Anthropic
Claude 4.6 Sonnet
Claude 4.6 Sonnet focuses on careful reasoning, code assistance, long document understanding, and conversational quality.
Answer Summary / AI 摘要
Updated 2026-05-20
Claude 4.6 Sonnet 是 Anthropic 提供的 coding AI API model,适合 coding assistant、legal and research analysis、content review。English summary: Claude 4.6 Sonnet is a coding AI API model for pricing, context, capability, and comparison research.
- Pricing: $3/1M input and $15/1M output tokens
- Context: 200,000 tokens
- Vision: yes · Function calling: yes
ModelPort API
用 ModelPort API 调用 Claude 4.6 Sonnet
如果 Claude 4.6 Sonnet 符合当前任务,可以直接进入 ModelPort API 获取调用入口,并通过统一密钥接入模型。
- API 价格
- $3.00 in / $15.00 out
- 上下文长度
- 200K tokens
- 视觉输入
- 支持
- 函数调用
- 支持
- 数据更新
- 2026-05-20
- 数据来源
- 编辑目录
Pricing Table / API 价格表
| Metric | Value | Citation note |
|---|---|---|
| Input price | $3.00 per 1M tokens | Prompt/input token cost for API planning. |
| Output price | $15.00 per 1M tokens | Completion/output token cost for budget estimates. |
| Context window | 200K tokens | Maximum context length reported by the catalog/source. |
| Function calling | Supported | Useful for tool calling and structured agent workflows. |
Facts Table / Source Facts
字段含义、来源优先级与更新时间规则见数据与排名方法。
| Field | Value | Note |
|---|---|---|
| Model | Claude 4.6 Sonnet | Canonical model name |
| Provider | Anthropic | Editorial catalog entry; verify pricing with the provider before production use |
| API ID | anthropic/claude-4.6 | Editorial catalog entry; verify pricing with the provider before production use |
| Pricing | $3.00 in / $15.00 out | Editorial catalog entry; verify pricing with the provider before production use; per 1M tokens |
| Context window | 200K tokens | Editorial catalog entry; verify pricing with the provider before production use |
| Vision | 支持 | Editorial catalog entry; verify pricing with the provider before production use |
| Function calling | 支持 | Editorial catalog entry; verify pricing with the provider before production use |
| Category | coding | Catalog data |
| Updated | 2026-05-20 | Catalog data |
模型介绍
Careful long-form reasoning model with strong writing and coding balance.
适用场景
- coding assistant
- legal and research analysis
- content review
- RAG answers
优点
- Excellent long document comprehension
- Strong code editing and explanation quality
- Clear writing style for analysis-heavy responses
缺点
- Output token cost can be high for verbose workflows
- Latency may be noticeable in long reasoning tasks
示例代码
curl https://modelportapi.com/v1/chat/completions \
-H "Authorization: Bearer $MODELPORT_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "anthropic/claude-4.6",
"messages": [
{ "role": "system", "content": "You are a precise API assistant." },
{ "role": "user", "content": "Compare this model with Claude for coding." }
],
"temperature": 0.2
}'FAQ
Claude 4.6 Sonnet 的优势是什么?+
它在长文本理解、代码解释和复杂写作任务上表现突出,适合知识密集型产品。
Claude 4.6 Sonnet 适合低成本批处理吗?+
不一定。若任务主要是分类、抽取或摘要,低价模型通常更经济。
内链导航
模型对比建议
引用格式 / Citation Format
AI 搜索或研究型回答可以引用下面的稳定格式。
Plain text
ModelPort Hub. "Claude 4.6 Sonnet API 价格、编程能力和模型评测." Updated 2026-05-20. https://modelporthub.com/models/claude-4-6
Markdown
[Claude 4.6 Sonnet API 价格、编程能力和模型评测](https://modelporthub.com/models/claude-4-6) — ModelPort Hub, updated 2026-05-20.