# Pi · 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 Pi from its official page. Create or copy your SI-API key from /keys. export SIAPI_API_KEY="YOUR_SIAPI_API_KEY" ## 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: ~/.config/siapi/pi ## 3. Start your Agent Start a new session and send a message. The startup model is deepseek-flash. PI_CODING_AGENT_DIR="$HOME/.config/siapi/pi" pi --provider siapi --model deepseek-flash ## 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 → SI-API → GLM 5.3 Flash (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 → SI-API → DeepSeek V4.1 Flash (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 → SI-API → Kimi K3.1 Pro (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 → SI-API → Kimi K3.1 Pro HighSpeed (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 → SI-API → GLM 5.3 (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 → SI-API → MiniMax M3.1 Flash (minimax-m3.1) Thinking settings: Use the model default. This route does not expose custom thinking controls. ### Qwen3.8 Max · qwen3.8-max /model → SI-API → Qwen3.8 Max (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 /thinking ``` 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. Save both supplied files. settings.json uses modelThinkingLevels to set High for DeepSeek, Max for Kimi and GLM, XHigh for Qwen. models.json declares which choices are available; it does not set these defaults. Open /thinking and choose Low or High, or use Shift+Tab to cycle supported levels. The footer shows the active level. This changes the session; Ctrl+S saves the global fallback. Per-model defaults take precedence over that fallback: edit modelThinkingLevels or use /settings → Default thinking level per model to change them. Ctrl+T only shows or hides reasoning text. ### Inside the Agent · send each command separately ```text /model /thinking ``` - If the selector is missing, confirm that Pi loaded the supplied models.json from the same PI_CODING_AGENT_DIR. Supported models need reasoning: true and the complete thinkingLevelMap. Null entries remove unsupported levels; do not delete them. Open /model to reload the file, then inspect /thinking again. 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. Pi custom reasoning capabilities: https://github.com/earendil-works/pi/blob/main/packages/coding-agent/docs/models.md ## 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 /thinking Use the file-reading tool to read README.md in this project and summarize its purpose in one sentence. Do not modify any files. ## models.json Save to: ~/.config/siapi/pi/models.json Save in the dedicated Pi directory. Keep reasoning, thinkingLevelMap and compat fields, including null entries that disable unsupported levels. Save settings.json alongside it for per-model effort defaults. Keep existing providers if this file already exists. ## settings.json Save to: ~/.config/siapi/pi/settings.json Merge these fields into an existing file, preserving other providers, permissions and preferences. Do not replace an existing configuration wholesale. modelThinkingLevels sets the starting effort for each model; models.json separately declares its available choices. Save both files in the same PI_CODING_AGENT_DIR. ## Notes Pi runs in your terminal, including an editor’s integrated terminal. There is no separate Desktop configuration here. Opening /model reloads models.json. Use /thinking for the session; settings.json holds startup defaults. Unsupported thinking levels are disabled in the model mapping. Off, Low, High and Max. Medium / XHigh map to High; Ultra maps to Max. Reference: https://github.com/earendil-works/pi/blob/main/packages/coding-agent/docs/models.md Model configuration: https://siapi.ai/docs/models#configuration Agent compatibility: https://siapi.ai/docs/compatibility