LMllm.market
OpenAI-compatible API · PAYG · subscription quotas

One API.Active catalog.

A unified llm.market control plane for OpenAI-compatible API usage, PAYG wallet and subscription quotas.

Get startedView models
Catalog modelsOpenAI-compatibleUsage ledgerPAYGSubscriptionAPI keys
Catalog
Active models
OIDC
Chat identity
PAYG
Billing
OpenAI-compatible requestBash
curl -X POST https://llm.market/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{"model":"MODEL_FROM_V1_MODELS","messages":[{"role":"user","content":"Hello!"}],"stream":true}'
01

OpenAI-Compatible Endpoints

Drop-in /v1/chat/completions support.

02

Account Billing

Usage is reserved and settled at the account level.

03

Active Catalog

Use /v1/models to discover active model IDs.

Popular paths

Pick the client you actually use. llm.market works as a custom OpenAI-compatible API for coding agents, roleplay frontends, chat clients and CLI tools.

Coding Agents

Cursor, Cline, Roo Code, Kilo Code, OpenCode, Zed and more.

View guide

Roleplay Clients

SillyTavern, Janitor.AI, Chub and RisuAI.

View guide

Chat Clients

LibreChat, LobeChat, Open WebUI, Chatbox and generic OpenAI-compatible clients.

View guide

CLI Tools

OpenAI-compatible SDKs, OpenCode, Aider, and supported coding clients.

View guide
Subscription · 1-Month Pass

Simple, transparent pricing

Subscription quotas and PAYG are charged from the active catalog. Prices and availability are shown before checkout.

Display currency

Pro

Rolling request quota for individual workloads

$20.00/month
  • 500 units / 5 hours
  • 5,000 units / 7 days
  • OpenAI-compatible API
  • PAYG fallback when enabled
Choose Pro
MOST POPULAR

Max

Higher rolling quota for regular use

$100.00/month
  • 2,000 units / 5 hours
  • 20,000 units / 7 days
  • OpenAI-compatible API
  • PAYG fallback when enabled
Choose Max
BEST VALUE

Ultra

Highest current catalog quota

$300.00/month
  • 6,000 units / 5 hours
  • 60,000 units / 7 days
  • OpenAI-compatible API
  • PAYG fallback when enabled
Choose Ultra
View all pricing details
Zero-Downtime Architecture

Integrate in Seconds.
Scale to Infinity.

Fully OpenAI-compatible endpoints. Switch providers without changing your code. One API key for the supported public contract.

OpenAI-Compatible Endpoints

Drop-in /v1/chat/completions support for existing clients.

Automatic Provider Failover

Account-level quota and PAYG accounting run before forwarding.

Active Catalog

Use GET /v1/models to discover currently available models.

Read Full API Docs→
bash
curl -X POST https://llm.market/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "MODEL_FROM_V1_MODELS",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ],
    "stream": true
  }'

Streaming requests request a final usage frame for accurate billing.

Architecture

Always-On.
Reliable AI.

Requests pass through the active gateway and are attributed to your account for quota and PAYG accounting.

Unified Endpoint

One OpenAI-compatible API for supported chat requests.

1

Smart Routing

Routes through the active gateway and model catalog.

2

Automatic Failover

Usage and billing are recorded at the account level.

3
Account-aware

usage, quota, and PAYG controls

Active catalog only

Supported Formats

{
  "models": "GET /v1/models",
  "chat": "POST /v1/chat/completions",
  "responses": "POST /v1/responses"
}

Only listed endpoints are part of the public API contract.

Ready to build the future?

Use llm.market for chat, API keys, PAYG billing and subscription quotas.