claude-sonnet-5-5
| Context window | 1m |
|---|---|
| Input (CNY / Million Tokens) | ¥9 |
| Output (CNY / million tokens) | ¥45 |
| Cache read (CNY / million tokens) | ¥0 |
| Cache write (1h, yuan / million tokens) | ¥20 |
Prices by channel
| Channel | Input | Output | Read Cache | Cache hit | Cache Write (1h) | Cache write (5m) | Multiplier |
|---|---|---|---|---|---|---|---|
| 聚合/反代节点1 | ¥9 | ¥45 | ¥0 | ¥0.9 | ¥20 | ¥11 | 1.00x |
Call example
This model belongs to theClaudegroup, calling protocol:Anthropic Messages native protocolEnter your API Key to use; groups determine the entry point and cannot be mixed (e.g., models in the Gemini group cannot use /v1/messages).
curl https://www.relay-api.com/v1/messages \
-H "x-api-key: sk-你的Key" \
-H "anthropic-version: 2023-06-01" \
-H "content-type: application/json" \
-d '{
"model": "claude-sonnet-5-5",
"max_tokens": 1024,
"messages": [
{ "role": "user", "content": "你好,请简单介绍一下自己" }
]
}'{
"id": "msg_01abcDEF...",
"type": "message",
"role": "assistant",
"model": "claude-sonnet-5-5",
"content": [
{ "type": "text", "text": "你好!我是 claude-sonnet-5-5,很高兴为你服务。\n\n有什么可以帮你?" }
],
"stop_reason": "end_turn",
"usage": {
"input_tokens": 303,
"output_tokens": 73
}
}Tool Integration Tutorial
Use this model with your usual AI coding tool, billed per token.
Tutorial for connecting the official Anthropic terminal coding agent (Claude Code): installation, setting ANTHROPIC_BASE_URL and API keys, switching models, and troubleshooting.
Using local reverse proxies like cc-switch or claude-code-proxy, you can forward Claude Code (Anthropic) and Codex (OpenAI) to our gateway with a single key and unified billing.
Tutorial for setting up the open-source VS Code coding agent Cline: creating sk- keys and configuring the API Provider and Base URL to use Claude, GPT, or Gemini models.
Configure a custom API Key and Base URL in Cursor's Settings → Models to use Claude, GPT, or Gemini models with your site-issued key.
RikkaHub (Open-source Android AI chat client) tutorial: Create an sk- key, select the Provider type based on the model group, configure the Base URL, and easily call Gemini / Claude / GPT models.
