GPT-6.1 Sol vs Tencent Hy4

vs

什么时候选哪个

提示词不超过 272000 个输入 token 时,每百万输出 token 为 $10 和 $2.501(gpt-6.1-sol 对 hy4)。 应用需要明确控制推理强度时,可评估 gpt-6.1-sol。 与 gpt-6.1-sol 相比,中英文长文档夹有截图时,可评估 hy4。

价格

GPT-6.1 Sol Tencent Hy4 Δ
输入 / 1M token $2 $0.834 2.4×
输出 / 1M token $10 $2.501 4×
缓存读取 / 1M token $0.1 $0.042 2.4×
缓存写入 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。 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-6.1 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 $2 $10
272,001 - 1,050,000 $4 $15

两个模型所处的位置:全部 86 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-6.1 Sol · $2 Tencent Hy4 · $0.834
$0.05 · Qwen3 VL Flash $30 · GPT-5.4 Pro

能力

GPT-6.1 Sol Tencent Hy4
工具调用 是 是
思考控制 始终开启 是,但供应商未公布调节参数
结构化输出 是 -
提示词缓存 隐式 + 显式 隐式(自动)
缓存有效期 at least 30m by default, 12h option on the Responses API 未公布
最小缓存前缀 1,024 个 token 未公布

规格

GPT-6.1 Sol Tencent Hy4
输入模态 文本 图像 文本 图像
输出模态 文本 文本
发布日期 2026-09-29 2026-11-04
知识截止日期 2026-04 -
上下文窗口 1,050,000 1,048,576
最大输出 128,000 65,536
思考参数 reasoning.effort -
可选值
reasoning.effort
  • low
  • medium
  • high
  • xhigh
  • max
-
默认值 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-6.1 Sol · Tencent Hy4

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-6.1 Sol 通过 · 3 sentences

Enabling reasoning makes the model do more computational work before answering, and many providers bill the resulting reasoning tokens even though users never see them. That means the same number of requests can cost twice as much because each request consumes more billable tokens, even if the visible answers stay the same length. We should confirm the increase in our usage breakdown and reserve higher reasoning levels for tasks where the improvement justifies the added cost.

输出 144 tok (+54 思考) 延迟 6.6 s

Tencent Hy4 通过 · 3 sentences

Enabling reasoning changed the unit economics of each request: the model now produces extra “reasoning tokens” and consumes more compute before it returns an answer, and those tokens are billed even if users never see them. Because our pricing is largely token-based, that extra work roughly doubled average cost per call, so flat request volume could still produce a doubled invoice. We are paying for better accuracy and less downstream rework on complex tasks, so the spend is justified only in high-value workflows and should be managed by cost per successful outcome.

输出 1519 tok (+1409 思考) 延迟 21.0 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-6.1 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 counts equal adjacent pairs rather than items in a run: a run of length `n` has only `n - 1` equal pairs, so a single-element input returns `0`, and a run ending at the last index is also undercounted. It does process the last index, so the issue is not a missing final check. Initializing each nonempty run to `1` and updating `best` after every iteration correctly counts items, including singleton and trailing runs; empty inputs still return `0`.

输出 189 tok 延迟 6.3 s

Tencent Hy4 通过 · 8/8 cases

```python def longest_run(xs): n = len(xs) if n == 0: return 0 best = cur = 1 for i in range(1, n): if xs[i] == xs[i - 1]: cur += 1 else: cur = 1 best = max(best, cur) return best ``` The loop range already includes the last index; the real bug is that `cur` and `best` start at `0` and only increase on equal adjacent comparisons, so the function counts equality links (`L - 1` for a run of `L` equal items), not the items in the run: a single item has no link, and the first item of a final run is never counted, with no end-of-list flush to compensate. […]

输出 4509 tok (+4263 思考) 延迟 56.0 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-6.1 Sol 通过 · 5/5 fields, guidance "Withheld pending the Q4 close"

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

输出 345 tok (+285 思考) 延迟 10.2 s

Tencent Hy4 通过 · 5/5 fields, guidance "withheld pending the Q4 close"

{"company":"Meridian Robotics","quarter":"September quarter","revenue_usd_m":412,"growth_pct":"eleven and change","guidance":"withheld pending the Q4 close"}

输出 9869 tok (+9827 思考) 延迟 125.2 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-6.1 Sol 通过 · 120 words, 0 banned, 1 question

Introducing Cross-Provider Prompt Cache, a new API gateway feature that stores reusable prompts and manages caching across your supported AI providers. Why rebuild the same context every time your application switches models? With one configuration, teams can reuse shared instructions, standardize cache policies, and reduce repeated prompt processing wherever provider caching is available. The gateway handles provider-specific requirements while giving you clear visibility into cache hits, usage, and estimated savings. Set expiration windows, isolate cached content by project, and invalidate entries when prompts change. Your existing routing logic stays intact, so you can compare models without rebuilding your caching workflow. […]

输出 588 tok (+435 思考) 延迟 13.9 s

Tencent Hy4 通过 · 120 words, 0 banned, 1 question

Today we are introducing Cross Provider Prompt Cache for our API gateway, a feature that caches prompts and securely reuses them across all connected model providers. Teams can cut duplicate calls, reduce latency, and keep spend predictable when identical instructions appear in chat, search, agents, or batch jobs. What if one cached prompt could support traffic routed to any provider in your stack? Gateway policies control cache keys, time to live, tenant isolation, redaction, and fallback behavior, while usage metrics show hit rates and savings by application. Setup requires one configuration change, and existing client code stays intact. Cross Provider Prompt Cache is available in private beta today for enterprise plans, with general availability next month across all supported regions.

输出 5744 tok (+5601 思考) 延迟 57.6 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-6.1-sol",
    # model="hy4",  # 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-6.1 Sol 和 Tencent Hy4 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-6.1 Sol 和 Tencent Hy4 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-6.1 Sol 和 Tencent Hy4 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