API subscriptions from CNY 59/month · Metered option

Subscribe monthly, build across models.

API subscriptions for Claude Code, Codex CLI and compatible clients, from CNY 59/month. A fixed monthly fee includes shared model usage for everyday development, intensive coding and team collaboration. Pay-as-you-go API billing is available separately.

LLMAPI is an independent multi-model API relay with monthly subscriptions, metered API billing and client setup guides. About LLMAPI · API relay selection guide (Chinese)

Claude Code / Anthropic API OpenAI SDK / Codex CLI Gemini API / SDK
Fixed monthly fee Shared model quota Separate metered option
Configure Claude Code in One Click

# one command, fully configured

PS> irm llmapi.pro/setup.ps1 | iex

# or two env vars, manually

$ export ANTHROPIC_BASE_URL=https://llmapi.pro

$ export ANTHROPIC_API_KEY=your-key

$ claude

Works with all Claude Code terminals and IDE plugins

Claude◆ GPT◆ Gemini◆ DeepSeek◆ GLM◆ Qwen◆ Kimi◆ MiniMax◆ Grok◆ Anthropic Protocol◆ OpenAI SDK◆ Codex CLI◆ Gemini Protocol◆ Claude◆ GPT◆ Gemini◆ DeepSeek◆ GLM◆ Qwen◆ Kimi◆ MiniMax◆ Grok◆ Anthropic Protocol◆ OpenAI SDK◆ Codex CLI◆ Gemini Protocol◆

MINIMAX H3 · 40% off official list prices

Turn your ideas into moving images.

H3 text and keyframe video generation: 768P at ¥0.30/s, 2K at ¥0.48/s. Seedance Mini and Standard are also available with separate model pricing.

Create a video →

Learn from examples → · Video pricing →

Boss Arrival: Stealing the Whole Cart

01 — Models

Choose Models by Billing Mode

Check available model IDs, billing modes and channel prices in the catalogue.

OpenAI GPT

OpenAI GPT

All-round · Codex coding agents

gpt-5.6 · codex
Google Gemini

Google Gemini

Multimodal · long context

gemini-3.1-pro · flash
DeepSeek

DeepSeek

Best value

GLM

GLM

Domestic flagship

Qwen

Qwen

Tongyi lineup

Kimi

Kimi

Long context

MiniMax

MiniMax

Fast multimodal

Grok

Realtime

Image

Per request

02 — Billing

A monthly plan. Shared model quota.

Plan your ongoing development usage with a subscription, or use a separate metered balance for other API calls.

Subscription

Fixed monthly price · plan usage limits

¥59from / mo
  • Fixed monthly price with an included usage allowance
  • Available subscription models share one quota; see the live plan list
  • Cross-device Remote Session
View plans

Metered API

Usage-based channel pricing

Top up & go
  • Balance never expires — no monthly fee
  • See the channel catalogue for available models and features
  • Transparent pricing: channels, multipliers and rates published live

03 — Before you connect

Plan your multi-model setup

Choose a billing mode

Subscriptions use fixed monthly plans with usage quotas. Metered API calls use a separate balance and channel prices.

Understand usage limits

A fixed monthly fee with 5-hour and weekly allowances. Check usage and reset times in your dashboard.

Check client compatibility

Choose a supported endpoint and model ID for your client, then test the tools and features your workflow needs.

Compare plans and follow the setup guides below.

04 — How It Works

Get started in three steps

Create an account, configure your client and test a request.

1

Sign up

Create an account, choose a billing mode and create the corresponding API key in your dashboard.

2

Configure your client

Use the endpoint and API key settings in the guide for your client and billing mode.

3

Test your setup

Start with a small request, confirm the model and tool behavior, then check usage in your dashboard.

terminal

# Point your client at LLM API

$ export ANTHROPIC_BASE_URL=https://llmapi.pro

$ export ANTHROPIC_API_KEY=your-key

# That's it. Start coding.

$ claude

05 — Included

Tools for your workflow

Setup and usage tools for Claude Code, Codex CLI and supported SDKs.

Documented API endpoints

Choose the documented Anthropic-, OpenAI- or Gemini-compatible endpoint for your client. Supported features depend on the model and channel.

Remote Session

Use the Remote Session setup guide to connect to a running Claude Code session from another device.

Usage Dashboard

Track tokens, monitor costs, manage API keys. All in one place.

Availability and failover

Automatic failover helps handle channel failures. Availability can vary with upstream load; check the status page for current service health.

06 — Why Us

Why LLM API

Clear subscription pricing

Pro starts at CNY 59/month with an included usage allowance. Pay-as-you-go API billing uses a separate balance, with prices listed by channel.

Availability and failover

Multi-node load balancing and automatic failover help handle channel availability changes. Speed and availability can vary with upstream load; the status page shows current service health.

Client setup guides

Follow the setup guide for your client, choose the correct billing mode, and configure its base URL and API key. Subscription plans are priced in CNY and support Alipay and WeChat Pay.

07 — Billing

Choose a plan for your workflow

Compare fixed monthly plans and their usage quotas. Metered API billing is also available separately.

Trial

¥1

One-time trial allowance

Get Started

Pro

¥59/mo

Everyday development for individuals

Get Started

Ultra

¥979/mo

Enterprise development and team collaboration

Get Started

08 — FAQ

FAQ

What kind of service is LLM API?
LLM API is an independent multi-model API relay and is not affiliated with model vendors. Available model IDs, features and usage limits depend on your billing mode and selected channel. Review the model catalogue and client setup guides before connecting.
How do I check tool compatibility?
Follow the guide for your client and choose a model that supports the features you need. Tool calling, streaming and other behavior can vary by model, channel and client version, so test a small representative task before broader use.
How do subscriptions and metered API billing differ?
Subscriptions have a fixed monthly fee and an included allowance with 5-hour and weekly limits. Metered API billing uses a separate key and balance, with prices shown by channel. Choose based on your development needs and expected usage.
Can I switch back to a provider directly?
Yes. Restore the endpoint and credentials required by your client and chosen provider. For Claude Code, review both the ANTHROPIC_BASE_URL setting and your authentication configuration; an LLM API key is not an official provider credential.
How is request data handled?
Requests pass through LLM API and the selected upstream provider. Usage metadata is retained for billing and statistics; request and response content may be retained for security, dispute resolution and troubleshooting under the privacy policy. Review that policy and the upstream provider’s terms before submitting sensitive data. Privacy →

Choose your plan. Start building.

Check available models and plan limits, then follow the setup guide for your client.