# Claude API access, up to 90% off list price

> Markdown mirror of https://router.one/cheap-claude-api for AI assistants and crawlers. Router One is an OpenAI-compatible LLM API gateway.
> Last updated: 2026-08-26

Router One is an LLM API gateway that resells metered Claude API access at posted per-token rates — select Claude models go as low as 10% of official list prices (up to 90% off) — through the native /v1/messages endpoint (Claude Code works unchanged) and the OpenAI-compatible /v1/chat/completions, with a cost trace for every request and top-ups that need no US credit card. Every rate is posted per token on the /models page; same wire format, plus a ledger for every request.

## Up to 90% off, verifiable

Select Claude models run as low as 10% of official list prices. The /models page is the live price sheet — every rate shown struck through against its base rate. How the posted rate is set — and how upstream price changes flow through within 24 hours — is documented in the pricing methodology (last updated 2026-08-22): https://router.one/pricing-methodology

## Anthropic-native endpoint

Call /v1/messages in the native wire format (Claude Code connects directly), or use the OpenAI-compatible /v1/chat/completions — one key works for both.

## Pay without a US card

Top up with a card or Alipay through one hosted checkout, or with USDT/USDC on six chains. Wallet balance never expires; subscription plans are live for heavy usage.

## How the discount works

### Metered per token, prepaid wallet

You pay the discounted per-token rate shown on the model page — no seats, no minimum commitment. Wallet balance is drawn down per request.

### The catalog is the price sheet

Every Claude model lists its current input and output rates on /models, struck through against the base rate, so you can verify the discount before calling.

### Documented methodology

How Router One sources capacity and sets prices is written up on the pricing methodology page — no mystery meat.

## First Claude call in 3 steps

Create a key, top up in your currency, and call /v1/messages — the native Anthropic wire format, reachable from Mainland China without a VPN.

### Create an API key

Sign up at router.one and create a key in the dashboard. Top up with a card or Alipay in one hosted checkout, or with USDT/USDC — no US credit card required.

### Point your client at the gateway

Use https://api.router.one/v1/messages for the Anthropic-native format (Claude Code works out of the box), or https://api.router.one/v1/chat/completions for OpenAI-compatible clients.

### Verify the cost trace

Open Dashboard → Logs after your first request to see model, tokens, latency, and the exact discounted cost per call.

`claude-via-router-one.sh`

```bash
# Native Anthropic wire format via Router One
curl -X POST https://api.router.one/v1/messages \
  -H "Authorization: Bearer sk-your-router-one-key" \
  -H "Content-Type: application/json" \
  -d '{"model": "<claude-model-id>", "max_tokens": 1024,
       "messages": [{"role": "user", "content": "Hello!"}]}'
```

- No low fixed cap for normal paid usage. Abuse prevention, per-account protection limits, and upstream constraints may still apply; if a request returns 429, check Dashboard -> Logs or contact support to raise limits.

## FAQ

### Why is it cheaper than list price?

Router One aggregates demand across many customers and routes over pooled, committed capacity, then passes the margin down as discounted per-token rates. The approach is documented on the pricing methodology page; the /models page always shows the current effective rate.

### Is this the official Claude API?

Router One is an independent gateway, not Anthropic — requests are routed to language models operated by third-party providers, and the wire formats are identical (/v1/messages and OpenAI-compatible /v1/chat/completions). Model names and trademarks belong to their owners.

### Does Claude Code work with it?

Claude Code works natively with Router One: Claude Code speaks /v1/messages, which Router One implements. Set ANTHROPIC_BASE_URL to the gateway and use your Router One key; the Claude Code China guide walks through it in two minutes.

### Which Claude models are available?

The current lineup — Opus, Sonnet, and Haiku series — is listed on /models with live per-token pricing, context windows, and capabilities. Discount levels vary by model, so check the struck-through rates there.

### How do I keep spend predictable?

Every request writes a cost trace — model, tokens, latency, status, and what it cost — to Dashboard → Logs, and each API key can carry its own spend cap and rate limit. A runaway loop stops at the key instead of showing up on the invoice.

### Can I use it from Mainland China?

Yes. Based on the China latency benchmark last updated 2026-05-15, Router One measured 110-130ms p50 across Beijing, Shanghai, and Shenzhen; individual networks may vary.

## See also

- Claude Code in China: https://router.one/claude-code-china
- Cheap GPT API: https://router.one/cheap-gpt-api
- Messages API reference (POST /v1/messages): https://router.one/docs/chat/createMessage
- Claude Max alternative: https://router.one/claude-max-alternative
- China latency benchmark: https://router.one/benchmarks/china-latency
- Claude Code Token Costs: Why So High and How to Cap Them: https://router.one/blog/claude-code-token-costs-explained
- Canonical page: https://router.one/cheap-claude-api
- Models and per-model token rates: https://router.one/models (markdown: https://router.one/models.md)
- Pricing: https://router.one/pricing
- API docs (markdown): https://router.one/docs.md
- Company facts: https://router.one/facts/company.md