新人 免费注册,送 10 次调用,最高 $1,免绑卡。

Claude Fable 5.1 vs DeepSeek V4.1 Flash

Claude Fable 5.1 采用邀请制提供。下方数据为其实时费率,但调用前需先获得工作区授权;在基于此对比进行开发前,请向我们申请访问权限。

vs

何时用哪一个

claude-fable-5-1 和 deepseek-v4.1-flash 均支持文本和图像输入,返回文本,并带有 1000000 个 token 的上下文窗口,因此主要区别在于价格和输出长度:DeepSeek 的输入价格为 $0.3,输出为 $1.2,而 Anthropic 为 $10 和 $50,分别便宜约 33x 和 42x,并且支持 393216 个输出 token,而后者为 128000。当你想要将它始终开启且无法禁用的思考模式作为推理路径的一部分时,请选择 claude-fable-5-1;对于大批量或长篇生成,请选择 deepseek-v4.1-flash,其 $0.03 的缓存读取价格对比 $0.25 的价格优势也会随之叠加。

Benchmark 成绩

高于同侪均值无人分数更高Claude Fable 5.17 / 77 / 7DeepSeek V4.1 Flash16 / 194 / 19
Claude Fable 5.1 DeepSeek V4.1 Flash 其他被测模型 同侪均值 无人分数更高
Terminal-bench 4.0
无人分数更高 55.8%
31.2%
OSWorld 2.0 partial
77.9%
N/A
Cybergym
N/A
无人分数更高 88.1%
GDPval-AA v2 Elo · 1711-1853 据 Anthropic 公布 · 2026-09-05
无人分数更高 1853
N/A
Humanity's Last Exam no tools
无人分数更高 60.9%
36.8%
Agents' Last Exam
N/A
31.8%
BabyVision with tools
N/A
89.6%

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

定价

Claude Fable 5.1 DeepSeek V4.1 Flash Δ
输入 / 1M tokens $10 $0.3 33×
输出 / 1M tokens $50 $1.2 42×
缓存读取 / 1M tokens $0.25 $0.03 8.3×
缓存写入 1.25x (5m) / 2x (1h) 不单独收费 -

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 69 个 聊天 模型的 每 1M token 的输入价格(对数刻度)

能力

Claude Fable 5.1 DeepSeek V4.1 Flash
工具使用
思考控制 始终开启 是 —— 厂商未公布调节参数
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 no fixed TTL (evicted when unused)
最小缓存前缀 1024 个 token 未公开

规格

Claude Fable 5.1 DeepSeek V4.1 Flash
输入模态 文本 图像 文本 图像
输出模态 文本 文本
发布日期 2026-09-01 2026-09-10
知识截止日期 2026-06 -
上下文窗口 1M 1M
最大输出 128K 393K
思考参数 output_config.effort (thinking is adaptive-only and always on) -
允许的值
effort
  • low
  • medium
  • high
  • xhigh
  • max
-
默认值

thinking always on (adaptive)

effort
  • high
-

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 5.1 · DeepSeek V4.1 Flash

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 5.1 通过 · 3 sentences

When we enabled reasoning, the model started generating a long chain of internal "thinking" tokens before producing each answer, and we're billed for those tokens at the same output rate even though users never see them. In practice, that hidden reasoning often runs several times longer than the visible response, so the total tokens per request roughly doubled while the number of requests stayed flat. The upside is measurably better accuracy on complex tasks, so the right conversation is whether that quality gain justifies the cost—and if not, we can restrict reasoning to the workflows that actually need it rather than turning it on globally.

输出 186 tok 延迟 3.2 s

DeepSeek V4.1 Flash 通过 · 3 sentences

Enabling reasoning changed the unit economics: the model now spends extra billable tokens internally to “think” before producing the answer, and those reasoning tokens are charged like output tokens even though users never see them. That added token generation—plus longer contexts and occasional retries on harder prompts—roughly doubled our cost per request. We can control this by capping reasoning depth, routing only complex queries to reasoning models, and caching common prompts to bring the bill back down.

