Claude Opus 5.5 是 Anthropic 面向长时运行的智能体编码与知识工作的模型,于 2026 年 9 月 22 日发布;Anthropic 的模型总览建议大多数负载从这里起步,把 Claude Fable 5.1 留给最苛刻的推理任务。
- 输入
- 文本 图像 $4/M
- 输出
- 文本 $20/M
- 缓存读取
- $0.2/M
- 上下文
- 1M
- 对比 GPT-4o
- 便宜约 20%
- 知识截止
- 2026-06
Benchmark 成绩
厂商公布: Alibaba (Qwen) Anthropic DeepSeek Google Moonshot OpenAI Z.ai
价格在同类中的位置
价格在 67 个同类模型中的位置
这条线显示该模型的价格,在 Synthorai 上同类模型里处于什么位置。两端标出了最便宜和最贵的那个。这里是基础价,批量、区域和缓存写入的折扣见价格页。
规格与限制
Token
| 上下文窗口(厂商规格) | 1,000,000 |
|---|---|
| 最大输出(厂商规格) | 128,000 |
| 知识截止 | 2026-06 |
提示词缓存
| 缓存方式 | 显式(需开启) |
|---|---|
| 最低前缀 | 512 厂商默认 1,024 |
| 存活时间 | 默认 5 分钟,可选 1 小时 |
| 写入成本 | 1.25x (5m) / 2x (1h) |
思考
| 厂商参数 | output_config.effort |
|---|---|
| 可选值 | low · medium · high · xhigh · max |
| 默认值 | medium 请求未指定时生效 |
| 可关闭 | 不支持 |
| 思考行为 | Adaptive thinking is always on: thinking {"type": "disabled"} and a manual {"type": "enabled", "budget_tokens": N} both return a 400 error, so effort is the only depth control. The default dropped from high on Claude Opus 5 to medium. |
| 参数 | reasoning_effort |
| 取值 | minimal · low · medium · high 网关侧参数面——以上方厂商映射为准 |
模型
| 模态 | 文本 + 图像 → 文本 |
|---|
- 1M context at standard pricing with no long-context tier
- prompt-cache reads cost 0.05x input ($0.20/M) rather than the usual 0.1x
- minimum cacheable prompt 512 tokens
- forced tool use (tool_choice any or tool) returns a 400
- thinking blocks are tied to the model and conversation that produced them
- up to 300k output tokens on the Message Batches API with the output-300k-2026-03-24 beta header
- fast mode is a research preview on the Claude API only
单个 Prompt —— 通过网关实测
Claude Opus 5.5 通过 · 3 sentences
When we turned on reasoning, the model began "thinking out loud" before each answer, generating thousands of internal working tokens that users never see but that we are billed for just like the final response. Those hidden tokens are charged at the output rate, typically the most expensive rate, so the same question with the same visible answer now costs roughly twice as much or more. We can bring the bill back down without losing the quality gains by capping the reasoning budget and reserving reasoning mode for the complex tasks that actually benefit from it.
输出 263 tok (+102 思考) 延迟 5.7 s
指令遵循(恰好三句,可数)、受众适配(面向 CFO 的语气),以及下方 token 计量所暴露的隐藏思考计费缺口。
Claude Opus 5.5 通过 · 8/8 cases
```python def longest_run(xs): if not xs: return 0 best = 1 cur = 1 for i in range(1, len(xs)): if xs[i] == xs[i - 1]: cur += 1 best = max(best, cur) else: cur = 1 return best ``` **Explanation:** The original code counted *matching adjacent pairs* rather than *items in a run*. Both `cur` and `best` started at 0, and `cur` reset to 0 on a mismatch, so a run of length *n* was reported as *n − 1*. For a single-element list the loop never executes, so it returned 0 instead of 1. For `[5, 5]` it returned 1 instead of 2. The fix treats every element as the start of a run of length 1: `best` and `cur` start at 1, and `cur` resets to 1 (not 0) when the value changes. An explicit check returns 0 for an empty list. The "misses runs at the last index" reports are the same off-by-one bug rather than a separate one. […]
输出 723 tok (+303 思考) 延迟 10.4 s
修复是否真的正确(可运行)、解释的信息密度,以及在一个边界明确的任务上的 token 效率。
Claude Opus 5.5 通过 · 5/5 fields, guidance "Withheld pending Q4 close"
```json { "company": "Meridian Robotics", "quarter": "September quarter", "revenue_usd_m": 412, "growth_pct": 11, "guidance": "Withheld pending Q4 close" } ``` **Judgment calls to check:** - **quarter**: Kept as "September quarter" rather than "Q3", since the fiscal calendar isn't stated. The text mentions an upcoming "Q4 close," so it may be fiscal Q3, but that's not certain. - **revenue_usd_m**: The text says only "412 for the topline." It doesn't state currency or units, and the figure is on a constant-currency basis, not reported USD. USD millions is an assumption. Use `null` if you need strictly stated values. - **growth_pct**: The source says "eleven and change," so the true figure is slightly above 11. 11 is an approximation. - **guidance**: Guidance was explicitly withheld. I recorded that rather than `null`, since the text addresses it directly.
输出 829 tok (+488 思考) 延迟 10.9 s
schema 服从度(不臆造字段)、幻觉压力(guidance 明确被暂缓给出),以及结构化输出路径的差异。
Claude Opus 5.5 通过 · 120 words, 0 banned, 1 question
Today we're launching Cross-Provider Prompt Caching for our API gateway. Why pay twice for the same context? Our gateway now stores repeated prompt prefixes, system instructions, and document chunks, then reuses them whether your request goes to OpenAI, Anthropic, Google, or an open-source model. Teams running retrieval pipelines or long agent loops can cut token costs by up to 60 percent and trim latency on every cached call. Setup takes one configuration flag; no code changes are required. Cache rules respect tenant boundaries, expire on your schedule, and log every hit for audit review. Dashboards show savings by provider, route, and application in real time. Cross-Provider Prompt Caching is available on all Pro and Enterprise plans. Turn it on today.
