Claude Opus 5.5 is built for long-running agentic coding and knowledge work with always-on thinking and five effort levels.
Provider: Anthropic
Category: text generation
Endpoint: /v1/chat/completions
Status: Available
Cost: --
Claude Opus 5.5 is built for long-running agentic coding and knowledge work with always-on thinking and five effort levels.
API access
Endpoint
POST /v1/chat/completions
Base URL
https://api.hiapi.ai
OpenAI Chat Completions compatible. Use one HiAPI key across all available models.
Input price
4,040 Credits
/ 1M tokens
Output price
20,160 Credits
/ 1M tokens
Context
1M
context window
Max output
128K
output tokens
Ask a question to stream the answer and inspect token usage, latency, and estimated cost.
Call Claude Opus 5.5 with the OpenAI-compatible Chat Completions format. Copy a ready-to-use cURL, Python, or Node.js example below.
/v1/chat/completionscurl -X POST "https://api.hiapi.ai/v1/chat/completions" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "claude-opus-5-5",
"messages": [
{
"role": "user",
"content": "请比较单体架构和微服务的取舍。"
}
],
"stream": false,
"output_config": {
"effort": "medium"
}
}'Tip: Replace YOUR_API_KEY with your actual API key from the API Keys page.
Compatible with the OpenAI Chat Completions format. Set the base URL, API key, and model name to get started.
Billing follows the input, output, and cache token categories actually reported in usage. All prices below are shown per 1 million tokens.
Prompts and context sent to the model
Responses and reasoning generated by the model
These specifications reflect the current public HiAPI text request contract. Undisclosed capabilities are not inferred by the page.
Claude Opus 5.5 is built for long-running agentic coding and knowledge work with always-on thinking and five effort levels.
HiAPI exposes this model through /v1/chat/completions. Test prompts and parameters in the Playground, then use the same HiAPI API key in your server application.
The Playground and API share the same model ID, so three steps take a tested prompt into production.
Step 1
Test the system prompt, output length, and model-supported reasoning options in the Playground.
Step 2
View an existing key or create another after signing in; one key works across all available models.
Step 3
Send requests to /v1/chat/completions and track cost with the usage object.
Claude Opus 5.5 is Anthropic's model for long-running agentic coding and knowledge work. Anthropic documents a 1M-token context window and 128K maximum output.
Use POST /v1/chat/completions with model=claude-opus-5-5.
No. Thinking is always on. Do not send thinking.type=disabled or a manual thinking budget; use output_config.effort instead.
Use low, medium, high, xhigh, or max. Medium is the default.
Use OpenAI-compatible tools with tool_choice=auto. Forced tool choices are unsupported. The initial HiAPI contract covers five-minute cache writes; verify writes and reads in usage and account logs.
Input, output, five-minute cache-write, and cache-read tokens use the live rates on the HiAPI model and pricing pages. Thinking tokens count as output.