theopenco

One API for every model — and the products we build on top of it

Website · Models · Providers · Pricing · Docs · Status · Changelog

We build open-source infrastructure for the multi-model era. One OpenAI-compatible endpoint routes to every major provider with smart routing, automatic fallback, caching, cost analytics and guardrails. DevPass brings it to coding agents, Lounge brings it to everyday creative work, and Airside lets providers bring their APIs onto the network.

flowchart LR
	A["DevPass<br/>coding agents &amp; editors"] --> G
	B["Lounge<br/>chat &amp; studios"] --> G
	C["Your app<br/>SDKs · CLI · MCP"] --> G
	D["Clanker Support<br/>AI support widget"] --> G
	G["<b>LLM Gateway</b><br/>routing · fallback · caching · analytics"] --> P[("Models &amp; providers")]
	E["Airside<br/>provider console"] -. approved listings .-> P

One endpoint in front of every model. Point the OpenAI SDK at us, change the base URL, and you're done — no rewrites, no per-provider glue code. Requests retry transparently on a healthy provider when one degrades, and every token lands in your usage dashboard.

• Build across modalities — OpenAI-compatible chat, streaming, tools, structured output and vision, plus image, video and audio APIs
• Smart routing & fallback — choose providers by cost, latency or throughput, with retries across eligible providers
• Cost-aware analytics — spend, tokens, cache hits and errors broken down by model, provider and project
• Pay at provider rates — flat 5% platform fee on credits, or free with your own keys (BYOK)
• Organization controls — budgets and access policies, with enterprise SSO, audit logs and compliance controls
• Run it yourself — AGPL-3.0 core, with Docker, Docker Compose and Kubernetes deployment guides

curl https://api.llmgateway.io/v1/chat/completions \
  -H "Authorization: Bearer $LLM_GATEWAY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "auto",
    "messages": [{ "role": "user", "content": "Hello!" }]
  }'

One subscription for your AI coding tools. Use DevPass Code, our terminal agent, or connect a supported editor or coding agent with the same DevPass key. Usage is metered at provider rates against your plan allowance, with automatic provider routing and optional pay-as-you-go overflow. See the current plans and limits for allowances and fair-use rules.

pnpm add -g devpass-code   # or: brew install theopenco/tap/devpass-code
devpass-code auth login # opens your browser — no keys to copy, models built in

→ devpass.llmgateway.io · DevPass Code repo · setup guide

Your models and creative studios in one place. Switch models mid-conversation, compare their answers in group chat, and generate images, video and speech. Projects keep your knowledge together; canvas, voice and reusable skills extend the workspace. Start with pay-as-you-go credits or choose a membership.

→ lounge.llmgateway.io

Bring your LLM API onto LLM Gateway. Airside is the self-serve console for model providers. Verify your company domain, claim an existing provider or register a new one, and submit your models for review.

• Manage your fleet — list models, declare capabilities and run preflight checks against your endpoint.
• File your pricing — submit launch prices, regional rates and later changes for approval before they take effect.
• Track your service — monitor requests, tokens and errors by model, and investigate incidents.
• Tune your offering — submit traffic discounts and gateway margin changes for review, and invite your team to manage the provider together.

Approved listings become available through the same API developers already use. See listing fees and terms before registering.

→ airside.llmgateway.io · provider guide

• VS Code extension — use gateway models in VS Code chat and agent mode, including with a DevPass key.
• CLI — launch coding agents, scaffold projects, discover models and manage keys, budgets and usage.
• MCP server — give assistants access to account analytics, model discovery, text and image generation.
• Vercel AI SDK provider — integrate the gateway into AI SDK applications.

The LLM Gateway core is AGPL-3.0; companion repositories publish their own licenses. Enterprise features under ee/ are commercially licensed — get in touch.