GPT-5.6 Sol vs Qwen3.7 Plus

vs

什么时候选哪个

qwen3.7-plus 的各项费率都低得多(输入 $0.4、输出 $1.6、缓存输入 $0.08,而 gpt-5.6-sol 为 $4、$20 和 $0.4),gpt-5.6-sol 的价格分别是它的 10 倍、12.5 倍和 5 倍。两者都支持文本和图像输入,都可以关闭思考模式,上下文窗口也相近(1000000 对 1050000 token);qwen3.7-plus 还支持视频输入。如果单次响应需要最多 128000 token 的输出,请选 gpt-5.6-sol,因为 qwen3.7-plus 最多只有 65536;大批量任务和视频输入则选 qwen3.7-plus。

Benchmark 成绩

领先高于同类均值无更高分GPT-5.6 Sol794 / 12128 / 121Qwen3.7 Plus011 / 244 / 24

7 项两边都有成绩。

GPT-5.6 Sol Qwen3.7 Plus 其他参测模型 同类均值 ★ 没有模型得分更高
SWE-Bench Pro
64.6%
55.8%
BioMysteryBench hard
44.7%
N/A
OSWorld-Verified
83%
N/A
Cybergym
84.5%
N/A
HealthBench Professional
60.5%
N/A
JobBench
45.4%
27.6%
Harvey Lab-AA
87.2%
N/A
GPQA Diamond
94.6%
90.3%
ERQA
N/A
69.8%
BrowseComp
90.4%
N/A
LVBench
82.1%
76.2%

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

价格

GPT-5.6 Sol Qwen3.7 Plus Δ
输入 / 1M token $4 $0.4 10×
输出 / 1M token $20 $1.6 13×
缓存读取 / 1M token $0.4 $0.08 5×
缓存写入 1.25x (30m) / 2.5x (12h) 1.25x -

价格取自构建时的实时目录,最新价格见各模型页面。 主表显示基础档。提示词长度可能改变整次请求的费率,各模型页有完整价目。

GPT-5.6 Sol · 按输入长度分档的价格

整次请求按输入长度所在档位计费。价格单位为美元/百万 token。

输入 token 数输入输出
0 - 272,000 $4 $20
272,001 - 1,050,000 $8 $30

Qwen3.7 Plus · 按输入长度分档的价格

整次请求按输入长度所在档位计费。价格单位为美元/百万 token。

输入 token 数输入输出思考模式输入
0 - 256,000 $0.4 $1.6 $1.6
256,001 - 1,000,000 $1.2 $4.8 $4.8

两个模型所处的位置:全部 91 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-5.6 Sol · $4 Qwen3.7 Plus · $0.4
$0.05 · Qwen3 VL Flash $30 · GPT-5.4 Pro

能力

GPT-5.6 Sol Qwen3.7 Plus
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 explicit: 5m, reset on hit
最小缓存前缀 1,024 个 token 1,024 个 token

规格

GPT-5.6 Sol Qwen3.7 Plus
输入模态 文本 图像 文本 图像 视频
输出模态 文本 文本
发布日期 2026-07-09 2026-06-01
知识截止日期 2026-02 -
上下文窗口 1,050,000 1,000,000
最大输出 128,000 65,536
思考参数 reasoning.effort
  • enable_thinking
  • thinking_budget
  • preserve_thinking
可选值
reasoning.effort
  • none
  • low
  • medium
  • high
  • xhigh
  • max
enable_thinking
  • true
  • false
thinking_budget
  • in tokens
preserve_thinking
  • true
  • false
默认值 medium 开启;Qwen3.7 Plus 系列为混合思考,思考默认启用,preserve_thinking 则为关闭

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-5.6 Sol · Qwen3.7 Plus

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-5.6 Sol 通过 · 3 sentences

Enabling reasoning makes the model generate additional internal tokens before producing an answer, so each request consumes more billable compute. Reasoning may also increase response length, latency, tool calls, and retries, further raising per-request cost. In short, usage volume may be unchanged, but the cost per task increased enough to double the bill.

输出 111 tok (+34 思考) 延迟 2.3 s

Qwen3.7 Plus 通过 · 3 sentences

Enabling reasoning requires the model to generate extensive internal "thinking" tokens to process complex logic before delivering a final answer. Because our vendor charges us per token consumed, this hidden computational overhead effectively doubles our output volume for the exact same number of user requests. Consequently, our costs have doubled because we are now paying for the model's increased processing time to achieve higher-quality, more accurate results.

输出 1428 tok (+1345 思考) 延迟 25.2 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-5.6 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 function counted equal *adjacencies* rather than items, so a run of length one produced `0` and every longer run was undercounted by one. Initializing `cur` and `best` to `1` for nonempty input makes them represent item counts, resetting `cur` to `1` starts a new run at the current item, and updating `best` on every iteration ensures a run reaching the final index is included.

输出 316 tok (+135 思考) 延迟 5.2 s

Qwen3.7 Plus 通过 · 8/8 cases

## Fixed Code ```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 ``` ## Bug Explanation The function has two related bugs rooted in how it counts run lengths. First, `cur` is initialized to `0` and only incremented on matches, so it counts the number of *transitions* between equal elements rather than the total elements in the run—a run of N identical items only reaches `cur = N − 1`, undercounting by one. This also causes the single-element case to return `0`, since the loop never executes and `cur` never increments. […]

输出 2317 tok (+2005 思考) 延迟 40.5 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-5.6 Sol 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 194 tok (+147 思考) 延迟 3.2 s

Qwen3.7 Plus 通过 · 5/5 fields, guidance null

{ "company": "Meridian Robotics", "quarter": "September", "revenue_usd_m": 412, "growth_pct": 11, "guidance": null }

输出 1807 tok (+1750 思考) 延迟 31.6 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。

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-5.6 Sol 通过 · 120 words, 0 banned, 1 question

Today, we’re introducing Provider Prompt Cache, a new API gateway feature that reuses prompt prefixes across supported AI providers, reducing latency, token costs, and duplicated processing. Teams can define cache policies once, route requests dynamically, and preserve provider flexibility without rewriting application logic. Switching models during testing or failover? The gateway identifies eligible prompt segments, applies provider-specific caching controls, and reports hits, misses, savings, and expiration details through unified logs and metrics. Configurable TTLs, tenant isolation, encryption, and cache-bypass options help teams balance performance, privacy, and freshness for every workload. Provider Prompt Cache is available today in beta through the dashboard and API, with SDK examples and migration guidance included. […]

输出 733 tok (+564 思考) 延迟 7.7 s

Qwen3.7 Plus 通过 · 120 words, 0 banned, 1 question

Introducing PromptCache, our new API gateway feature designed to store and reuse prompts across multiple artificial intelligence providers. Have you ever noticed how repeatedly sending identical queries drains your budget and increases latency? PromptCache solves this by intelligently storing responses at the gateway level. When your application requests the same prompt from a different provider, the system instantly returns the cached result. This drastically reduces API costs and accelerates response times for your users. You can configure custom expiration times and set specific fallback rules for each vendor. You must stop paying twice for the exact same computation. Please upgrade your entire infrastructure today and experience much faster and cheaper integrations without changing a single line of your application code.

输出 4453 tok (+4312 思考) 延迟 76.8 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-5.6-sol",
    # model="qwen3.7-plus",  # 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-5.6 Sol 和 Qwen3.7 Plus 哪个更便宜?

主表显示基础档。提示词长度可能改变整次请求的费率,各模型页有完整价目。

不用分别集成两次,就能对 GPT-5.6 Sol 和 Qwen3.7 Plus 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-5.6 Sol 和 Qwen3.7 Plus 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