Redeem voucher

Anthropic

Claude Sonnet 4.5 Thinking

anthropic/claude-sonnet-4.5:thinking
/v1/chat/completions/v1/messages/v1/responses/v1beta/models/*/v1/models/*

Claude Sonnet 4.5 是 Anthropic 迄今为止最先进的 Sonnet 模型,针对真实代理和编码工作流程进行了优化。它在 SWE-bench Verified 等编码基准测试中展现出顶尖性能,并在系统设计、代码安全性和规范遵循性方面均有所改进。该模型旨在实现扩展自主操作,保持跨会话的任务连续性,并提供基于事实的进度跟踪。 Sonnet 4.5 还引入了更强大的代理功能,包括改进的工具编排、推测并行执行以及更高效的上下文和内存管理。凭借增强的上下文跟踪和跨工具调用的令牌使用感知功能,它尤其适用于多上下文和长时间运行的工作流。用例涵盖软件工程、网络安全、财务分析、研究代理以及其他需要持续推理和工具使用的领域。

Input / output modalities
文本 · 图像 to 文本
Reference input / output price
Input¥21Output¥105per 1M tokens
Context window
200K
Added to catalog
Sep 30, 2025

Providers and pricing

ProviderInput /MOutput /MCached /MContextMax outputDetails
Amazon Bedrock¥21¥105¥2.1200K64K
Google Vertex¥21¥105¥2.1200K64K

Amazon Bedrock

Latency
1.94s
Throughput
61 tokens/s
Context
200K

Pricing

Input
¥21/M tokens
Output
¥105/M tokens
Cached
¥2.1/M tokens
Cache write (1 hour)
¥42/M tokens
Cache write (5 minutes)
¥26.25/M tokens

Additional pricing

Cache write
¥26.25
Cache read
¥2.1
Cache write price 5m
¥26.25
Cache write price 1h
¥42

Specifications

Context
200K
Max output
64K
Supported APIs
/v1/chat/completions/v1/messages/v1/responses/v1beta/models/*/v1/models/*

Google Vertex

Latency
0s
Throughput
0 tokens/s
Context
200K

Pricing

Input
¥21/M tokens
Output
¥105/M tokens
Cached
¥2.1/M tokens
Cache write (1 hour)
¥42/M tokens
Cache write (5 minutes)
¥26.25/M tokens

Additional pricing

Cache write
¥26.25
Cache read
¥2.1
Cache write price 5m
¥26.25
Cache write price 1h
¥42

Specifications

Context
200K
Max output
64K
Supported APIs
/v1/chat/completions/v1/messages/v1/responses/v1beta/models/*/v1/models/*

Claude Sonnet 4.5 Thinking 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.
View endpoint guideGetting startedLearn what each endpoint does and choose one for your coding tool

Endpoints are the entry points for calling a model, and each uses a different request format. Choose a protocol for your coding tool, then enter the Base URL, API Key, and current model ID.

Endpoint guide for the current model
EndpointWhat it isMain usesCoding agents / tools and requirements
/v1/chat/completionsThe OpenAI chat format: send messages with roles such as user and assistant.Multi-turn conversations and coding questions; tool calling when supported by both the model and gateway.Cline OpenAI Compatible mode and Continue OpenAI-compatible configuration. Set the Base URL, Key, and model ID. If Continue automatically selects Responses, set useResponsesApi: false.
/v1/messagesThe Anthropic Messages format: inputs and outputs are organized as messages and content blocks.Claude-style conversations, coding tasks, and tool calling.Claude Code: connect to a compatible gateway using ANTHROPIC_BASE_URL. Messages, tools, and streaming event formats must be compatible. Official support covers Claude models; protocol conversion for other models requires platform adaptation and testing. This endpoint alone does not establish compatibility.
/v1/responsesThe OpenAI Responses format: a unified structure for inputs, model outputs, and tool results.Multi-turn tasks, agent coding workflows, and tool calling.Codex (custom provider): set base_url, env_key, and the model ID, with wire_api = "responses". The gateway must support compatible tool calling and streaming events.
/v1beta/models/*The Gemini beta model operation path. * represents the model name and operation, such as {model}:generateContent.Content generation, supported multimodal inputs, and features available in the beta API.Gemini CLI (Gemini API Key mode): point GOOGLE_GEMINI_BASE_URL at a compatible gateway and use the matching v1beta version. Verify generation, streaming, and tool calling for the selected model. Google Gen AI SDK can also be configured by API version.
/v1/models/*The Gemini stable model operation path, such as /v1/models/{model}:generateContent.Content generation features available in the stable API; capabilities depend on the model and API version.Gemini CLI (Gemini API Key mode): the client must actually use v1, and the gateway must support the corresponding operation. Changing the version in a URL alone does not establish compatibility. Google Gen AI SDK can explicitly select v1.

Usage tips

  • This table explains protocol and tool relationships. Availability depends on the current model, gateway adaptation, and tool version. Verify tool calling and streaming before using an agent.
  • * is a placeholder, not a request URL. Here, /v1/models/* means Gemini model operations, not the OpenAI model listing endpoint GET /v1/models.
  • The Base URL is a shared address prefix; an endpoint is a specific operation path. SDKs and tools combine them according to their own rules. Usually, do not enter a complete endpoint as the Base URL. For example, the OpenAI examples on this page use https://router.shengsuanyun.com/api/v1 as the Base URL, and the complete Chat Completions URL is https://router.shengsuanyun.com/api/v1/chat/completions. Do not duplicate /v1.
  • Use the address prefixes in the Anthropic and Gemini examples rather than copying the OpenAI Base URL. Configuration field names differ between tools.
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-sonnet-4.5:thinking", 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