intensities. Follow this Agent's default and switching instructions below; a supported control does not set a session's starting value.
The supplied agent.reasoning_overrides set a legal starting effort for every model. They take precedence over the global agent.reasoning_effort, including after a model switch or a new session. Without them, a custom provider can default to Medium, which Kimi K3 and both GLM routes reject.
Use /reasoning to inspect the current setting, then /reasoning low or /reasoning high for this session. Run /reasoning again after each change. --global saves the global fallback; it does not replace the per-model entries. Edit the matching reasoning_overrides entry to change a model's persistent default. /reasoning show and /reasoning hide change presentation, not reasoning intensity.
- DeepSeek Flash
- Off / Low / High / Max
- Starting setting: high
- Start with Low; choose High or Max for more reasoning, or Off to disable thinking. Medium and XHigh requests map to High; Ultra maps to Max.
- GLM-5.3-Flash
- Low / High / Max
- Starting setting: max
- Choose Low for shorter reasoning, High for more reasoning, or Max for the largest budget. Thinking is always enabled; there is no Off option. The model default is Max unless the client sends a different effort.
- MiMo V2.6 Flash
- Off / On
- Starting setting: On (High)
- Choose On to enable thinking or Off to disable it. In clients that label On as High, choose High. There are no separate Low, Medium or High intensities.
- MiMo V2.6 Pro
- Off / On
- Starting setting: On (High)
- Choose On to enable thinking or Off to disable it. In clients that label On as High, choose High. There are no separate Low, Medium or High intensities.
- GLM-5.3
- Low / High / Max
- Starting setting: max
- Choose Low for shorter reasoning, High for more reasoning, or Max for the largest budget. Thinking is always enabled; there is no Off option. The model default is Max unless the client sends a different effort.
- Kimi-K3
- Low / High / Max
- Starting setting: max
- Choose Low for shorter reasoning, High for more reasoning, or Max for the largest budget. Thinking is always enabled; there is no Off option. The model default is Max unless the client sends a different effort.
- Qwen3.8 Max
- Off / Low / Medium / XHigh
- Starting setting: xhigh
- Start with Low; choose Medium or XHigh for more reasoning, or Off to disable thinking. High, Max and Ultra requests all map to XHigh.
- MiniMax M3
- Off / On
- Starting setting: On (High)
- High means On. Auto needs the native thinking.type=adaptive control; this setup's effort selector does not expose Auto. Check the current selection before sending.
| Model | What can I change? | Starting setting | What should I do? |
|---|---|---|---|
| DeepSeek Flash | Off / Low / High / Max | high | Start with Low; choose High or Max for more reasoning, or Off to disable thinking. Medium and XHigh requests map to High; Ultra maps to Max. |
| GLM-5.3-Flash | Low / High / Max | max | Choose Low for shorter reasoning, High for more reasoning, or Max for the largest budget. Thinking is always enabled; there is no Off option. The model default is Max unless the client sends a different effort. |
| MiMo V2.6 Flash | Off / On | On (High) | Choose On to enable thinking or Off to disable it. In clients that label On as High, choose High. There are no separate Low, Medium or High intensities. |
| MiMo V2.6 Pro | Off / On | On (High) | Choose On to enable thinking or Off to disable it. In clients that label On as High, choose High. There are no separate Low, Medium or High intensities. |
| GLM-5.3 | Low / High / Max | max | Choose Low for shorter reasoning, High for more reasoning, or Max for the largest budget. Thinking is always enabled; there is no Off option. The model default is Max unless the client sends a different effort. |
| Kimi-K3 | Low / High / Max | max | Choose Low for shorter reasoning, High for more reasoning, or Max for the largest budget. Thinking is always enabled; there is no Off option. The model default is Max unless the client sends a different effort. |
| Qwen3.8 Max | Off / Low / Medium / XHigh | xhigh | Start with Low; choose Medium or XHigh for more reasoning, or Off to disable thinking. High, Max and Ultra requests all map to XHigh. |
| MiniMax M3 | Off / On | On (High) | High means On. Auto needs the native thinking.type=adaptive control; this setup's effort selector does not expose Auto. Check the current selection before sending. |
Enter in the Agent ·Inside the Agent · send each command separately
/reasoning
/reasoning low
/reasoning
/reasoning high
/reasoning
/reasoning lowCheck agent.reasoning_effort, agent.reasoning_overrides and extra_body in the active profile if the requested value differs. Remove a fixed reasoning_effort in extra_body. If the endpoint rejects reasoning and the session disables it, fix the setting and start a new session. After switching to Kimi or GLM, select Low, High or Max; do not keep an Off setting from another model.
