Anthropic: Claude Opus 4.1

anthropic/claude-opus-4.1

200KContext Window

32KMax Output

Supported Protocols:max_tokenstop_ptemperaturestopreasoninginclude_reasoningtoolstool_choice

Normal

Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains in multi-file code refactoring, debugging precision, and detail-oriented reasoning. The model supports extended thinking up to 64K tokens and is optimized for tasks involving research, data analysis, and tool-assisted reasoning.

Capabilities

👁 Vision🧠 Reasoning🔧 Function CallingText GenerationCode GenerationAnalysis & ReasoningReasoning

Technical Specs

Input Modality

Image、Text、Text

Output Modality

Text

Arch

—

Default Temperature

0.7

Default Top_P

Pricing

Pay per use, no monthly fees

Billing Type	Unit	Price
Text Input	—	$15.0000/M tokens
Text Output	—	$75.0000/M tokens
Cache Read	—	$1.5000/M tokens
Cache Write 1h	—	$18.7500/M tokens
Cache Write	—	$18.7500/M tokens
Web Search	—	$0.0100/次

Quick Start

from openai import OpenAI

client = OpenAI(
    base_url="https://api.uniontoken.ai/v1",
    api_key="YOUR_UNIONTOKEN_API_KEY",
)

response = client.chat.completions.create(
    model="anthropic/claude-opus-4.1",
    messages=[
        {"role": "user", "content": "Hello!"}
    ],
)

print(response.choices[0].message.content)