One Subscription. Unlimited Tokens, Every Major Model.
One key for the full Claude / GPT / Gemini / Grok chat lineup — works with Claude Code, Codex CLI and any SDK, plus exclusive Remote Session
Trial — taste everything first
40 requests · all models available · subscribe with confidence after you try
Pro
For getting started
≈ $8 USD/mo
- Unlimited tokens
- 500 weighted units / 5h · 2,500 / week
- 2 API keys
Max
For daily heavy use
≈ $36 USD/mo
- Unlimited tokens
- 2,000 weighted units / 5h · 10,000 / week
- 10 API keys
- Priority support
Ultra
For professionals & teams
≈ $137 USD/mo
- Unlimited tokens
- 6,000 weighted units / 5h · 40,000 / week
- 20 API keys
- All advanced features · per-key stats
Models included in every plan
Any plan tier can call all models below. They share the same token-weighted usage quota; long-context calls may consume multiple units, with no additional per-token charge.
Claude series — full lineup
The primary lineup for Claude Code — latest flagship included
Historical Opus / Sonnet / Haiku versions are also accepted. Model IDs go straight into the model field of Claude Code or any SDK.
GPT series
Gemini
Text chat models
Grok
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.
Weighted quota: Displayed figures are usage units rather than message counts. Roughly 10K processed tokens count as 1 unit, so longer contexts may use several units.
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.
One-click setup
Works with all Claude Code terminals and IDE plugins
irm llmapi.pro/setup.ps1 | iexcurl -fsSL llmapi.pro/setup.sh | bashFAQ
Which models can I use with a subscription? Is everything in the model catalog included?
A subscription covers the full list shown in "Models included in every plan" above: the entire Claude chat lineup (including claude-opus-5 and claude-fable-5) plus GPT / Gemini / Grok chat models, all sharing your plan quota. Models with -aws / -5x or -codex suffixes, GLM / DeepSeek direct-connect, and image/multimodal models are metered-API only and cannot be called with a subscription key — see the live catalogue on the API page (/channels). The authoritative list is returned by GET /v1/models.
How is this different from official Claude?
Your Claude Code experience is identical — same CLI, same tools, same workflow. We optimize backend infrastructure to dramatically reduce cost, and add exclusive features like Remote Session.
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.
Any catch with "unlimited tokens"?
We don't charge for or separately cap total token volume; instead we differentiate plans by a usage quota (5-hour and weekly rolling windows), weighted by the tokens each request processes (~1 per 10K tokens) — the same model as Claude Code's official subscription. Normal coding usage rarely hits any limit.
How is a "request" counted? How long does it last?
Quota is metered by usage, not a flat count of messages. A "request" is one API call from Claude Code to us, but how much it costs depends on the tokens processed that turn: roughly 1 per 10K tokens, a minimum of 1 for tiny requests, cached repeated context counted at 1/10, capped at 50 per request. Failed requests are never charged — timeouts, retries, and upstream errors (e.g. rate limits / 5xx) consume no quota; only requests that successfully return content count. This works the same way as Claude Code's official subscription — metered by token usage, with 5-hour and weekly windows. So a Claude Code request carrying a large 100K+ token context typically counts as 5–6, while a short Q&A counts as just 1.
Typical consumption patterns (for reference only; varies significantly based on task complexity):
- Simple Q&A / single edit: ~ 1
- Medium task (3–5 tool calls): ~ 2–4
- Large-context Claude Code (deep refactor / long session): ~per turn5–6 higher for big changes
Based on the 5-hour window:
- Pro (500 / 5h): Plenty for light-to-moderate daily use; ~1–1.5 hours of heavy Claude Code
- Max (2,000 / 5h): Comfortable for a full day of moderate coding; ~half a workday of heavy Claude Code
- Ultra (6,000 / 5h): Large teams / sustained multi-agent workloads
Quotas reset automatically on two independent rolling windows: 5-hour and 7-day. No overage charges, and failed requests are never counted — just wait for the next window. Claude Code will show a "rate limit" warning near the cap, then you're good to go again.
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 transfer, bank remittance, corporate Alipay and regular Alipay/WeChat payments are all supported.
How to configure Claude Code?
Two steps:export ANTHROPIC_BASE_URL=https://llmapi.proexport ANTHROPIC_API_KEY=your_key
Then run normally claude That's it.