# OpenClaw · SI-API All 7 SI-API models · one Agent setup Default startup model: deepseek-flash Surface: cli System: macos Included models: GLM 5.3 Flash (glm-5.3-flash), DeepSeek V4.1 Flash (deepseek-flash), Kimi K3.1 Pro (kimi-k3.1-pro), Kimi K3.1 Pro HighSpeed (kimi-k3.1-pro-highspeed), GLM 5.3 (glm-5.3), MiniMax M3.1 Flash (minimax-m3.1), Qwen3.8 Max (qwen3.8-max). Templates contain placeholders only. Save your real key locally. Keep unrelated settings and permissions. ## 1. Prepare your tool and key Install OpenClaw from its official page. Create or copy your SI-API key from /keys. Save the configuration and key on the machine running your OpenClaw Gateway, not just the browser opening the Control UI. ## 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: ~/.openclaw ## 3. Start your Agent Start a new session and send a message. The startup model is deepseek-flash. openclaw gateway restart openclaw models set siapi/deepseek-flash openclaw tui ## 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. ### GLM 5.3 Flash · glm-5.3-flash /model siapi/glm-5.3-flash Thinking settings: 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 siapi/deepseek-flash Thinking settings: Off, Low, High and Max. Medium / XHigh map to High; Ultra maps to Max. ### Kimi K3.1 Pro · kimi-k3.1-pro /model siapi/kimi-k3.1-pro Thinking settings: 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 siapi/kimi-k3.1-pro-highspeed Thinking settings: 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 siapi/glm-5.3 Thinking settings: 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 siapi/minimax-m3.1 Thinking settings: Use the model default. This route does not expose custom thinking controls. ### Qwen3.8 Max · qwen3.8-max /model siapi/qwen3.8-max Thinking settings: 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 ```text /think low /think high ``` 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 agents.defaults.models entries set params.thinking separately for each supported model: High for DeepSeek, Max for Kimi and GLM, XHigh for Qwen. These defaults are separate from thinkingLevelMap, where null disables an unsupported choice. Send /think low or /think high as a message by itself to change the saved session setting. /think reports the current level; /status shows the requested and effective settings. Send /think default to clear the session override and inherit the configured default. It does not ask the upstream model to choose a default. Per-agent defaults can still override the shared model settings. The TUI uses the same local OpenClaw Gateway configuration as the browser Control UI. Recheck /think after changing models or resuming a saved session. ### Inside the Agent · send each command separately ```text /think /think low /status /think high /status /think low ``` - Restart the local OpenClaw Gateway after updating reasoning, thinkingLevelMap or compat. Higher levels need the supplied supportedReasoningEfforts declaration. Off must map to none; omitting effort does not guarantee thinking is disabled. Agent-specific defaults and session overrides can supersede shared model settings. 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. OpenClaw thinking levels and custom endpoints: https://docs.openclaw.ai/tools/thinking ## 6. 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. /model Use the file-reading tool to read README.md in this project and summarize its purpose in one sentence. Do not modify any files. ## openclaw.json Save to: ~/.openclaw/openclaw.json Merge these fields into an existing file, preserving other providers, permissions and preferences. Do not replace an existing configuration wholesale. Preserve agents.defaults.models entries with params.thinking: these supply per-model starting efforts. The provider’s thinkingLevelMap and compat.supportedReasoningEfforts declare the available choices. ## .env.example Save to: ~/.openclaw/.env Add the key to the Gateway’s .env, including when it runs as a background service. ## Notes The model allowlist includes all seven SI-API models. Existing per-agent model choices can override the default. Restart an already installed Gateway after editing its environment. Use the official onboarding guide first if the Gateway has not been installed. Off, Low, High and Max. Medium / XHigh map to High; Ultra maps to Max. Reference: https://docs.openclaw.ai/concepts/model-providers/custom-providers Model configuration: https://siapi.ai/docs/models#configuration Agent compatibility: https://siapi.ai/docs/compatibility