Set up OpenClaw

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 DeepSeek plan, then open Billing & API keys to copy your active key. OpenAI base: https://ds-api.savemytoken.com/v1. Claude Code base: https://ds-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. Make SAVEMYTOKEN_API_KEY available to the local OpenClaw Gateway process, including its service environment or private ~/.openclaw/.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.

{
  "models": {
    "mode": "merge",
    "providers": {
      "savemytoken-deepseek": {
        "baseUrl": "https://ds-api.savemytoken.com/v1",
        "apiKey": "${SAVEMYTOKEN_API_KEY}",
        "api": "openai-completions",
        "models": [
          {
            "id": "deepseek-flash",
            "name": "DeepSeek Flash",
            "input": [
              "text"
            ],
            "reasoning": true,
            "thinkingLevelMap": {
              "off": "none",
              "minimal": null,
              "low": "low",
              "medium": null,
              "high": "high",
              "xhigh": null,
              "max": "max"
            },
            "compat": {
              "supportsDeveloperRole": false,
              "supportsReasoningEffort": true,
              "supportedReasoningEfforts": [
                "none",
                "low",
                "high",
                "max"
              ],
              "reasoningEffortMap": {
                "off": "none"
              }
            }
          }
        ]
      }
    }
  },
  "agents": {
    "defaults": {
      "model": {
        "primary": "savemytoken-deepseek/deepseek-flash"
      },
      "models": {
        "savemytoken-deepseek/deepseek-flash": {
          "alias": "deepseek-flash",
          "params": {
            "thinking": "high"
          }
        }
      }
    }
  }
}

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.

openclaw models set savemytoken-deepseek/deepseek-flash
openclaw gateway restart
openclaw tui

Use /model in the TUI or the Control UI picker. Keep the custom provider and check agent-specific models, fallback models and saved sessions if it switches back.

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

Per-model params.thinking selects the default; reasoning, thinkingLevelMap and supportedReasoningEfforts describe available choices. Both parts are needed.

Use /think for the session and /status to verify it. /think default clears the session override and resolves defaults again. Off must map explicitly to none. Recheck after changing models or resuming an old session.

/think
/think low
/status
/think high
/status
/think default

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

The setup templates start with DeepSeek Flash. Add other delivered routes only after confirming their exact IDs and capabilities.

05 / DESKTOP

Browser Control UI

OpenClaw's browser Control UI connects to your local Gateway. Configure the provider on the host that runs that Gateway; entering a key in an unrelated shell does not change the service environment.

Restart the Gateway, open its dashboard, then choose the custom model and thinking control. The browser and TUI are two clients of that Gateway, not independent model providers.