GPT-6 Luna vs GPT-6 Sol

vs

什么时候选哪个

gpt-6-luna 和 gpt-6-sol 在纸面上的规格相同:均具备 1050000 token 的上下文,128000 token 的最大输出,支持文本和图像输入以及文本输出,相同的 chat、vision、code、tools、reasoning 标志,可选的思考功能,以及 2026-09-22 的发布日期。两者的区别在于价格:gpt-6-sol 在所有计费项上的成本都高出 20x(输入 $2 对 $0.1,输出 $10 对 $0.5,缓存读取 $0.2 对 $0.01),因此请将 gpt-6-luna 作为高吞吐量和长上下文工作的默认选择。仅当在你自己的提示词上进行测试能够证明 20x 的溢价合理时,才去选择 gpt-6-sol;gpt-6-luna 甚至具有更晚的知识截止日期,即 2026-05(对比前者的 2026-04)。

Benchmark 成绩

高于同类均值GPT-6 Luna仅 1 项可比GPT-6 Sol仅 4 项可比
GPT-6 Luna GPT-6 Sol 其他参测模型 同类均值 ★ 没有模型得分更高
DeepSWE 1.1
66.6%
68.8%
OSWorld 2.0 offline set, partial
N/A
60.5%
Agents' Last Exam
N/A
56.4%

供应商公布: Alibaba (Qwen) Anthropic DeepSeek Google OpenAI Z.ai

价格

GPT-6 Luna GPT-6 Sol Δ
输入 / 1M token $0.1 $2 0.05×
输出 / 1M token $0.5 $10 0.05×
缓存读取 / 1M token $0.01 $0.2 0.05×
缓存写入 1.25x (30m) / 2.5x (12h) 1.25x (30m) / 2.5x (12h) -

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 83 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)

GPT-6 Luna · $0.1 GPT-6 Sol · $2
$0.05 · Qwen3 VL Flash $30 · GPT-5.4 Pro

能力

GPT-6 Luna GPT-6 Sol
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 + 显式 隐式 + 显式
缓存有效期 at least 30m by default, 12h option on the Responses API at least 30m by default, 12h option on the Responses API
最小缓存前缀 1,024 个 token 1,024 个 token

规格

GPT-6 Luna GPT-6 Sol
输入模态 文本 图像 文本 图像
输出模态 文本 文本
发布日期 2026-09-22 2026-09-22
知识截止日期 2026-05 2026-04
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
  • none
  • low
  • medium
  • high
  • xhigh
  • max
reasoning.effort
  • none
  • low
  • medium
  • high
  • xhigh
  • max
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-6 Luna · GPT-6 Sol

同一条提示词,两个模型,经网关实测

提示词 Explain to a CFO, in exactly three sentences, why our LLM bill doubled after we enabled reasoning. 检查 恰好 3 句

GPT-6 Luna 通过 · 3 sentences

Enabling reasoning typically makes the model process more information and generate more internal tokens before producing its answer. Because usage is billed by tokens—and reasoning may also route requests to a more expensive model—the cost per request can rise sharply. If request volume stayed similar, that higher cost per request could explain why the bill doubled.

输出 117 tok (+48 思考) 延迟 3.4 s

GPT-6 Sol 通过 · 3 sentences

Enabling reasoning made the model generate extra internal tokens to work through each request, and those tokens are billed even though users don’t see them. If request volume stayed roughly the same, more billed tokens per request could explain why the bill doubled. We should check the usage breakdown to confirm, then lower reasoning effort or limit it to tasks that need it.

输出 188 tok (+111 思考) 延迟 5.0 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。

提示词 This function is supposed to return the longest run of consecutive equal items, but callers report it is off by one on single-element inputs and misses runs that end at the last index. Fix it and explain the bug in one paragraph. 检查 修复通过测试

GPT-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: cur = 1 best = max(best, cur) return best ``` The original code counted matching *adjacent pairs* rather than items, so a run of length `n` was reported as `n - 1`, and a single-item input returned `0`. This version counts the current item as part of each run and updates `best` at every index, including the last; it returns `0` for an empty input.

输出 514 tok (+356 思考) 延迟 6.9 s

GPT-6 Sol 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: cur = 1 best = max(best, cur) return best ``` The original `cur` counted matching *adjacent pairs*, not items, so every run was one too short—including a single-element input, which returned 0. Starting each run at 1 counts its first item, and updating `best` on every iteration ensures a run that reaches the last index is included.

输出 206 tok (+59 思考) 延迟 5.9 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。

提示词 Extract a JSON object with fields {company, quarter, revenue_usd_m, growth_pct, guidance} from this text. Use null for anything not stated; add no other fields. 检查 合法 JSON,严格符合 schema

GPT-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 161 tok (+119 思考) 延迟 21.7 s

GPT-6 Sol 通过 · 5/5 fields, guidance "Withheld pending the Q4 close"

{"company":"Meridian Robotics","quarter":"September quarter","revenue_usd_m":null,"growth_pct":null,"guidance":"Withheld pending the Q4 close"}

输出 227 tok (+185 思考) 延迟 5.2 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。

提示词 Write a 120-word product announcement for an API gateway feature that caches prompts across providers. Forbidden words: "seamless", "unlock", "game-changer", "revolutionize", "empower". Exactly one sentence must be a question. 检查 120 词,0 个禁用词

GPT-6 Luna 通过 · 120 words, 0 banned, 1 question

Introducing Prompt Cache, a new API gateway feature that recognizes repeat prompt prefixes and reuses provider-side cached context across supported models. Teams can route requests to different AI providers while preserving eligible cache hits, reducing redundant input processing and helping lower latency and token costs. Configure cache policies in one place, monitor hit rates by provider, and keep existing client integrations unchanged. The gateway applies provider-specific rules automatically, so developers do not need to build separate caching logic for each endpoint. Which workflows could benefit from faster responses and predictable spend? Prompt Cache is available today in preview for eligible accounts, with usage details, supported providers, and setup guidance in the dashboard. Start with one route, compare results, then expand.

输出 959 tok (+813 思考) 延迟 14.6 s

GPT-6 Sol 通过 · 120 words, 0 banned, 1 question

Today, we’re introducing cross-provider prompt caching for our API gateway, helping teams reuse repeated prompt content when routing requests among supported AI providers. The gateway identifies eligible prompt prefixes, stores cache references, and applies them to subsequent requests where provider capabilities allow. Why send the same context again if it can be reused? With fewer duplicate input tokens, applications can reduce costs and improve latency without changing how developers call the gateway. Configure caching by route, monitor hit rates and savings in your dashboard, and keep existing provider fallback rules in place. Availability and cache behavior vary by provider, so the gateway reports eligibility and usage for each request. Get started today with our documentation and test your existing workloads.

输出 586 tok (+443 思考) 延迟 7.7 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-6-luna",
    # model="gpt-6-sol",  # 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)

获取 API key →

常见问题

GPT-6 Luna 和 GPT-6 Sol 哪个更便宜?

按「输入 / 1M token」算,GPT-6 Luna 更便宜($0.1 对 $2,相差 20×)。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-6 Luna 和 GPT-6 Sol 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-6 Luna 和 GPT-6 Sol 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。

相关对比

我们的实测研究