Anthropic

Claude Opus 5

anthropic/claude-opus-5
/v1/chat/completions/v1/messages

Claude Opus 5 是 Anthropic 公司推出的旗舰模型,适用于需要复杂推理、编码以及长期规划的代理任务。它在以下方面表现出强大的能力:端到端的软件任务处理、代码审查与缺陷检测、图表与文档的视觉分析、复杂的办公任务执行,以及平行子代理的协调工作。 这个模型在执行长时间任务时仍能保持出色的指令遵循能力和工具使用能力,同时在处理那些更注重延迟和效率的工作负载时,其性能依然十分出色。

Input / output modalities
文本 · 图像 · 文件 to 文本
Reference input / output price
Input¥35Output¥175per 1M tokens
Context window
1M
Added to catalog
Jul 26, 2026

Providers and pricing

ProviderInput /MOutput /MCached /MContextMax outputDetails
Amazon Bedrock¥35¥175¥3.51M128K

Amazon Bedrock

Latency
3.88s
Throughput
112 tokens/s
Context
1M

Pricing

Input
¥35/M tokens
Output
¥175/M tokens
Cached
¥3.5/M tokens
Cache write (1 hour)
¥70/M tokens
Cache write (5 minutes)
¥43.75/M tokens

Additional pricing

Cache write
¥43.75
Cache read
¥3.5
Cache write price 5m
¥43.75
Cache write price 1h
¥70

Specifications

Context
1M
Max output
128K
Supported APIs
/v1/chat/completions/v1/messages

Claude Opus 5 code examples and API guide

Modelmesh normalizes requests and responses across service providers behind one consistent API.

Modelmesh provides an OpenAI-compatible Completion API for more than 300 models and service providers. Call it directly, through the OpenAI SDK, or with supported third-party SDKs.

Modelmesh-specific request headers in these examples are optional. When supplied, your application can appear on the Modelmesh rankings.

Supported endpointsSelect an endpoint to switch the example below.
/v1/chat/completions
from openai import OpenAI API_KEY = "$SSY_API_KEY" client = OpenAI( base_url="https://router.shengsuanyun.com/api/v1", api_key=API_KEY, ) try: completion = client.chat.completions.create( model="anthropic/claude-opus-5", messages=[{"role": "user", "content": "Which number is larger, 9.11 or 9.8?"}], temperature=0.6, top_p=0.7, stream=True, ) response_text = "" for chunk in completion: if chunk.choices and chunk.choices[0].delta.content is not None: content = chunk.choices[0].delta.content print(content, end="", flush=True) response_text += content except Exception as error: print(f"Request failed: {error}")
                
              

Related Models