The Claude API,
redefined.
Same answers. A fraction of the price. Drop-in for everything Anthropic-shaped — Cursor, Cline, Claude Code, Continue.
Uptime · 24h
%
Avg latency
Users · 24h
Why AliCode
Three things we got right.
Pricing
85%
cheaper than retail
Same Claude model your code already knows. Pay a fraction of what Anthropic charges. No subscription. No minimum.
Speed
~30ms
gateway overhead
Streaming starts as fast as upstream. Token-by-token SSE delivery, identical to Anthropic's protocol.
Freedom
0
rate limits, ever
No per-minute caps. No daily quotas. Spin up 50 parallel agents — we won't blink.
30-second setup
Connect anything.
Point your tool at api.alicode.store with your key. Done.
.sh
# Cursor → Settings → Models → API Keys OpenAI API Key: sk-ali-••• Override Base URL: https://api.alicode.store/v1 # Custom model: claude-sonnet-4-5
# VS Code → Cline → ⚙ Settings API Provider: Anthropic API Key: sk-ali-••• Custom base URL: https://api.alicode.store Model ID: claude-sonnet-4-5
# Two env vars, one command export ANTHROPIC_BASE_URL=https://api.alicode.store export ANTHROPIC_API_KEY=sk-ali-••• claude
curl https://api.alicode.store/v1/messages \ -H 'x-api-key: sk-ali-•••' \ -H 'anthropic-version: 2023-06-01' \ -H 'content-type: application/json' \ -d '{ "model": "claude-sonnet-4-5", "max_tokens": 1024, "messages": [{"role":"user","content":"hi"}] }'
Same shape as Anthropic. Your code keeps working — only the endpoint changes.
Also works with
Pricing
Pay per token.
Top up from 300 ₽. Credits never expire. No subscription.
Fastest
Claude Haiku 4.5
Input
$0.80
/ 1M tokens
Output
$4.00
/ 1M tokens
- 200K context window
- Sub-second time to first token
- Built for fast agent loops
10× cheaper than Anthropic
Start →
Most popular
Balanced
Claude Sonnet 4.7
Input
$2.50
/ 1M tokens
Output
$12.00
/ 1M tokens
- 200K context window
- Best general-purpose coding
- Default model in Cursor & Cline
17× cheaper than Anthropic
Start →
Deepest
Claude Opus 4.8
Input
$3.00
/ 1M tokens
Output
$14.00
/ 1M tokens
- Extended thinking mode
- Hardest reasoning tasks
- Auto token-budget boost
30× cheaper than Anthropic
Start →
All prices per 1M tokens, USD. Batch API runs at 50% off these rates.
Prompt caching reads at 10% of input price.
Stop paying
retail for tokens.
Top up from 300 ₽. Pay only for what you use. Credits never expire.