Best balance of speed and intelligence. Production ready.
from anthropic import Anthropic
client = Anthropic(
base_url="https://claudeapi.cheap/api/proxy",
api_key="sk-cc-your-key-here",
)
msg = client.messages.create(
model="claude-sonnet-4-6",
max_tokens=1024,
messages=[{"role": "user", "content": "Hello!"}],
)
print(msg.content[0].text)from openai import OpenAI
client = OpenAI(
base_url="https://claudeapi.cheap/api/proxy/v1",
api_key="sk-cc-your-key-here",
)
resp = client.chat.completions.create(
model="claude-sonnet-4-6",
messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)curl https://claudeapi.cheap/api/proxy/v1/messages \
-H "x-api-key: sk-cc-your-key-here" \
-H "anthropic-version: 2023-06-01" \
-H "content-type: application/json" \
-d '{
"model": "claude-sonnet-4-6",
"max_tokens": 1024,
"messages": [{"role": "user", "content": "Hello!"}]
}'AI pair programming in your terminal — multi-file edits, git-aware, and aggressive about token use.
Anthropic's official terminal coding agent — the gold standard, but $200-1000/month if you let it loose on a real project.
The autonomous coding agent for VS Code that turned plan-and-act into a 1-click button — at the cost of your Anthropic invoice.
Open-source IDE assistant for VS Code and JetBrains — autocomplete, chat, edit, agent — all powered by your API key.
On the Pro plan ($19 lifetime), Claude Sonnet 4.6 is $0.60 per 1M input tokens and $3.00 per 1M output tokens. That's 80% off the official price ($3/$15). The Basic plan is free forever at 70% off.
Yes. The proxy forwards requests to the same underlying model with the same context window (200k tokens) and capabilities. Only vendor-fingerprint headers are stripped. Behavior, output quality, and reasoning are identical.
Change one line — the base URL — in your existing Anthropic or OpenAI SDK initialization. Use https://claudeapi.cheap/api/proxy for Anthropic-format calls or https://claudeapi.cheap/api/proxy/v1 for OpenAI-format. Use your sk-cc-... key as the API key. No code changes beyond that.
Pro plan caps at 500 requests/min and 2M tokens/min globally across all models. Basic plan is 200 RPM / 1M TPM. Newer models may have lower upstream caps that float — see /status for live availability.
Yes. Streaming, tool/function calling, and prompt caching all work end-to-end. Vision is supported where the upstream model supports it.
Free Basic plan, $19 lifetime Pro. Crypto only. No subscription.
Get an API key — free