Gemini 4 Hydrogen vs GLM-5.3-Flash

vs

什么时候选哪个

两者都支持视频输入。需要调节思考档位时可试 gemini-4-hydrogen,并将思考 token 算入输出预算。 输入为 100000 token 时,每百万输入/输出 token 的费率为 gemini-4-hydrogen $1.5/$7.5,glm-5.3-flash $0.15/$0.5。

Benchmark 成绩

Gemini 4 Hydrogen:公布了 10 项成绩,但每一项测过的其他模型都太少,没法比较。

高于同类均值无更高分GLM-5.3-Flash4 / 61 / 6
Gemini 4 Hydrogen GLM-5.3-Flash 其他参测模型 同类均值 ★ 没有模型得分更高
DeepSWE 1.1
N/A
63.4%
OSWorld 2.1 82 offline tasks, partial score. Hydrogen and Sonnet: best of 3. Terra: system card
77.6%
N/A
GDPval-AA v2 Elo · 1504-1773 据 Z.ai 公布 · 2026-09-04
N/A
没有模型得分更高 1773
Humanity's Last Exam with tools
N/A
55.3%
Agents' Last Exam
N/A
26.3%
Chartography No tools. Hydrogen and Terra: Google evaluation. Sonnet: system card
66.6%
N/A

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

价格

Gemini 4 Hydrogen GLM-5.3-Flash Δ
输入 / 1M token $1.5 $0.15 10×
输出 / 1M token $7.5 $0.5 15×
缓存读取 / 1M token $0.075 $0.03 2.5×

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 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)

Gemini 4 Hydrogen · $1.5 GLM-5.3-Flash · $0.15
$0.05 · Qwen3 VL Flash $30 · GPT-5.4 Pro

能力

Gemini 4 Hydrogen GLM-5.3-Flash
工具调用 是 是
思考控制 始终开启 始终开启
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 未公布 未公布
最小缓存前缀 4,096 个 token 未公布

规格

Gemini 4 Hydrogen GLM-5.3-Flash
输入模态 文本 图像 音频 视频 文本 图像 视频
输出模态 文本 文本
发布日期 2026-11-12 2026-08-26
知识截止日期 2026-03 -
上下文窗口 1,048,576 1,000,000
最大输出 65,536 163,840
思考参数 thinking_level reasoning_effort
可选值
thinking_level
  • low
  • medium
  • high
  • xhigh

"minimal" and thinking_budget return 400

reasoning_effort
  • low
  • high
  • max
默认值 high max

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: Gemini 4 Hydrogen · GLM-5.3-Flash

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

Gemini 4 Hydrogen 通过 · 3 sentences

When reasoning is enabled, the AI generates extensive hidden "thinking" tokens to verify its logic step-by-step before delivering a final answer. Because vendors bill us for every token produced—meaning we pay full output-token rates for this invisible internal work—our billable consumption doubled even though the user-facing responses stayed the same length. To protect our margins, we should restrict reasoning mode strictly to complex, high-value tasks and route routine queries back to standard models.

输出 1236 tok (+1136 思考) 延迟 9.0 s

GLM-5.3-Flash 通过 · 3 sentences

Enabling reasoning means the model now generates thousands of invisible "thinking" tokens before each visible answer, and we're billed for those hidden tokens at full output rates—our most expensive tier. Since output tokens cost 3–5x more than input tokens, that hidden thinking volume compounds across every request, which is why the bill doubled rather than edged up. If the spend concerns you, the fix is straightforward: route only complex queries to reasoning models and keep simple tasks on standard ones, which can reclaim a meaningful share of that cost without losing accuracy where it matters.

输出 742 tok (+626 思考) 延迟 23.2 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

Gemini 4 Hydrogen 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 best = max(best, cur) else: cur = 1 return best ``` The bug is that `best` and `cur` were initialized (and `cur` was reset) to `0` instead of `1`, causing the loop to count matching adjacent transitions rather than the number of elements in a run. As a result, any non-empty input was off by one—returning `0` on single-element lists where the loop doesn't execute at all, and undercounting every run (including runs ending at the last index) by 1. Returning `0` early for empty inputs and starting/resetting the run length at `1` ensures each element is counted accurately while still updating `best` on the final iteration when a run ends at the last index.

输出 1489 tok (+1247 思考) 延迟 10.8 s

GLM-5.3-Flash 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 best = max(best, cur) else: cur = 1 return best ``` **The bug:** `cur` is supposed to hold the length of the current run, but it's seeded with `0` and reset to `0` on a mismatch instead of `1` — and since the loop starts at index 1, the first element of every run never passes through the `==` branch and so never gets counted at all. That means `cur` actually holds *run length minus 1* for every run, so every run is underreported by one: a single-element input never enters the loop and returns 0 instead of 1, and a run of length n returns n − 1 (e.g., `[3, 3, 3]` returns 2). […]

输出 2462 tok (+2138 思考) 延迟 29.1 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

Gemini 4 Hydrogen 通过 · 5/5 fields, guidance "withheld pending the Q4 close"

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

输出 3165 tok (+3100 思考) 延迟 21.2 s

GLM-5.3-Flash 通过 · 5/5 fields, guidance "Withheld pending the Q4 close"

```json { "company": "Meridian Robotics", "quarter": "September quarter", "revenue_usd_m": 412, "growth_pct": 11, "guidance": "Withheld pending the Q4 close" } ``` Notes on judgment calls: revenue of 412 is on a constant-currency basis as stated; growth of "eleven and change" is approximated as 11 since no precise figure is given.

输出 717 tok (+616 思考) 延迟 9.1 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

Gemini 4 Hydrogen 通过 · 120 words, 0 banned, 1 question

Introducing unified prompt caching, the newest capability in our enterprise API gateway. Are you tired of paying repeatedly for identical prompts sent across different AI providers? Our gateway now caches prompts across major AI providers within a unified, shared memory layer. When an application submits a matching query, the gateway intercepts the request and returns the saved output in milliseconds, completely bypassing external inference fees. Engineering teams gain predictable latency and substantial cost reductions without modifying any existing application code. Managing cache policies at the infrastructure edge helps your organization prevent provider dependency while maintaining strict data privacy standards. Enable unified prompt caching in your dashboard today to build faster, more economical artificial intelligence applications across your entire technology stack.

输出 3710 tok (+3574 思考) 延迟 24.1 s

GLM-5.3-Flash 通过 · 120 words, 0 banned, 1 question

Introducing Cross-Provider Prompt Cache, the newest feature in our API gateway. Today, teams send identical prompts to multiple LLM providers and pay full price each time. Why duplicate that work and cost? With Cross-Provider Prompt Cache, your gateway stores prompt-response pairs and serves repeated requests from cache, regardless of which provider handles the call. The result: lower latency, reduced spend, and consistent outputs across OpenAI, Anthropic, Google, and self-hosted models. Configure cache policies per route, set TTLs, and invalidate entries instantly through the dashboard or API. Built-in analytics show hit rates and savings in real time. Enable the cache with a single flag, no code changes required. Available today on all paid plans. Contact sales for enterprise volume pricing details.

输出 2095 tok (+1937 思考) 延迟 20.2 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="gemini-4-hydrogen",
    # model="glm-5.3-flash",  # 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

Gemini 4 Hydrogen 和 GLM-5.3-Flash 哪个更便宜?

按「输入 / 1M token」算,GLM-5.3-Flash 更便宜($0.15 对 $1.5,相差 10×)。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 Gemini 4 Hydrogen 和 GLM-5.3-Flash 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。

Gemini 4 Hydrogen 和 GLM-5.3-Flash 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