Claude Opus 5
⧉Claude Opus 5 是 Anthropic 新一代旗舰模型，默认开启自适应思考，长于复杂推理、代码工程与 Agent 编排，支持图片理解、工具调用与提示缓存。完全兼容 OpenAI 接口，把 model 改成 claude-opus-5 即可接入；也可用原生 Anthropic Messages 接口让 Claude Code 直连。
Live Test · Playground
Try out Claude Opus 5 right here (available after login)。
Input
Advanced
Conversation
About Claude Opus 5
Claude Opus 5 is Anthropic's next-generation flagship model. Adaptive thinking is on by default: the model decides how long to reason per request, answering simple questions directly and working through harder ones first, with the reasoning visible on the native API and in the playground. It is strong at complex reasoning, code engineering, agent orchestration and long-context documents, and natively supports image input, tool use and prompt caching. NezhaGate serves it two ways: the OpenAI-compatible endpoint (point base_url at NezhaGate, set model to claude-opus-5, reuse your OpenAI SDK unchanged), and the native Anthropic Messages API (point ANTHROPIC_BASE_URL at NezhaGate's /anthropic so Claude Code connects directly, preserving thinking, tool_use and prompt caching). Billing is pay-as-you-go and failed requests are not charged.
Use cases
Cross-file refactors, hard bug hunts, architecture review and migration plans - with tool use it can drive an agent through multi-step changes.
Multi-step logic, trade-off analysis, data interpretation and technology selection, with adaptive thinking spending more budget on the hard cases.
Summarize, extract from and answer questions over contracts, papers, manuals and large repositories; prompt caching makes repeated questions much cheaper.
Native tool_use supports function calling and multi-turn tool loops, which suits automated workflows and engineering assistants.
Read charts, screenshots and design mockups and respond with analysis or code; both base64 and remote image URLs are accepted.
How to choose
Choose Claude Opus 5 when the task is genuinely hard and you want the model to think before it answers - complex reasoning, large code projects and agent orchestration are its home turf. For narrative, scripts or long-form writing, its sibling Claude Fable 5 has a finer touch; for cheaper everyday chat and coding, use Claude Sonnet 4.6; for million-token context, consider Gemini 3.1 Pro. All of them switch with a single model field on the same endpoint.
FAQ
What is Claude Opus 5?
Why is my temperature ignored?
How do I see the thinking?
Is prompt caching supported, and how is it billed?
Can Claude Code connect directly?
Related Models
Explore other models you can integrate.
GPT-5.6 Sol
前沿旗舰 Agentic 编程模型
GPT-5.6 Terra
日常均衡 Agentic 编程模型
GPT-5.6 Luna
快而省的 Agentic 编程模型
GPT-5.5
旗舰对话与推理模型
GPT Image 2
高质量文生图 / 图生图模型
Nano Banana 2
高质量文生图 / 图生图模型
Nano Banana Pro
旗舰级文生图 / 图生图模型
Claude Sonnet 4.6
均衡高效的对话 / 代码模型
Claude Fable 5
Anthropic Fable 系列 · 叙事与长文特化
Gemini 3.1 Pro
Google 新一代旗舰推理模型
Gemini 3.6 Flash
新一代高速思考模型 · 四档思考预算
Gemini 3.6 Flash High
深度思考档
Gemini 3.6 Flash Low
极速低耗档
Gemini 3.6 Flash Tiered
自动调档
Gemini 3 Flash
高速低延迟，高性价比对话模型
Gemini 3.5 Flash
新一代高速思考模型
Gemini 2.5 Flash
高速低延迟，高性价比对话
Veo 3.1
文生 / 图生视频 · 多档 · 多分辨率
Seedance 2.5
文生 / 图生视频 · 最长 30 秒
Seedance 2.0
文生 / 图生视频 · 4–15 秒
Seedance 2.0 Fast
低延迟 · 最省
MiniMax H3
1440P · 原生音频
