Now in Public Beta

One Gateway for
Every LLM

Route, observe, cache, and orchestrate all your LLM calls through a single intelligent control plane. Connect any provider. Ship faster.

Start Building — Free See How It Works

No credit card required · 5,000 free credits/month

Just change your base URL — that's it

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://gateway.phthos.ai/v1",  // ← swap in Phthos
  apiKey:  "pk_your_api_key",
});

const res = await client.chat.completions.create({
  model: "my-gpt4o-router",   // routes to cheapest provider
  messages: [{ role: "user", content: "Hello!" }],
});

Works with every LLM provider

OpenAIAnthropicGoogle GeminiMistralGroqAzureAWS BedrockOllama

Everything you need to
ship LLM apps

From prototype to production. One platform, zero lock-in.

⚡

Multi-Provider Gateway

OpenAI-compatible API. Route across OpenAI, Anthropic, Gemini, Groq, and more.

🧠

Smart Caching

Exact and semantic response caching to cut latency and provider spend.

📚

RAG & Vector Stores

Ingest documents, search vectors, and ground model answers in your data.

🤖

Agent Workflows

Orchestrate tools, memory, and models — usage metered per operation, not per flow.

Simple, credit-based pricing

Paid plans unlock features. Usage is metered in credits at each leaf operation — cache hits are free.

Free

For solo developers and prototypes

$0 /month

✓ 5,000 credits/month
✓ 2 LLM providers
✓ Basic request logging (7-day retention)
✓ 1 RAG & vector store
✓ 1 user
✓ Community support

Get Started Free

Growth

For beginners and small teams

$20 /month

✓ 50,000 credits/month
✓ All LLM providers & models
✓ Full observability (14-day retention)
✓ Exact response caching
✓ Routers & aliases
✓ Unlimited agent workflows
✓ Unlimited RAG & vector stores
✓ 5 users
✓ Email support

Start Growth Plan

Pro

For teams shipping to production

$50 /month

✓ 500,000 credits/month
✓ All LLM providers & models
✓ Full observability (30-day retention)
✓ Semantic + exact caching
✓ Smart routers & aliases
✓ Unlimited agent workflows
✓ Unlimited RAG & vector stores
✓ Unlimited users
✓ Priority support

Start Pro Plan

Enterprise

For organizations at scale

$200 /month

✓ Custom included credits
✓ All LLM providers & models
✓ Full observability (3-month retention)
✓ Semantic + exact caching
✓ Smart routers & aliases
✓ Unlimited agent workflows
✓ Unlimited RAG & vector stores
✓ Unlimited users
✓ Priority support & SLA

Start Enterprise Plan

Metering

Credit costs

Credits debited per leaf operation — not per agent run. Paid plans unlock features; cache hits are free.

Model call (chat completion) 1

Embedding model callStandalone /v1/embeddings only 1

Vector DB searchQuery embedding + similarity search (one charge) 1

Memory read / write 1

Cache read (exact or semantic) Free

RAG queryVector search + model call 2

Vector ingestEmbedding + vector DB write 2

Agent workflow run1 each: model, embedding, vector, memory · cache hits free · RAG/ingest use bundled rates · no flat run fee Per step

All plans include OpenAI-compatible API, multi-tenant workspaces, and encrypted API key storage. Usage beyond included credits stops until the next period. Prices in USD.

One Gateway forEvery LLM

Everything you need toship LLM apps