# Codex · 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 Codex 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: ~/.codex ## 3. Start your Agent Start a new session and send a message. The startup model is deepseek-flash. codex --profile 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 Run /model, select an SI-API model, then choose its reasoning level. Repeat /model whenever you want to switch. ### Inside your Agent ```text /model ``` 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. Use /model, select DeepSeek V4.1 Flash, then choose the reasoning level. Open /status to inspect the current session. Repeat /model to change it without editing JSON. The catalog declares the available choices; it does not lock the session to a default. - The catalog supplies a separate default and supported list for every model. Remove an old model_reasoning_effort = "low" if you want these catalog defaults. A command-line -c override or saved task selection can still take precedence. 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. Codex model catalog and Desktop effort settings: https://api-docs.deepseek.com/quick_start/agent_integrations/codex/ ## 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. /status /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. ## siapi.config.toml Save to: ~/.codex/config.toml Merge these fields into an existing file, preserving other providers, permissions and preferences. Do not replace an existing configuration wholesale. Replace the catalog path with its actual absolute path. If CODEX_HOME is set, use that folder. ## siapi-models.json Save to: ~/.codex/siapi-models.json Save this model catalog beside config.toml. In config.toml, set model_catalog_json to this file’s full absolute path. Both files are required. ## Notes The CLI uses a dedicated siapi profile. Desktop reads the main config.toml, which also sets defaults for CLI runs without a profile. Desktop reads a private key file through auth.command so Dock and Start menu launches can authenticate. Do not combine command authentication with env_key or requires_openai_auth. Hosted web search is disabled. This configuration uses text and client-defined function tools; it does not enable image input or cloud tasks. Off, Low, High and Max. Medium / XHigh map to High; Ultra maps to Max. Reference: https://developers.openai.com/codex/config-reference/ Model configuration: https://siapi.ai/docs/models#configuration Agent compatibility: https://siapi.ai/docs/compatibility