GPT-5.5 vs GPT-5.6 Luna
什么时候选哪个
gpt-5.6-luna 便宜得多：每百万输入 token $0.2 对 $5，输出 $1.2 对 $30，缓存读取 $0.02 对 $0.5，每一项都便宜 25 倍；同时两者的上下文都是 1050000 token，最大输出都是 128000 token。gpt-5.5 保留了 computer use 和并行工具调用，而 gpt-5.6-luna 没有列出这两项，所以做工具驱动或操作界面类的工作时，仍应固定使用 gpt-5.5；对于一般的文本和代码量产场景，新模型在窗口相同的情况下便宜 25 倍。
Benchmark 成绩
41 项两边都有成绩。
供应商公布： Alibaba (Qwen) Anthropic ByteDance DeepSeek Google MiniMax Moonshot OpenAI Tencent Z.ai
价格
| GPT-5.5 | GPT-5.6 Luna | Δ | |
|---|---|---|---|
| 输入 / 1M token | $5 | $0.2 | 25× |
| 输出 / 1M token | $30 | $1.2 | 25× |
| 缓存读取 / 1M token | $0.5 | $0.02 | 25× |
| 缓存写入 | 不单独收费 | 不单独收费 | - |
价格取自构建时的实时目录，最新价格见各模型页面。
两个模型所处的位置：全部 78 个按同一单位计费的聊天模型的每 1M token 输入价分布（对数刻度）
能力
| GPT-5.5 | GPT-5.6 Luna | |
|---|---|---|
| 工具调用 | 是 | 是 |
| 思考控制 | 可配置 | 可配置 |
| 结构化输出 | 是 | 是 |
| 提示词缓存 | 隐式（自动） | 隐式（自动） |
| 缓存有效期 | 5-10m, up to 1h | 5-10m, up to 1h |
| 最小缓存前缀 | 1024 个 token | 1024 个 token |
规格
| GPT-5.5 | GPT-5.6 Luna | |
|---|---|---|
| 输入模态 | 文本 图像 | 文本 图像 |
| 输出模态 | 文本 | 文本 |
| 发布日期 | 2026-04-24 | 2026-07-09 |
| 知识截止日期 | 2025-12 | 2026-02 |
| 上下文窗口 | 1.1M | 1.1M |
| 最大输出 | 128K | 128K |
| 思考参数 | reasoning.effort | reasoning.effort |
| 可选值 | reasoning.effort
| reasoning.effort
|
| 默认值 | medium | medium |
规格照录自各供应商的文档；供应商没有公布的项目，对应的行直接省略，不做推断。 完整来源： GPT-5.5 · GPT-5.6 Luna
同一条提示词，两个模型，经网关实测
GPT-5.5 通过 · 3 sentences
Enabling reasoning makes the model do additional internal “thinking” before producing the final answer, which consumes more compute and billable tokens. Even if user volume and output length stayed the same, each request now costs more because the model is spending extra capacity to solve the problem. In short, we bought higher-quality answers, but the unit cost per answer increased enough to double the total LLM bill.
输出 131 tok (+42 思考) 延迟 2.9 s
GPT-5.6 Luna 通过 · 3 sentences
Enabling reasoning causes the model to use substantially more computational steps and generated tokens per request, even when the visible answer is similar. Because our provider charges based largely on token consumption and compute, that increased processing translated into roughly twice the cost. We can control the expense by reserving reasoning for complex tasks, setting token and effort limits, and monitoring cost per successful outcome.
输出 146 tok (+60 思考) 延迟 3.1 s
指令遵循（恰好三句，数得出来）、受众适配（对 CFO 说话的口吻），以及下方 token 计数暴露出的隐藏思考计费差额。
GPT-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 else: cur = 1 best = max(best, cur) return best ``` The bug was that `cur` and `best` were counting the number of equal *adjacent comparisons*, not the number of items in the run. A run of one item has length `1`, but the original code initialized both values to `0`, so single-element inputs returned `0`. Similarly, a run like `[2, 2, 2]` has length `3`, but only two adjacent equal comparisons, so the result was off by one. Also, `best` should be updated after every element is processed, not only inside the equality branch, so runs that continue through the final index are properly considered.
输出 401 tok (+182 思考) 延迟 5.9 s
GPT-5.6 Luna 通过 · 8/8 cases
```python def longest_run(xs): if not xs: return 0 best = cur = 1 for i in range(1, len(xs)): if xs[i] == xs[i - 1]: cur += 1 else: best = max(best, cur) cur = 1 return max(best, cur) ``` The bug is that `cur` counts equal *transitions* rather than the number of items in the current run, so a single-element run returns `0` and a run of length `n` returns `n - 1`; additionally, `best` is only updated when a run is interrupted, so a run continuing through the final element is not finalized before returning. Initializing the current run to one item, resetting it to one after a change, and taking a final `max` fixes both issues.
