🎁 新人 免费注册,送 10 次调用,最高 $1,免绑卡。

Claude Fable 5 vs GLM-5.2

vs

何时使用哪一个 — 经过整理的结论,而非基准测试表格

两个模型都带有 1,000,000-token 上下文窗口和相近的最大输出(claude-fable-5 为 128000,glm-5.2 为 131072),因此区别在于输入和成本:claude-fable-5 接受图像与文本输入,并且始终保持思考功能开启运行,而 glm-5.2 仅限文本并允许你关闭思考功能。在价格表上,glm-5.2 的输入便宜约 13x($0.77 对比 $10),输出便宜约 21x($2.42 对比 $50),缓存读取便宜近 7x($0.143 对比 $1)。当你需要图像输入或强制推理时选择 claude-fable-5;对于大批量的长上下文文本工作,请选择 glm-5.2。

定价

Claude Fable 5 GLM-5.2 Δ
输入 / 1M tokens $10 $0.77 13×
输出 / 1M tokens $50 $2.42 21×
缓存读取 / 1M tokens $1 $0.143
缓存写入 1.25x (5m) / 2x (1h)

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 63 个 聊天 模型的 每 1M token 的输入价格(对数刻度)

Claude Fable 5 · $10 GLM-5.2 · $0.77
$0.05 · Qwen3 VL Flash $30 · GPT-5.4 Pro

能力

Claude Fable 5 GLM-5.2
工具使用
思考控制 始终开启 可配置
结构化输出
提示词缓存 显式(由您标记前缀) 隐式(自动)
缓存生存时间 5m default, 1h option 未公开
最小缓存前缀 1024 个 token 未公开

规格

Claude Fable 5 GLM-5.2
输入模态 文本 图像 文本
输出模态 文本 文本
发布日期 2026-06-09 2026-06-16
知识截止日期 2026-01
上下文窗口 1M 1M
最大输出 128K 131K
思考参数 output_config.effort (thinking.type is adaptive-only and needs no configuration)
  • thinking.type
  • reasoning_effort
允许的值
effort
  • low
  • medium
  • high
  • xhigh
  • max

both "enabled" and "disabled" return 400

thinking.type
  • enabled
  • disabled
reasoning_effort
  • none
  • minimal
  • low
  • medium
  • high
  • xhigh
  • max (none and minimal skip thinking, low and medium map to high, xhigh maps to max)
默认值

thinking always on (adaptive)

effort
  • high
enabled, with reasoning_effort at max: the only GLM with an effort dial, and it defaults to the top of it

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: Claude Fable 5 · GLM-5.2

单个 Prompt,两个模型 —— 通过网关实测

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

Claude Fable 5 通过 · 3 sentences

When we enabled reasoning, the model began generating extensive internal "thinking" tokens before each answer, and those tokens are billed as output even though users never see them. Output tokens typically cost several times more than input tokens, so adding thousands of hidden reasoning tokens per request effectively multiplied our per-query cost. In short, we're paying for a much longer response behind the scenes in exchange for higher answer quality, and we can manage this by tuning reasoning effort levels or reserving reasoning mode for complex tasks only.

输出 228 tok 延迟 6.7 s

GLM-5.2 通过 · 3 sentences

Enabling reasoning means the LLM now generates thousands of invisible "thinking" tokens to systematically work through complex problems before producing a final answer. Because our cloud providers bill for these internal processing steps at the same rate as standard output, our billable token volume per query has doubled. While this increases our direct API costs, it drastically reduces error rates and manual review labor, ultimately lowering our total cost per resolved transaction.

输出 1223 tok (+1138 思考) 延迟 17.1 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。

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

Claude Fable 5 通过 · 8/8 cases

## Fixed code ```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 ``` ## Explanation The original function counts **adjacent equal pairs** rather than **items in a run**: a run of length *n* contains only *n − 1* equal neighbor pairs, so every result is off by one — a single-element list yields 0 instead of 1, and `[1, 2, 2]` yields 1 instead of 2 (which callers perceive as "missing" the run at the end). The fix is to initialize both `cur` and `best` to 1 (any nonempty list has a run of at least length 1), reset `cur` to 1 rather than 0 when

输出 531 tok 延迟 12.5 s

GLM-5.2 未命中 · 1/8 cases (fails [1])

```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 […]

输出 4097 tok (+4036 思考) 延迟 58.4 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。

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,schema 精确

Claude Fable 5 通过 · 5/5 fields, guidance null

```json { "company": "Meridian Robotics", "quarter": "Q3 (September quarter)", "revenue_usd_m": 412, "growth_pct": 11, "guidance": null } ``` Notes on interpretation: "up eleven and change" is rendered as 11 (the precise figure isn't stated), and guidance is null because it was explicitly withheld.

输出 192 tok 延迟 6.5 s

GLM-5.2 通过 · 5/5 fields, guidance "withheld"

```json { "company": "Meridian Robotics", "quarter": "September quarter", "revenue_usd_m": 412, "growth_pct": 11, "guidance": "withheld" } ```

输出 1947 tok (+1893 思考) 延迟 30.9 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。

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

Claude Fable 5 通过 · 120 words, 0 banned, 1 question

**Introducing Cross-Provider Prompt Caching for our API Gateway** Starting today, your repeated prompts are cached once and reused across OpenAI, Anthropic, Google, and any other provider you route through the gateway. Instead of paying full token costs every time your application sends the same system prompt or context block, the gateway detects matching prefixes and serves cached results in milliseconds. Why keep spending money and latency on identical requests? Early adopters report cost reductions of up to 60 percent on high-volume workloads, along with faster median response times. Configuration is simple: enable caching in your dashboard, set a TTL, and choose which routes participate. Cache entries are encrypted at rest and never shared between accounts. Available now on all plans.

输出 1173 tok 延迟 18.2 s

GLM-5.2 通过 · 120 words, 0 banned, 1 question

We are introducing Caching for our API Gateway, the smartest way to optimize your workflows. Why pay for the exact same response twice? Now, you can automatically store and reuse prompt results across multiple AI providers, drastically reducing latency and overall operational costs. If a user submits a duplicate query, the gateway serves the cached answer instantly, regardless of whether you route to OpenAI, Anthropic, or others. This directly translates to faster applications and significantly lower monthly API bills. You can easily configure your specific caching rules within the developer dashboard and watch your efficiency soar. Stop wasting your valuable tokens on completely redundant computations. Upgrade to the latest gateway version today and experience the future of intelligent prompt management.

输出 11125 tok (+10984 思考) 延迟 114.8 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="claude-fable-5",
    # model="glm-5.2",  # 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 密钥 →

常见问题

Claude Fable 5 和 GLM-5.2 哪个更便宜?

在 输入 / 1m tokens 方面,GLM-5.2 更便宜($0.77 对比 $10,相差 13×)。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 Claude Fable 5 和 GLM-5.2 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。

Claude Fable 5 和 GLM-5.2 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。

相关对比

来自我们的实测研究