Claude Fable 5 vs GPT-5.6

Claude Fable 5 採邀請制。下方的數字是即時費率,但要先取得工作空間的授權才能呼叫;如果你打算依據這份比較來開發,請先向我們申請開通。

vs

什麼情況選哪一個

兩者皆接受文字與圖片輸入,回傳文字,並將輸出上限設在 128000 token,因此真正的差異在於價格與控制:gpt-5.6 的收費為輸入 $4 / 輸出 $20 / 快取讀取 $0.4,對比 claude-fable-5 的 $10 / $50 / $1,Anthropic 的模型在這三項的成本都是前者的 2.5 倍,且擁有略小一些的 1000000-token 視窗,對比 1050000。針對想要關閉思考功能的高用量或對延遲敏感的工作請選擇 gpt-5.6;當你希望將其常駐推理模式應用於每個請求並願意支付溢價時請選擇 claude-fable-5。

Benchmark 成績

領先高於平均沒有模型更高Claude Fable 54686 / 9740 / 97GPT-5.62994 / 12128 / 121

兩邊都有成績的有 75 項。

Claude Fable 5 GPT-5.6 其他有成績的模型 其他模型平均 ★ 沒有模型分數更高
SWE-Bench Pro
沒有模型分數更高 80.3%
64.6%
BioMysteryBench hard
46.5%
44.7%
OSWorld-Verified
沒有模型分數更高 85%
83%
Cybergym
83.1%
84.5%
HealthBench Professional
60.9%
60.5%
Finance Agent v2
56.3%
53.8%
Harvey Lab-AA
93.6%
87.2%
GPQA Diamond
92.6%
94.6%
Blueprint-Bench 2
38.6%
N/A
BrowseComp
87.4%
90.4%
CharXiv (RQ) reasoning
沒有模型分數更高 88.9%
84.6%

供應商公布: 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

定價

Claude Fable 5 GPT-5.6 Δ
輸入 / 1M tokens $10 $4 2.5×
輸出 / 1M tokens $50 $20 2.5×
快取讀取 / 1M tokens $1 $0.4 2.5×
快取寫入 1.25x (5m) / 2x (1h) 1.25x (30m) / 2.5x (12h) -

費率取自網站建置時的即時目錄;各模型頁面都列有最新的價目。 主表顯示基礎級距。提示詞長度可能改變整筆請求的費率,各模型頁有完整價目。

GPT-5.6 · 依輸入長度分級的價格

整次請求依輸入長度所在級距計費。價格單位為美元/百萬 token。

輸入 token 數輸入輸出
0 - 272,000 $4 $20
272,001 - 1,050,000 $8 $30

兩者的相對位置:每 1M tokens 的輸入價格,涵蓋同一計費單位下全部 91 個聊天模型(對數尺度)

Claude Fable 5 · $10 GPT-5.6 · $4
$0.05 · Qwen3 VL Flash $30 · GPT-5.4 Pro

功能

Claude Fable 5 GPT-5.6
工具使用 是 是
思考控制 一律開啟 可設定
結構化輸出 是 是
提示詞快取 顯式(由你標記前綴) 隱式 + 顯式
快取存活時間 5m default, 1h option at least 30m by default, 12h option on the Responses API
最小快取前綴 512 個 token 1,024 個 token

規格

Claude Fable 5 GPT-5.6
輸入模態 文字 圖像 文字 圖像
輸出模態 文字 文字
發布日期 2026-06-09 2026-07-09
知識截止日期 2026-01 2026-02
上下文視窗 1,000,000 1,050,000
最大輸出 128,000 128,000
思考參數 output_config.effort (thinking.type is adaptive-only and needs no configuration) reasoning.effort
可接受的值
effort
  • low
  • medium
  • high
  • xhigh
  • max

both "enabled" and "disabled" return 400

reasoning.effort
  • none
  • low
  • medium
  • high
  • xhigh
  • max
預設值 思考始終開啟(自適應);effort 為 high medium

規格摘錄自各供應商的文件;供應商沒有公布的項目就直接略過,不自行推測。 完整來源: Claude Fable 5 · GPT-5.6

同一段提示詞,兩個模型,經閘道實測

提示詞 Explain to a CFO, in exactly three sentences, why our LLM bill doubled after we enabled reasoning. 檢查 恰好 3 句

Claude Fable 5 通過 · 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.

