GPT-5.4 vs GPT-5.6 Luna
何时用哪一个
两者上下文同为 1050000 token,单次最多输出 128000 token,所以决定因素是价格和工具能力。gpt-5.6-luna 在每一档费率上都更低:每百万输入 $1 对 $2.5,输出 $6 对 $15,缓存读取 $0.1 对 $1.25 —— 在重复系统提示形成的热前缀上便宜约 12 倍。需要 computer use 或并行工具调用时选 gpt-5.4,这两项 gpt-5.6-luna 未列出;只看费率的话它没有任何优势。
Benchmark 成绩
双方都被测过的 14 项。
厂商公布: Alibaba (Qwen) Anthropic ByteDance DeepSeek Google MiniMax Moonshot OpenAI Tencent Z.ai
定价
| GPT-5.4 | GPT-5.6 Luna | Δ | |
|---|---|---|---|
| 输入 / 1M tokens | $2.5 | $1 | 2.5× |
| 输出 / 1M tokens | $15 | $6 | 2.5× |
| 缓存读取 / 1M tokens | $1.25 | $0.1 | 13× |
| 缓存写入 | 不单独收费 | 不单独收费 | - |
费率取自构建时的实时目录；每个模型页面均附有当前的费率卡。
它们的位置 — 以该计费单位计费的所有 64 个 聊天 模型的 每 1M token 的输入价格（对数刻度）
能力
| GPT-5.4 | GPT-5.6 Luna | |
|---|---|---|
| 工具使用 | 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） |
| 缓存生存时间 | 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-5.4 | 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 | 2026-03-05 | 2026-07-09 |
| 知识截止日期 | 2025-08 | 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 |
| 允许的值 | reasoning.effort
| reasoning.effort
|
| 默认值 | none | medium |
规格转录自各供应商的文档；若供应商未发布某项数据，则直接省略该行，而非进行推断。 完整来源： GPT-5.4 · GPT-5.6 Luna
单个 Prompt，两个模型 —— 通过网关实测
GPT-5.4 通过 · 3 sentences
Enabling reasoning makes the model generate and evaluate additional internal steps before producing an answer, which increases the total tokens processed and therefore the cost per request. It also tends to increase latency and can trigger more tool calls, retries, or longer context retention, all of which compound usage-based charges. So even if user traffic stayed flat, the average cost per interaction rose materially once reasoning was turned on.
输出 82 tok 延迟 1.9 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，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。
GPT-5.4 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: best = max(best, cur) cur = 1 best = max(best, cur) return best ``` The bug is that the original code was counting *matching transitions* between adjacent elements instead of the *length of the run itself*, so a single element started at `0` instead of `1`, making all run lengths off by one. It also only updated `best` inside the equality case, which means the final run could be lost if the loop ended before a change triggered any correction logic. […]
输出 243 tok 延迟 3.0 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（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。
GPT-5.4 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 39 tok 延迟 1.3 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
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。
GPT-5.4 通过 · 126 words, 0 banned, 1 question
Today we’re introducing Prompt Cache, a new API gateway feature that stores prompt results and reuses them across supported model providers. Teams can reduce latency, lower repeated compute costs, and keep application behavior more consistent when identical or near-identical prompts appear in production. Prompt Cache works at the gateway layer, so developers can adopt it without rewriting provider integrations or changing routing logic. Built-in controls let you set cache keys, expiration policies, and privacy rules for sensitive workloads. Need faster responses without duplicating optimization work for each vendor? With shared observability, you can track hit rates, savings, and cache performance in one place. […]
输出 154 tok 延迟 2.9 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
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。
只需一行代码即可在它们之间切换
两个 ID 都包含在下方的每个选项卡中 — 高亮显示的两行是唯一的修改。相同的端点，相同的密钥，相同的请求结构。
from openai import OpenAI
client = OpenAI(
base_url="https://synthorai.io/v1",
api_key="sk-syn-...",
)
resp = client.chat.completions.create(
model="gpt-5.4",
# 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-5.4",
// 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-5.4",
# "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-5.4",
// 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-5.4")
// .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-5.4 和 GPT-5.6 Luna 哪个更便宜？
在 输入 / 1m tokens 方面，GPT-5.6 Luna 更便宜（$1 对比 $2.5，相差 2.5×）。其他行可能得出相反的结论——上方表格提供了完整信息，实际成本取决于你的组合使用情况。
我可以在不进行两次集成的情况下，对 GPT-5.4 和 GPT-5.6 Luna 进行 A/B 测试吗？
可以。两者均通过同一个兼容 OpenAI 的端点提供服务，并使用同一把 API 密钥——切换只需更改一行模型字符串，因此你可以将一部分流量路由到各个模型并直接比较账单。
GPT-5.4 和 GPT-5.6 Luna 支持提示词缓存吗？
是的 —— 两者对缓存读取的计费均低于其输入费率，因此热前缀工作负载的成本低于标价。准确的缓存读取行位于上方的定价表中。