Claude Fable 5.1 vs Gemini 4 Carbon
Claude Fable 5.1 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。
什麼情況選哪一個
兩者的上下文長度都接近一百萬個 token (claude-fable-5-1 為 1000000,gemini-4-carbon 為 1048576),但在計費標準上相距甚遠:gemini-4-carbon 的輸入便宜 5 倍 ($2 對 $10),輸出便宜 5 倍 ($10 對 $50),且快取讀取便宜 2.5 倍 ($0.1 對 $0.25)。當成本為首要考量,或是輸入包含音訊或視訊 (claude-fable-5-1 不支援此類輸入) 時,請選擇 gemini-4-carbon。如果是需要回覆高達 128000 個 token (大約是 gemini-4-carbon 65536 的 2 倍) 的圖文任務,請選擇 claude-fable-5-1。
Benchmark 成績
兩邊都有成績的有 11 項。
供應商公布: Alibaba (Qwen) Alibaba (Qwen) Alibaba (Qwen) Alibaba (Qwen) Alibaba (Qwen) Alibaba (Qwen) Alibaba (Qwen) Anthropic Anthropic Anthropic Anthropic ByteDance DeepSeek DeepSeek Google Google Google Google MiniMax Moonshot OpenAI OpenAI OpenAI OpenAI OpenAI OpenAI OpenAI Tencent Z.ai Z.ai Z.ai Z.ai
定價
| Claude Fable 5.1 | Gemini 4 Carbon | Δ | |
|---|---|---|---|
| 輸入 / 1M tokens | $10 | $2 | 5× |
| 輸出 / 1M tokens | $50 | $10 | 5× |
| 快取讀取 / 1M tokens | $0.25 | $0.1 | 2.5× |
| 快取寫入 | 1.25x (5m) / 2x (1h) | - | - |
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。
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 86 個聊天模型(對數尺度)
功能
| Claude Fable 5.1 | Gemini 4 Carbon | |
|---|---|---|
| 工具使用 | 是 | 是 |
| 思考控制 | 一律開啟 | 一律開啟 |
| 結構化輸出 | 是 | 是 |
| 提示詞快取 | 顯式(由你標記前綴) | 隱式(自動) |
| 快取存活時間 | 5m default, 1h option | 未公布 |
| 最小快取前綴 | 512 個 token | 4,096 個 token |
規格
| Claude Fable 5.1 | Gemini 4 Carbon | |
|---|---|---|
| 輸入模態 | 文字 圖像 | 文字 圖像 音訊 影片 |
| 輸出模態 | 文字 | 文字 |
| 發布日期 | 2026-09-01 | 2026-11-10 |
| 知識截止日期 | 2026-06 | 2026-03 |
| 上下文視窗 | 1,000,000 | 1,048,576 |
| 最大輸出 | 128,000 | 65,536 |
| 思考參數 | output_config.effort (thinking is adaptive-only and always on) | thinking_level |
| 可接受的值 | effort
| thinking_level
"minimal" and thinking_budget return 400 |
| 預設值 | thinking always on (adaptive) effort
| 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 5.1 · Gemini 4 Carbon
同一段提示詞,兩個模型,經閘道實測
Claude Fable 5.1 通過 · 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.
輸出 186 tok 延遲 3.2 s
Gemini 4 Carbon 通過 · 3 sentences
Enabling reasoning instructs the AI to generate a lengthy, behind-the-scenes "thought process" to verify its logic before delivering a final answer. Because our vendor bills us based on total output volume, we are charged for all of that invisible scratchpad work in addition to the visible response, effectively doubling the compute consumed per query. Moving forward, we can control this cost by restricting reasoning strictly to complex, high-stakes workflows where higher accuracy justifies the premium, while routing routine tasks back to standard, lower-cost models.
輸出 908 tok (+799 思考) 延遲 18.0 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。
Claude Fable 5.1 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)): 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). […]
輸出 882 tok (+507 思考) 延遲 3.4 s
Gemini 4 Carbon 通過 · 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 original function counts the number of matching adjacent *transitions* rather than the number of *elements* in a run because `best` and `cur` are initialized and reset to `0` instead of `1`. Because a single item on its own already forms a run of length `1`, starting at `0` causes every non-empty result to be short by one: single-element lists (where the loop never executes) and lists with no duplicates return `0` instead of `1`, and any run of $k$ equal items—including one ending at the last index—only increments `cur` $k - 1$ times, making it appear as though the final element of the run was missed. […]
輸出 1411 tok (+1131 思考) 延遲 32.7 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。
Claude Fable 5.1 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 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`.
