Engy – Verified LLM Inference

poidos1 pts0 comments

engy · verified inference<br>Verified inference.<br>Verified inference means cryptographic proof that the exact open model you requested produced your output, not a cheaper or quantized stand-in. Run frontier open models like GLM-5.2 , billed by the token.<br>Create an account<br>Getting started<br>1. Claude Code<br>In ~/.claude/settings.json, then run claude:<br>"env": {<br>"ANTHROPIC_BASE_URL": "https://api.engy.ai",<br>"ANTHROPIC_AUTH_TOKEN": "$ENGY_API_KEY",<br>"ANTHROPIC_MODEL": "glm-5.2",<br>"ANTHROPIC_DEFAULT_HAIKU_MODEL": "glm-5.2"<br>}No /v1 on the URL; keep the haiku model set.<br>2. OpenAI API<br>curl https://api.engy.ai/v1/chat/completions \<br>-H "Authorization: Bearer $ENGY_API_KEY" \<br>-H "Content-Type: application/json" \<br>-d '{"model":"glm-5.2","messages":[{"role":"user","content":"hello"}]}'from openai import OpenAI<br>client = OpenAI(base_url="https://api.engy.ai/v1", api_key="$ENGY_API_KEY")<br>client.chat.completions.create(model="glm-5.2",<br>messages=[{"role":"user","content":"hello"}])3. Cursor<br>Cursor Settings → Models → API Keys, under OpenAI API Key :<br>OpenAI API Key $ENGY_API_KEY<br>Override OpenAI Base URL https://api.engy.ai/v1 ← enable the toggle, then VerifyUnder Models, + Add model → glm-5.2, enable it, and select it in chat. Custom endpoints drive the chat/plan panel; Tab and Composer stay on Cursor's own models. Requests are relayed by Cursor's servers, so it works from any machine. Needs a paid Cursor plan: on the free plan Cursor shows "Named models unavailable" for any custom model (free is Auto-only, that is Cursor's gating, not this API).<br>4. Codex<br>In ~/.codex/config.toml, then export ENGY_API_KEY=… and run codex:<br>model = "glm-5.2"<br>model_provider = "engy"

[model_providers.engy]<br>name = "engy"<br>base_url = "https://api.engy.ai/v1"<br>env_key = "ENGY_API_KEY"<br>wire_api = "responses"5. Hermes<br>In ~/.hermes/config.yaml, then run hermes chat:<br>model:<br>provider: "custom"<br>default: "glm-5.2"<br>base_url: "https://api.engy.ai/v1"<br>api_key: "$ENGY_API_KEY"

engy model engy_api_key openai cursor https

Related Articles