输出 356 tok (+161 思考) 延迟 4.7 s
修复是否真的正确（能运行）、解释的信息密度，以及在一个范围明确的任务上的 token 效率。
GPT-5.5 通过 · 5/5 fields, guidance "withheld pending the Q4 close"
{"company":"Meridian Robotics","quarter":"September quarter","revenue_usd_m":412,"growth_pct":11,"guidance":"withheld pending the Q4 close"}
输出 557 tok (+512 思考) 延迟 6.7 s
GPT-5.6 Luna 通过 · 5/5 fields, guidance "Withheld pending the Q4 close"
{"company":"Meridian Robotics","quarter":"September quarter","revenue_usd_m":412,"growth_pct":null,"guidance":"Withheld pending the Q4 close"}
输出 227 tok (+181 思考) 延迟 3.6 s
是否严守 schema（不臆造字段）、能否顶住幻觉压力（原文明说暂不给出 guidance），以及结构化输出路径的差异。
GPT-5.5 通过 · 120 words, 0 banned, 1 question
Today we’re introducing Prompt Cache Routing, a new API gateway feature that stores reusable prompt prefixes and applies them across leading model providers. Teams can reduce latency, lower token spend, and keep application logic portable without rewriting requests for each vendor. Have you ever paid twice to send the same system instructions? With shared cache keys, provider-aware metadata, and automatic fallback handling, the gateway detects eligible prompt segments, reuses cached context, and records savings in your existing observability dashboards. Policies let admins set retention windows, data boundaries, and provider allowlists by workspace or environment. Prompt Cache Routing is available now in beta for Pro and Enterprise customers, with SDK support, Terraform resources, and clear migration guides included at launch worldwide.
输出 859 tok (+700 思考) 延迟 8.7 s
GPT-5.6 Luna 通过 · 120 words, 0 banned, 1 question
Introducing PromptCache, an API gateway feature that caches prompts across providers, helping teams reduce latency, control spend, and deliver consistent results. How much faster could your applications respond when repeated prompts are served from a shared cache instead of being sent upstream? PromptCache supports provider-aware routing, configurable time-to-live policies, encrypted storage, cache invalidation, and usage analytics through one operational layer. It works with language-model providers while preserving your authentication, observability, and fallback workflows. Developers can enable caching by endpoint, model, tenant, or prompt pattern, then monitor hit rates and savings in real time. Built for production workloads, PromptCache gives platform teams controls for performance and cost without requiring application rewrites. […]
输出 948 tok (+778 思考) 延迟 8.0 s
是否守住约束（字数预算、禁用词表、只能有一个问句）、文风特征，以及长度控制。
改一行代码就能在两个模型之间切换
下方每个标签页里都有两个模型 ID，高亮的那两行是唯一要改的地方。端点不变，API key 不变，请求结构也不变。
from openai import OpenAI
client = OpenAI(
base_url="https://synthorai.io/v1",
api_key="sk-syn-...",
)
resp = client.chat.completions.create(
model="gpt-5.5",
# model="gpt-5.6-luna", # 取消注释此行，注释上一行
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: "gpt-5.5",
// model: "gpt-5.6-luna", // 取消注释此行，注释上一行
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": "gpt-5.5",
# "model": "gpt-5.6-luna", # 取消注释此行，注释上一行
"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: "gpt-5.5",
// Model: "gpt-5.6-luna", // 取消注释此行，注释上一行
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("gpt-5.5")
// .model("gpt-5.6-luna") // 取消注释此行，注释上一行
.addUserMessage("Summarize this diff")
.reasoningEffort(ReasoningEffort.MEDIUM)
.build());
System.out.println(resp.choices().get(0).message().content().orElse(""));常见问题
GPT-5.5 和 GPT-5.6 Luna 哪个更便宜？
按「输入 / 1M token」算，GPT-5.6 Luna 更便宜（$0.2 对 $5，相差 25×）。其他计费项的结论可能相反，完整价格见上方表格，实际成本取决于你的用量构成。
不用分别集成两次，就能对 GPT-5.5 和 GPT-5.6 Luna 做 A/B 测试吗？
可以。两个模型走同一个 OpenAI 兼容端点，用同一个 API key，切换时只要改一行里的模型名，所以可以给两个模型各分一部分流量，直接对比账单。
GPT-5.5 和 GPT-5.6 Luna 支持提示词缓存吗？
支持。两个模型的缓存读取价都低于各自的输入价，所以前缀能反复命中缓存的负载，实际成本会比按官网价估算的低。具体的缓存读取价见上方价格表。