Hermes Agent setup

One connection. All seven models.

Set up your Agent once, then switch models and reasoning effort in the same session.

Run inOperating system

Prefer to skip manual setup? Ask AI to do it for you.

AI setup prompt

Follow https://siapi.ai/docs/hermes?model=deepseek-flash&surface=cli&platform=macos to connect my Agent to all SI-API models. Preserve existing settings and ask for my API key when needed.

GLM 5.3 Flash
DeepSeek V4.1 Flash
Kimi K3.1 Pro
Kimi K3.1 Pro HighSpeed
GLM 5.3
MiniMax M3.1 Flash
Qwen3.8 Max

All seven models are in this download. Keep the same configuration when switching models. Get your API key →

1. Prepare your tool and key

Install Hermes Agent from its official page. Create or copy your SI-API key from /keys.

Official installation guide ↗

Select the Hermes profile you intend to use. Save both config.yaml and .env in that profile directory; the default is ~/.hermes.

2. Save the configuration

Download and extract the ZIP. Replace YOUR_SIAPI_API_KEY with your key, then save each file to the path below. Merge these fields into an existing file, preserving other providers, permissions and preferences. Do not replace an existing configuration wholesale.

Configuration location: ~/.hermes

config.yaml

Save to: ~/.hermes/config.yaml

Merge these fields into an existing file, preserving other providers, permissions and preferences. Do not replace an existing configuration wholesale. Merge agent.reasoning_overrides and model_overrides as well as providers and model. The reasoning overrides set per-model starting efforts; model_overrides prevents Hermes from inventing a Medium effort for MiniMax M3.1. The providers.siapi.models entries register model names. For a named profile, edit that profile’s config.yaml instead. Remove a stale model.base_url pointing to another provider.

View or copy configuration

config.yaml

Download

providers:
  siapi:
    name: SI-API
    api: https://siapi.ai/v1
    key_env: SIAPI_API_KEY
    transport: chat_completions
    default_model: deepseek-flash
    models:
      glm-5.3-flash: {}
      deepseek-flash: {}
      kimi-k3.1-pro: {}
      kimi-k3.1-pro-highspeed: {}
      glm-5.3: {}
      minimax-m3.1: {}
      qwen3.8-max: {}

agent:
  reasoning_overrides:
    "glm-5.3-flash": "max"
    "deepseek-flash": "high"
    "kimi-k3.1-pro": "max"
    "kimi-k3.1-pro-highspeed": "max"
    "glm-5.3": "max"
    "qwen3.8-max": "xhigh"

model_overrides:
  custom:
    minimax-m3.1:
      supports_reasoning: false

model:
  provider: custom:siapi
  default: deepseek-flash

.env.example

Save to: ~/.hermes/.env

Add this line to the active profile’s .env and replace the placeholder locally. Preserve other entries.

View or copy configuration

.env.example

Download

SIAPI_API_KEY=YOUR_SIAPI_API_KEY

3. Start your Agent

Start a new session and send a message. The startup model is deepseek-flash.

Start your Agent

hermes

4. Switch between all models

After setup, choose any model below inside your Agent. The same key and configuration work for all seven models; no new download or connection is needed.

All 7 models in this Agent configuration
Model / API ID	Command / picker path	Thinking settings
GLM 5.3 Flash `glm-5.3-flash`	`/model custom:siapi:glm-5.3-flash`	Low, High and Max. Thinking is always enabled; choose Low for less reasoning. The model default is Max.
DeepSeek V4.1 Flash `deepseek-flash`	`/model custom:siapi:deepseek-flash`	Off, Low, High and Max. Medium / XHigh map to High; Ultra maps to Max.
Kimi K3.1 Pro `kimi-k3.1-pro`	`/model custom:siapi:kimi-k3.1-pro`	Low, High and Max. Thinking is always enabled; choose Low for less reasoning. The model default is Max.
Kimi K3.1 Pro HighSpeed `kimi-k3.1-pro-highspeed`	`/model custom:siapi:kimi-k3.1-pro-highspeed`	Low, High and Max. Thinking is always enabled; choose Low for less reasoning. The model default is Max.
GLM 5.3 `glm-5.3`	`/model custom:siapi:glm-5.3`	Low, High and Max. Thinking is always enabled; choose Low for less reasoning. The model default is Max.
MiniMax M3.1 Flash `minimax-m3.1`	`/model custom:siapi:minimax-m3.1`	Use the model default. This route does not expose custom thinking controls.
Qwen3.8 Max `qwen3.8-max`	`/model custom:siapi:qwen3.8-max`	Off, Low, Medium and XHigh. High / Max map to XHigh, not additional levels.

5. Choose reasoning effort

Send each command separately inside your Agent. On DeepSeek V4.1 Flash, switch from Low to High before your next message.

Inside your Agent

/reasoning low
/reasoning high

Available effort levels depend on the model; see the table above. MiniMax M3.1 Flash uses its model default.

Effort defaults and saved settings

Start on DeepSeek V4.1 Flash. Choose Low, send a short file-reading task, then choose High and repeat. Check the current setting after each change.

Effort means how much reasoning to request. Kimi K3.1 Pro / HighSpeed, 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.

MiniMax M3.1 Flash uses its default reasoning behavior. MiniMax M3 settings apply to a different model.

The supplied agent.reasoning_overrides set a legal starting effort for every model with declared controls. 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 K3.1 Pro / HighSpeed 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.

Inside the Agent · send each command separately

/reasoning
/reasoning low
/reasoning
/reasoning high
/reasoning
/reasoning low

Check 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.

Expected: On DeepSeek V4.1 Flash, the current setting changes from Low to High and back to Low before your next message. Other models follow the controls listed below.

Hermes reasoning controls ↗

Check the model and run your first task

Open a project containing README.md. Allow the tool to read it, then send the prompt below. Confirm that it reads the file and returns a summary. To check another model, switch using the table above and repeat this task.

Inside your tool

/model

Send this task in your tool

Use the file-reading tool to read README.md in this project and summarize its purpose in one sentence. Do not modify any files.

Tool-specific notes

CLI and Desktop must select the same profile. Check the displayed provider before sending a task.
Search is configured separately in Hermes tool settings. Review auxiliary models and fallback providers if you want those requests to use SI-API too.

Official configuration reference ↗ · Model configuration

Connection not working? · Usage

Agent compatibility — Client versions, tested reasoning fields and known limits.

Download setup instructions