Set up Hermes

01 / PREPARE

Install the agent and prepare access

1. Install the agent using its official guide. Check its version before merging the examples below.
2. Purchase your Multi-Model plan, then open Billing & API keys to copy your active key. OpenAI base: https://multi-api.savemytoken.com/v1. Claude Code base: https://multi-api.savemytoken.com. DeepSeek credentials are a separate scope.
3. Back up the file you will edit. Merge fields into existing objects and tables; preserve unrelated providers, tools and permission settings. Keep credentials in private local settings.
4. Image input is supported by seven routes; GLM-5.3 is text-only. Send JPEG, PNG, GIF or WebP images as Base64 or public HTTP(S) image URLs. The gateway accepts up to 20 images, 10 MiB per inline image and 20 MiB total inline image data per request.
5. Each image temporarily reserves 16,384 input tokens at the selected model's points rate. After completion, the reservation is replaced by the supplier's actual input and output token usage, including image tokens. Base64 characters are not billed as text tokens.
6. Add SAVEMYTOKEN_API_KEY=REPLACE_WITH_YOUR_DELIVERED_KEY to the active Hermes profile's private .env (normally ~/.hermes/.env).

Ready when: the agent opens, and you know which plan, process and configuration directory you will use.

02 / CONFIGURE

Save the connection and model catalog

Create the parent directories if needed. Download or copy each file, replace the example endpoint and local placeholders, then merge it into the stated location. Downloads and the examples below contain the same configuration.

providers:
  savemytoken-multi-model:
    name: SaveMyToken
    api: https://multi-api.savemytoken.com/v1
    key_env: SAVEMYTOKEN_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:savemytoken-multi-model
  default: deepseek-flash

Ready when: the files parse successfully and the selected profile points to the delivered URL, key reference and exact model catalog.

03 / START

Start the agent and choose your model

Open a terminal in a trusted project. Complete the file setup before running these commands.

hermes

Inside chat use /model custom:savemytoken-multi-model:deepseek-flash, or select another exact ID from the provider. Review auxiliary and fallback models separately.

Check: the provider is the one you configured and the selected model is deepseek-flash. A visible model list alone does not prove inference works.

04 / REASONING

Choose and verify reasoning effort

The supplied reasoning_overrides set a legal default for every model. Without these, a generic Medium default can be rejected by GLM and Kimi routes.

Use /reasoning to inspect the effective setting and its source. Session overrides and per-model defaults have separate precedence; check the result after each command and model switch. --global changes the fallback, not the per-model entries. Edit the matching reasoning_overrides entry for a persistent per-model change.

Show/hide commands only affect presentation. If a session command is shadowed by a per-model override, use the session-scoped control supported by your Hermes version or edit the model override and start a new session.

/model custom:savemytoken-multi-model:deepseek-flash
/reasoning
/reasoning low
/reasoning high

On DeepSeek Flash, choose Low, then High, then Low again. Inspect the active setting each time before sending the next message. A longer answer is not evidence that effort changed.

REASONING CONTROLS

Choose effort for the actual model

Use these exact gateway IDs. All eight models draw from the same points allowance. Image input support is listed per model below. Output is text or tool calls; audio and video input and media generation are not included.

05 / DESKTOP

Hermes Desktop · same profile

Choose the same Hermes profile in Desktop that owns config.yaml and .env. Select the custom provider and model, then inspect the thinking/effort control or reasoning pill.

Restart after configuration changes and check the effective effort. A terminal profile, Desktop profile and messaging gateway can have different active state.