🎉 National Day referral · 10% off + 10% API credit · inviter earns 10% Invite →

Choose the plan that fits your work

For individual development, team collaboration and API integration.

All subscription models · Claude / GPT / Gemini / Grok · A predictable monthly fee

Pro

For everyday individual development

59¥/mo

For code completion, debugging and daily iteration.

≈ $8 USD/mo

Get started with Pro

Everything you need to get started:

  • All models in the subscription catalog, including Claude, GPT, Gemini and Grok
  • Connect Claude Code, Codex CLI and compatible clients
  • OpenAI and Anthropic API compatibility
  • Streaming responses and multi-turn conversations
  • Unlimited API keys, organized by project
  • View usage and allowance reset times

Max

Recommended

For developers who work with AI throughout the day

259¥/mo

For sustained coding, multiple projects and frequent iteration.

≈ $36 USD/mo

Get started with Max

Everything in Pro, plus:

  • More development capacity for everyday intensive AI use
  • Sustained coding, multiple projects and frequent iteration
  • Designed for code reviews, refactoring and multi-step development
  • Priority technical support

Plan allowances reset periodically. Usage varies by model, context length and task complexity. View your usage and allowance reset times in the console.

TRIAL
¥1 one-time

Trial — try before subscribing

One-time allowance · subscription models listed below · try before subscribing

Models included in every plan

Every plan can use the models below within its shared allowance. Usage varies with context length and task complexity; there is no additional per-token subscription charge.

Claude series

The primary lineup for Claude Code — latest flagship included

claude-haiku-5-5 claude-sonnet-5-5 claude-opus-5-5 claude-opus-5 claude-fable-5-2 claude-fable-5-1 claude-fable-5 claude-opus-4-8 claude-opus-4-7 claude-sonnet-5 claude-sonnet-4-6 claude-haiku-4-5-20251001

Use an exact model ID from this list in the model field of Claude Code or your SDK.

GPT series

gpt-6.1-sol gpt-6-astra gpt-6-sol gpt-6-luna gpt-5.6-sol gpt-5.6-terra gpt-5.6-luna gpt-5.6-codex gpt-5.5 gpt-5.4 gpt-5.4-mini

Gemini

gemini-4-argon gemini-3.8-flash gemini-3.7-flash gemini-3.6-flash gemini-3.5-flash-lite gemini-3.1-pro-preview gemini-3.5-flash gemini-3.1-flash-lite

Text chat models

Grok

grok-4.7 grok-4.6 grok-4.5 grok-4.3 grok-4.2 grok-4.1 grok-4 grok-4-fast grok-3

Text chat models

The authoritative list of subscription-available models is returned by GET /v1/models on the gateway.

A quick note about subscription plans

Subscription plans combine capacity from IDE-plan relays and promotional resource channels to keep monthly costs accessible. Upstream load and policy changes may occasionally affect model quality, speed or availability, so this mode is best suited to everyday coding and general tasks. If consistent peak quality and stability matter most to you, API billing with a premium or direct channel may be a better fit.

We continue to invest in the subscription service and work hard to keep its channels stable, reliable and highly available. If you run into any issue, email support@llmapi.pro and we will assist you as soon as possible.

Usage allowance: Subscription usage depends on the model, context length, cache use, output size and task complexity. Long text and multi-step tool workflows typically use more allowance. Check your dashboard for actual usage and reset times. Failed requests consume no allowance, and internal web searches carry no additional subscription quota charge.

After purchase: Subscriptions are non-refundable. If your needs change, contact support to convert the remaining eligible value to API billing balance under the applicable rules.

Compare API billing channels →

One-click setup

Works with all Claude Code terminals and IDE plugins

irm llmapi.pro/setup.ps1 | iex

FAQ

Which models can I use with a subscription? Is everything in the model catalog included?

Your subscription covers the exact model IDs in the live list above, sharing the same plan quota. For other models, check the billing-mode labels on /all-models and the channel catalogue on /channels. API billing uses a separate key and balance. The subscription list is synchronized with GET /v1/models.

How is this different from official Claude?

LLM API is an independent API relay. Configure Claude Code with the documented base URL and API key. Available models, usage limits and service performance depend on the billing mode and current channels; review the model list and usage notes on this page.

What happens if I upgrade from Pro to Max?

The upgrade takes effect immediately. The unused portion of your current plan is converted into a prorated credit and applied directly to the amount due for the new plan. The new plan starts a fresh full term on the upgrade date. Because the previous plan has already been converted into credit, its remaining time is not restored when the new plan expires. If no other plan is active then, the account returns to Free.

How do subscription usage limits work?

Subscriptions include a usage allowance with 5-hour and weekly limits; usage is not unlimited. Context length, output size and task complexity affect consumption. When either allowance is exhausted, wait for its reset. No automatic subscription overage charges apply.

What affects subscription usage?

Subscription usage depends on the model, context length, cache use, output size and task complexity. Long text and multi-step tool workflows typically use more allowance. Check your dashboard for actual usage and reset times. Failed requests consume no allowance, and internal web searches carry no additional subscription quota charge.

Usage varies with your tasks:

  • Everyday questions, code completion and small edits typically use less allowance.
  • Long context, larger outputs and multi-step agent tasks use allowance more quickly.

Choose a plan for your workflow:

  • Pro: Everyday development for individuals
  • Max: Intensive development
  • Ultra: Enterprise development and team collaboration

Paid subscriptions use separate fixed 5-hour and 7-day windows, timed from each window’s start. Usage for a window resets when it expires, and the next call opens a new window. Check the Console or usage API for your reset times. If either window has insufficient quota, further calls can receive a 429 rate-limit response. Failed requests consume no quota, and subscription overage charges are not added automatically.

Can I get an invoice (VAT special invoice / fapiao)?

Yes. Both subscription orders and API pay-as-you-go top-ups can be invoiced with a VAT special invoice (专票), line item "Technical Services". Corporate payment, contracts/agreements, and detailed order or usage statements are also available for universities, labs, project teams and other reimbursable purchases.

How to configure Claude Code?

Two steps:
export ANTHROPIC_BASE_URL=https://llmapi.pro
export ANTHROPIC_API_KEY=your_key
Then run normally claude That's it.