Claude

Anthropic: Claude Opus 5.5Chat

anthropic/claude-opus-5-5

Claude Opus 5.5 accepts text, images and documents and produces text. Its 1M-token context window and 128K-token output limit support large codebases and long document tasks. It supports tools, structured outputs, prompt caching and reasoning effort controls. Call anthropic/claude-opus-5-5 through HaoAI; the Anthropic provider model ID is claude-opus-5-5.

1M context window
128K max output tokens
Released: 2026-09-21
Protocols:OpenAIAnthropic
Capabilities:VisionFunction CallingReasoningPrompt CachingPDF InputWeb Search

Capabilities

  • Code and agent workflowsWork across large codebases and multi-step tasks using tool calls.
  • Long contextUse up to 1M context tokens and 128K output tokens.
  • Vision and documentsCombine text, image and PDF inputs to produce text answers.
  • Reasoning and structured resultsControl reasoning effort and request structured outputs.
  • Prompt cachingReuse cached context with separate read and 5-minute or 1-hour write rates.

Pricing

PriceRate 0.2x
HaoAI
Official
Input
$0.8/M
$4/M
Output
$4/M
$20/M
Cache read
$0.04/M
$0.2/M
Cache write
$1/M
$5/M
Cache write 5m
$1/M
$5/M
Cache write 1h
$1.6/M
$8/M

Code Examples

import anthropic

client = anthropic.Anthropic(
    base_url="https://api.hao.ai/anthropic",
    api_key="YOUR_HAOAI_API_KEY",
)

message = client.messages.create(
    model="anthropic/claude-opus-5-5",
    max_tokens=1024,
    messages=[
        {"role": "user", "content": "Hello!"}
    ],
)

print(message.content[0].text)

Frequently asked questions

HaoAI bills based on actual request usage. Input, output, cache, and any other applicable rates follow the live pricing table on this page. Final request costs are available in the console.