輸出 228 tok 延遲 6.7 s

GPT-5.6 通過 · 3 sentences

Enabling reasoning makes the model generate many additional internal tokens before producing an answer, so each request consumes substantially more compute. Those reasoning tokens are billed even though they are not visible to users, and longer processing can also increase tool calls, retries, and output length. The bill doubled because our cost per request rose, not necessarily because usage volume increased; we can control it by limiting reasoning effort and routing simpler tasks to cheaper models.

輸出 126 tok (+30 思考) 延遲 3.0 s

是否照指令做(剛好三句,數得出來)、語氣是否貼合對象(寫給 CFO 看),以及下方 token 計量顯示出的隱藏思考計費落差。

提示詞 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. 檢查 修正後通過測試

Claude Fable 5 通過 · 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

輸出 531 tok 延遲 12.5 s

GPT-5.6 通過 · 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: best = max(best, cur) cur = 1 return max(best, cur) ``` The original code counted equal *transitions* rather than items, so a run of one had length `0`, a run of three had length `2`, and tracking from zero caused the off-by-one error. The corrected version starts each run at length `1`, resets to `1` when the value changes, and performs a final `max` after the loop so a run ending at the last element is included; an empty input still returns `0`.

輸出 277 tok (+93 思考) 延遲 4.2 s

修正是否真的正確(跑得起來)、說明的資訊密度,以及在範圍明確的任務上的 token 效率。

提示詞 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. 檢查 有效的 JSON,完全符合 schema

Claude Fable 5 通過 · 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.

輸出 192 tok 延遲 6.5 s

GPT-5.6 通過 · 5/5 fields, guidance "withheld pending the Q4 close"

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

輸出 179 tok (+118 思考) 延遲 3.7 s

是否遵守 schema(不自創欄位)、面對幻覺誘因的表現(題目明確不給 guidance),以及結構化輸出路徑的差異。

提示詞 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. 檢查 120 詞,0 個禁用詞

Claude Fable 5 通過 · 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.

輸出 1173 tok 延遲 18.2 s

GPT-5.6 通過 · 120 words, 0 banned, 1 question

Today we are introducing Prompt Cache, a new API gateway feature that stores reusable prompt prefixes and serves them across supported model providers. By recognizing identical system instructions, tools, examples, and context blocks, Prompt Cache reduces repeated input processing, lowers latency, and helps control token costs without changing application code. Teams can configure retention windows, cache keys, provider routing, encryption, and regional storage policies from one dashboard or API. What happens when a preferred provider is unavailable? The gateway can route requests to another provider while reusing eligible cached content, preserving performance and consistency. Built-in metrics report hit rates, savings, latency, and provider usage, while audit logs support governance. Prompt Cache is available today in public preview for all customers.

輸出 628 tok (+473 思考) 延遲 7.3 s

是否遵守限制(字數上限、禁用詞清單、只能有一句問句)、文字風格的特徵,以及長度控制。

改一行程式碼就能在兩者之間切換

下面每個頁籤都列了這兩個模型 ID,要改的只有醒目標示的那兩行。端點、金鑰和請求格式都不變。

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="gpt-5.6",  # 取消這一行的註解,並把上一行註解掉
    messages=[{"role": "user", "content": "Summarize this diff"}],
    reasoning_effort="medium",
)
print(resp.choices[0].message.content)

取得 API 金鑰 →

常見問題

Claude Fable 5 和 GPT-5.6 哪個比較便宜?

主表顯示基礎級距。提示詞長度可能改變整筆請求的費率,各模型頁有完整價目。

可以只串接一次,就對 Claude Fable 5 和 GPT-5.6 做 A/B 測試嗎?

可以。兩個模型都走同一個 OpenAI 相容端點,用的也是同一把 API 金鑰,切換時只要改一行裡的模型名稱字串。你可以把一部分流量分別導到兩邊,再直接比較帳單。

Claude Fable 5 與 GPT-5.6 支援提示詞快取嗎?

支援。兩者的快取讀取費率都低於輸入費率,所以前綴已經進快取的工作負載,實際成本會比官網價算出來的低。確切的快取讀取價格請見上方定價表。

相關比較