What models are available?
What models are available?
Lightweight gives you access to 25+ models from OpenAI, Anthropic, Google, and xAI — all through a single API key. This includes GPT-5.4, Claude Opus 4.6, Gemini 3.1 Pro, Grok, and many more.Browse the full list on the Models page or call
GET /v1/models for the live catalog.Is the API OpenAI-compatible?
Is the API OpenAI-compatible?
Yes — 100% OpenAI-compatible. The primary endpoint is
POST /v1/chat/completions, which follows the exact same request and response format as the OpenAI API.Any tool, SDK, or library that works with OpenAI will work with Lightweight by simply changing the base URL and API key. No code changes, no wrapper libraries, no workaround flags.How do I check my usage?
How do I check my usage?
You can check your token usage and remaining quota in two ways:
- API: Call
GET /v1/usagewith your API key. - Dashboard: Visit the Lightweight Dashboard for a visual breakdown of your consumption.
What happens when I hit my rate limit?
What happens when I hit my rate limit?
You’ll receive a
429 Too Many Requests response. The response includes a Retry-After header that tells you exactly how many seconds to wait before retrying.Rate limits are per API key and measured in requests per minute (RPM). See Rate Limits for tier details.Does Lightweight support streaming?
Does Lightweight support streaming?
Yes. Add
"stream": true to your request body and the API will return server-sent events (SSE) — exactly like the OpenAI streaming format.Streaming works with every model in the catalog, regardless of provider.How do I get an invite / API key?
How do I get an invite / API key?
Lightweight is currently in beta. You can request access and get your API key from the Dashboard.Once approved, your key will start with
lw_sk_ and you can start making API calls immediately.