Use CcHUB from your code
CcHUB exposes both Anthropic-compatible (/v1/messages) and OpenAI-compatible (/v1/chat/completions) endpoints backed by Claude on AWS Bedrock. Works with Anthropic SDK, OpenAI SDK, LangChain, Claude Code, Cursor, and more.
https://bedrock.cchub.africaAuthorization: Bearer sk-…Available models
| Model ID | Description | Cost multiplier | Max tokens |
|---|---|---|---|
claude-4-6-sonnet | Enhanced performance and capabilities | 3.5× | 8,000 |
claude-4-5-opus | Most capable, highest quality | 5× | 8,000 |
claude-4-6-opus | Most capable, highest quality | 5× | 8,000 |
Credit cost: (input_tokens + output_tokens × 5) × cost_multiplier × 1.2. Output tokens are 5× more expensive than input tokens.
Quickstart
Install the Anthropic SDK and point it at CcHUB:
pip install anthropic
from anthropic import Anthropic
client = Anthropic(
api_key="sk-your-cchub-key", # your staff API key
base_url="https://bedrock.cchub.africa",
)
message = client.messages.create(
model="claude-4-6-sonnet",
max_tokens=1024,
messages=[
{"role": "user", "content": "Summarise our company values in 3 bullets."},
],
)
print(message.content[0].text)
print(f"Credits remaining: {message.usage.credits_remaining}")
API Endpoints
/v1/messagesAnthropic-compatible Messages API. Use with Anthropic SDK or any tool expecting native Anthropic format (Claude Code, Cursor, etc.).
/v1/chat/completionsOpenAI-compatible Chat Completions API. Use with OpenAI SDK, LangChain, or any OpenAI-compatible tool.
/v1/modelsLists every model available to your key, with cost multipliers and limits.
/v1/usageReturns your remaining credits, 24h usage breakdown and per-model statistics.