輸出 633 tok (+349 思考) 延遲 3.8 s
Gemini 4 Carbon 通過 · 5/5 fields, guidance null
```json { "company": "Meridian Robotics", "quarter": "September quarter", "revenue_usd_m": null, "growth_pct": null, "guidance": null } ```
輸出 3338 tok (+3281 思考) 延遲 61.6 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。
Claude Fable 5.1 通過 · 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.
輸出 1722 tok (+1463 思考) 延遲 2.9 s
Gemini 4 Carbon 通過 · 120 words, 0 banned, 1 question
Are your engineering teams paying multiple AI vendors to generate identical responses? Today, we are introducing Universal Prompt Caching for our flagship API Gateway. When applications route traffic across providers like OpenAI, Anthropic, and Mistral, duplicate queries drain budgets and degrade user experiences. Our new unified caching layer intercepts incoming prompts directly at the network edge. If an identical request was previously fulfilled by any connected model, the gateway delivers the stored response in milliseconds, completely bypassing external API calls. This practical upgrade cuts monthly token expenses substantially while accelerating overall application speed. Best of all, deployment requires zero complex code changes. Simply activate this capability inside your gateway configuration dashboard today to start reducing latency and infrastructure costs immediately.
輸出 2620 tok (+2480 思考) 延遲 31.1 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-5-1",
# model="gemini-4-carbon", # 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)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://synthorai.io/v1",
apiKey: "sk-syn-...",
});
const resp = await client.chat.completions.create({
model: "claude-fable-5-1",
// model: "gemini-4-carbon", // 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",
});
console.log(resp.choices[0].message.content);curl https://synthorai.io/v1/chat/completions \
-H "Authorization: Bearer sk-syn-..." \
-H "Content-Type: application/json" \
-d '{
"model": "claude-fable-5-1",
# "model": "gemini-4-carbon", # 取消這一行的註解,並把上一行註解掉
"messages": [{"role": "user", "content": "Hello"}],
"reasoning_effort": "medium"
}'package main
import (
"context"
"fmt"
"github.com/openai/openai-go/v3"
"github.com/openai/openai-go/v3/option"
)
func main() {
client := openai.NewClient(
option.WithBaseURL("https://synthorai.io/v1"),
option.WithAPIKey("sk-syn-..."),
)
resp, _ := client.Chat.Completions.New(context.TODO(), openai.ChatCompletionNewParams{
Model: "claude-fable-5-1",
// Model: "gemini-4-carbon", // 取消這一行的註解,並把上一行註解掉
Messages: []openai.ChatCompletionMessageParamUnion{
openai.UserMessage("Summarize this diff"),
},
ReasoningEffort: openai.ReasoningEffortMedium,
})
fmt.Println(resp.Choices[0].Message.Content)
}import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.chat.completions.*;
import com.openai.models.ReasoningEffort;
OpenAIClient client = OpenAIOkHttpClient.builder()
.baseUrl("https://synthorai.io/v1")
.apiKey("sk-syn-...")
.build();
ChatCompletion resp = client.chat().completions().create(
ChatCompletionCreateParams.builder()
.model("claude-fable-5-1")
// .model("gemini-4-carbon") // 取消這一行的註解,並把上一行註解掉
.addUserMessage("Summarize this diff")
.reasoningEffort(ReasoningEffort.MEDIUM)
.build());
System.out.println(resp.choices().get(0).message().content().orElse(""));常見問題
Claude Fable 5.1 和 Gemini 4 Carbon 哪個比較便宜?
以「輸入 / 1M tokens」來看,Gemini 4 Carbon 比較便宜($2 對 $10,相差 5.0×)。其他項目的結果可能相反,完整價目請看上表;實際成本要看你的用量組合。
可以只串接一次,就對 Claude Fable 5.1 和 Gemini 4 Carbon 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 5.1 與 Gemini 4 Carbon 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。