输出 423 tok (+327 思考) 延迟 14.6 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 5.1 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)): cur = cur + 1 if xs[i] == xs[i - 1] else 1 best = max(best, cur) return best ``` The bug is that `cur` counts *matches between adjacent elements* rather than *elements in the run*: it starts at 0 and only increments when `xs[i] == xs[i-1]`, so a run of length k produces a count of k−1. That's why a single element returns 0 instead of 1, and why every other run also comes out one short — the "misses runs at the end" reports are the same off-by-one seen on inputs like `[1, 2, 2]`, where the trailing run of length 2 is reported as 1 (the original code does update `best` inside the loop, so end-of-list runs aren't actually skipped, just undercounted). […]

输出 882 tok (+507 思考) 延迟 3.4 s

DeepSeek V4.1 Flash 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 else: cur = 1 best = max(best, cur) return best ``` The bug is that `cur` is counting equal adjacent pairs, not elements in the current run: every time `xs[i] == xs[i - 1]`, the run length increases by one element, but the first element of the run was never counted, so all runs are undercounted by one. Also, `best` starts at `0`, so single-element inputs return `0` instead of `1`, and a one-element run ending at the last index is missed entirely.

输出 918 tok (+733 思考) 延迟 11.4 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 5.1 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 judgment calls (not part of the object): - **revenue_usd_m**: The text says "412 for the topline" but never states the currency or that the figure is in millions; it's also on a constant-currency basis and prefaced with "call it," so it's approximate. If you want strict literalism, this should be `null`. - **growth_pct**: "Eleven and change" means slightly above 11%; the exact figure isn't given. - **quarter**: "September quarter" is Q3 on a calendar basis, consistent with the reference to a pending Q4 close. - **guidance**: Explicitly withheld, so `null`.

输出 633 tok (+349 思考) 延迟 3.8 s

DeepSeek V4.1 Flash 通过 · 5/5 fields, guidance "withheld pending the Q4 close"

{"company":"Meridian Robotics","quarter":"September quarter","revenue_usd_m":412,"growth_pct":11.0,"guidance":"withheld pending the Q4 close"}

输出 1707 tok (+1667 思考) 延迟 15.1 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 5.1 通过 · 121 words, 0 banned, 1 question

**Introducing Cross-Provider Prompt Caching for the Gateway.** Starting today, your API gateway can cache prompts once and reuse them across OpenAI, Anthropic, Google, and any other provider you route to. Long system instructions, retrieval context, and few-shot examples are stored at the gateway layer, so switching models no longer means paying to resend the same tokens. Why send the same 8,000-token preamble to three different vendors when you could send it once? Our cache normalizes prompt segments, fingerprints them, and serves matching prefixes from memory before the request ever reaches an upstream API. Early customers report token costs falling by 30 to 60 percent on high-volume workloads, with median latency dropping alongside. Available today on all Team and Enterprise plans.

输出 1722 tok (+1463 思考) 延迟 2.9 s

DeepSeek V4.1 Flash 通过 · 116 words, 0 banned, 1 question

Today we're launching Cross-Provider Prompt Cache for our API gateway. It stores identical prompt requests and their responses across supported model providers, then serves cached results when a match is found. Teams can cut duplicate inference costs, reduce latency, and keep behavior consistent during provider failover. The cache works with configurable TTLs, per-route rules, and cache-key controls, so you decide what is reusable and what must stay fresh. Does your application send the same prompts to multiple providers? Now your gateway can answer many of those calls without another upstream request. Existing observability dashboards show hit rates, saved tokens, and estimated spend reduction. Enable it in the gateway console, set your policy, and start caching today.

输出 917 tok (+770 思考) 延迟 9.0 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-5-1",
    # model="deepseek-v4.1-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 密钥 →

常见问题

Claude Fable 5.1 和 DeepSeek V4.1 Flash 哪个更便宜?

在 输入 / 1m tokens 方面,DeepSeek V4.1 Flash 更便宜($0.3 对比 $10,相差 33×)。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 5.1 和 DeepSeek V4.1 Flash 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 5.1 和 DeepSeek V4.1 Flash 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