6. Choose a model and start working
Use /model in Hermes chat or the Desktop model picker. The explicit chat commands below also switch models on this provider.
Open a project with a README.md and send the file-reading prompt below. Approve access to the file if prompted. You can switch models later without changing the key or gateway address.
You can also ask a question or search for current documentation. Send each example as a separate message.
For web search, configure a search provider in Hermes tool settings as well as the model provider.
Enter in the Agent ·Ask a question
What is 6 × 7?Enter in the Agent ·Read a project file
Use the file-reading tool to read README.md in the selected project and summarize its purpose in one sentence. Do not modify any files.Enter in the Agent ·Find documentation
Use web_search to find the official Claude Desktop gateway documentation. Summarize the setup requirements and include source links.Switch models in Hermes Agent
Use one command or picker entry at a time. An arrow means choose the entry in the picker; it is not part of a command. Your key must have access to the model you choose.
- DeepSeek Flash
/model custom:multi-model-gateway:deepseek-flash - GLM-5.3-Flash
/model custom:multi-model-gateway:glm-5.3-flash - MiMo V2.6 Flash
/model custom:multi-model-gateway:mimo-flash - MiMo V2.6 Pro
/model custom:multi-model-gateway:mimo-pro - GLM-5.3
/model custom:multi-model-gateway:glm-5.3 - Kimi-K3
/model custom:multi-model-gateway:kimi-k3 - Qwen3.8 Max
/model custom:multi-model-gateway:qwen3.8-max - MiniMax M3
/model custom:multi-model-gateway:minimax-m3
Connection reference
Keep these values consistent with the configuration above.
| Parameter | Value and purpose |
|---|---|
| Base URL | https://multi-api.deepseekv4pro.com/v1Keep the /v1 suffix in the provider base URL. |
| API protocol | OpenAI Chat Completions |
| API key | Use your delivered gateway key in the location shown in the setup steps. Replace credential placeholders locally. |
| Starting model | deepseek-flash |
Optional: check the API connection
Agent protocol: OpenAI Chat Completions. This Bash command uses the same API protocol with DeepSeek Flash. First export MULTI_MODEL_API_KEY in your terminal even if you saved the key in a settings file. The response should contain a short reply from DeepSeek Flash.
curl --fail-with-body "https://multi-api.deepseekv4pro.com/v1/chat/completions" \
-H "Authorization: Bearer $MULTI_MODEL_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"deepseek-flash","messages":[{"role":"user","content":"Reply with a short hello."}],"max_tokens":256}'Troubleshooting
- Models are missing
- Check the active config path, restart the Agent and look for project overrides. In Codex, check model_catalog_json; in OpenClaw, check model allowlists. Older Claude Code versions can use /model with an exact ID.
- Chat works but search fails
- Check Hermes web_search availability and its search-provider error separately from the model connection.
- 401 / 404
- 401: confirm the key is available to the running process. 404: check the model ID and base URL. Claude Code uses the root host; the other Agents here use /v1.
- 429 / unavailable endpoint
- Read the error for quota or provider capacity. Changing models does not refill points. Before activation, use only the confirmed endpoint supplied with your key.