Claude Opus 4.6 是 Anthropic 的升级版 Opus 级模型,专为编程、长上下文推理、智能体工作流及复杂知识型任务打造。它具备更强的调试能力、更优的代码审查表现,以及在大上下文场景下更可靠的性能。

Pricing: Input 285 credits / 1M tokens (≈ $1.425), Output 1,430 credits / 1M tokens (≈ $7.150) — both ~28.5% of official pricing. High-tier top-ups include +10% bonus credits. Effective pricing is approximately 10% lower than the above rates.
claude-opus-4-6

Automatically append previous messages to maintain multi-turn context. May increase token usage.

Function calling
Thinking process
Max tokens
Stream Response

How can I help you today?

README

Complete guide to using claude-opus-4-6

Kie.ai 现已提供高性价比 Claude Opus 4.6 API

Original image
Claude Opus 4.6 API:更强劲的编程、调试与代码审查能力
Claude Opus 4.6 API 配备 1M Token 上下文窗口
Claude Opus 4.6 API 新特性:自适应思考、推理力度控制与上下文压缩
128k Token 输出扩展了 Claude Opus 4.6 API 对更大规模任务的支持
4.9/ 5
41,197 ratings
Tap a star to rate
基准测试Claude Opus 4.6Claude Opus 4.5Claude Sonnet 4.5Gemini 3.1 ProGPT-5.4
Agentic terminal coding65.40%59.80%51.00%68.50%75.10%
Agentic computer use72.70%66.30%61.40%—75.00%
Agentic search84.00%67.80%43.90%85.90%82.70%
Multidisciplinary reasoning (no tools)40.00%30.80%17.70%44.70%39.80%
Multidisciplinary reasoning (with tools)53.00%43.40%33.60%—52.10%
Graduate-level reasoning91.30%87.00%83.40%94.30%92.80%