Route, observe, cache, and orchestrate all your LLM calls through a single control plane. Connect any provider. Ship faster.
No credit card · 5,000 Gateway credits/month · billed on console.phthos.ai
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://gateway.phthos.ai/v1",
apiKey: "pk_your_api_key",
});
Works with every LLM provider
OpenAI-compatible API. Route across OpenAI, Anthropic, Gemini, Groq, and more.
Exact and semantic response caching to cut latency and provider spend.
Ingest documents, search vectors, and ground model answers in your data.
Orchestrate tools, memory, and models — usage metered per operation, not per flow.
Paid plans unlock Gateway features. Usage is metered in Gateway credits. This is not Task AI or Eval billing.
$0/mo
$20/mo
$50/mo
Gateway usage
Debited on your Gateway account only. Cache hits are free.
Pay and track usage at console.phthos.ai/billing. Prices in USD.