输出 1263 tok (+1007 思考) 延迟 13.5 s
约束服从度(字数预算、禁用词表、唯一的那句问句)、文风指纹,以及长度控制。
30 秒用上 Claude Opus 5.5
OpenAI 兼容:换掉 base_url,SDK 不用改。POST /v1/chat/completions
from openai import OpenAI
client = OpenAI(
base_url="https://synthorai.io/v1",
api_key="sk-syn-...",
)
resp = client.chat.completions.create(
model="claude-opus-5-5",
messages=[{"role": "user", "content": "Summarize this diff"}],
reasoning_effort="medium",
)
print(resp.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://synthorai.io/v1",
apiKey: "sk-syn-...",
});
const resp = await client.chat.completions.create({
model: "claude-opus-5-5",
messages: [{ role: "user", content: "Summarize this diff" }],
reasoning_effort: "medium",
});
console.log(resp.choices[0].message.content);curl https://synthorai.io/v1/chat/completions \
-H "Authorization: Bearer sk-syn-..." \
-H "Content-Type: application/json" \
-d '{
"model": "claude-opus-5-5",
"messages": [{"role": "user", "content": "Hello"}],
"reasoning_effort": "medium"
}'package main
import (
"context"
"fmt"
"github.com/openai/openai-go/v3"
"github.com/openai/openai-go/v3/option"
)
func main() {
client := openai.NewClient(
option.WithBaseURL("https://synthorai.io/v1"),
option.WithAPIKey("sk-syn-..."),
)
resp, _ := client.Chat.Completions.New(context.TODO(), openai.ChatCompletionNewParams{
Model: "claude-opus-5-5",
Messages: []openai.ChatCompletionMessageParamUnion{
openai.UserMessage("Summarize this diff"),
},
ReasoningEffort: openai.ReasoningEffortMedium,
})
fmt.Println(resp.Choices[0].Message.Content)
}import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.chat.completions.*;
import com.openai.models.ReasoningEffort;
OpenAIClient client = OpenAIOkHttpClient.builder()
.baseUrl("https://synthorai.io/v1")
.apiKey("sk-syn-...")
.build();
ChatCompletion resp = client.chat().completions().create(
ChatCompletionCreateParams.builder()
.model("claude-opus-5-5")
.addUserMessage("Summarize this diff")
.reasoningEffort(ReasoningEffort.MEDIUM)
.build());
System.out.println(resp.choices().get(0).message().content().orElse(""));关于 Claude Opus 5.5
- 它的价格为每百万输入 token $4、每百万输出 token $20,提示词缓存读取按输入价的 5%(每百万 $0.20)计费,而不是常见的 10%,因此反复重放稳定前缀的智能体循环会明显更便宜。
- 它保留 1M token 上下文窗口且没有长上下文加价,最大输出 128K,支持文本与图像输入,知识截止为 2026 年 6 月。
- Anthropic 文档列出了从 Claude Opus 5 迁移时的四项破坏性变更:自适应思考始终开启,关闭思考或设置手动预算会报错,默认改为 medium 的 effort 参数成为唯一的深度控制;通过 tool_choice any 或 tool 强制调用工具会被拒绝,需要保持 tool_choice 为 auto,并用严格工具调用或结构化输出获得符合 schema 的 JSON;思考块与产生它的模型和对话绑定;Claude API 上不再接受较早的 computer_20251124 工具。
- 模型在工具调用之间写的简短说明现在以思考块返回,需要流式展示这些内容的界面应设置 thinking 的 display 值。
- Synthorai 通过与其余 Claude 模型相同的 API 提供 Claude Opus 5.5。
常见问题
Claude Opus 5.5 API 可以免费试用吗?
可以。新账号可获得 10 次试用调用和最高 $1 的免费额度,无需绑卡。按输入 $4/M 计算,仅这笔额度就足够对 Claude Opus 5.5 发起约 31 次 ~8K token 的请求。
Claude Opus 5.5 最擅长什么?
Anthropic 推荐大多数负载的起步模型、缓存读取为输入价的 5%,每百万 token $0.20、思考始终开启,effort 默认 medium。完整能力请见「关于」部分,内容取自厂商官方发布说明。
Claude Opus 5.5 的价格是多少?
在 Synthorai 上,Claude Opus 5.5 输入 $4/百万 token、输出 $20/百万 token,即厂商牌价,无平台加价。缓存命中的输入 token 按 $0.2/M 计费。
Claude Opus 5.5 支持提示词缓存(prompt caching)吗?
支持,需主动开启:用 cache_control 断点标记稳定前缀。缓存命中的输入 token 按 $0.2/M 计费(未命中 $4/M);提示词需有 512 token 以上的稳定前缀才能命中缓存(TTL 默认 5 分钟,可选 1 小时)。 提示词缓存指南 →
如何开通 Claude Opus 5.5?
把现有 OpenAI SDK 的 base_url 指向 "https://synthorai.io/v1",model 设为 "claude-opus-5-5" 即可。一把 API key 通用网关上的全部模型。
Claude Opus 5.5 的知识截止日期是什么时候?
Claude Opus 5.5 的知识截止日期为 2026-06,依据厂商官方文档(数据核验于 2026-09-23)。
相关模型
对比
本页每个值都转录自厂商自己的文档(链接见上),并带有核对日期。价格在全目录范围内比较;各厂商定义不同的规格值,只说明差异而不作图表对比。此处没有任何由我们测量的数据,也不做评分。