Zyora Labs
Z-AI

One API key. Every LLM.

Z-AI is an OpenAI-compatible gateway in front of every major model provider. Stop juggling SDKs, keys and dashboards — point your app at one endpoint and switch models with a string.

Why Z-AI

Built for teams that ship to production, not just prototype.

8 providers behind one URL

OpenAI, Anthropic, Gemini, Groq, Mistral, Together, Fireworks and Nexula. 60+ models.

OpenAI-compatible API

Drop-in. Works with the official openai SDK, langchain, llamaindex, anything that speaks /v1/chat/completions.

One key, scoped per project

Issue, revoke, cap spend and pin allowed models per key. BYOK your provider credentials, encrypted at rest.

Streaming + fallbacks

SSE streaming on every model. Configure a fallback model per key when the primary is down.

Native dev tools

A CLI and a VS Code extension shipped on day one — chat, models, logs and spend from your terminal and editor.

Real observability

Every request logged with tokens, latency, cost, fallback hits. No black box.

Get going in 60 seconds
  1. Open Z-AI → API keys and create a key (starts with zk_live_…).
  2. In Providers, paste a provider API key (e.g. OpenAI). It is encrypted at rest with Fernet — never exposed in plaintext.
  3. Make your first call:
bash
curl https://api.zyoralabs.com/v1/chat/completions \
  -H "Authorization: Bearer zk_live_..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-5.4-mini",
    "messages": [{"role":"user","content":"Hello"}]
  }'

That request hits Z-AI, which calls OpenAI using your stored provider key, logs the request, deducts the cost, and returns the response.