Claude Fable 5 vs Kimi K3
Claude Fable 5 已从我们的目录下线。下方是它最后公布的价格;这个模型已无法调用,对比中的另一个模型仍可正常调用。
什么时候选哪个
kimi-k3 在价格表上比 claude-fable-5 低约 3.3x(每百万输入 $3 对比 $10,输出 $15 对比 $50,缓存读取 $0.3 对比 $1),并且它也接受视频输入,能在其 1,048,576-token 的窗口内生成多达 1,048,576 个输出 token。claude-fable-5 提供 1,000,000-token 上下文,但将输出限制在 128,000 个 token 内,并且它带有一项明确的思考能力加上 2026 年 1 月的知识截止日期。为了更低成本的视频输入和极长生成,请选择 kimi-k3;当上述思考能力和既定的时效性比价格更重要时,请选择 claude-fable-5。
Benchmark 成绩
58 项两边都有成绩,其中 1 项打平。
供应商公布: Alibaba (Qwen) Anthropic ByteDance DeepSeek Google MiniMax Moonshot OpenAI Tencent Z.ai
价格
| Claude Fable 5 | Kimi K3 | Δ | |
|---|---|---|---|
| 输入 / 1M token | $10 | $3 | 3.3× |
| 输出 / 1M token | $50 | $15 | 3.3× |
| 缓存读取 / 1M token | $1 | $0.3 | 3.3× |
| 缓存写入 | 1.25x (5m) / 2x (1h) | - | - |
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 76 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)
能力
| Claude Fable 5 | Kimi K3 | |
|---|---|---|
| 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 | 显式(由你标记前缀) | 隐式(自动) |
| 缓存有效期 | 5m default, 1h option | 未公布 |
| 最小缓存前缀 | 1024 个 token | 未公布 |
规格
| Claude Fable 5 | Kimi K3 | |
|---|---|---|
| 输入模态 | 文本 图像 | 文本 图像 视频 |
| 输出模态 | 文本 | 文本 |
| 发布日期 | 2026-06-09 | 2026-07-16 |
| 知识截止日期 | 2026-01 | - |
| 上下文窗口 | 1M | 1M |
| 最大输出 | 128K | 1M |
| 思考参数 | output_config.effort (thinking.type is adaptive-only and needs no configuration) | reasoning_effort (top-level; the thinking object is not accepted) |
| 可选值 | effort
both "enabled" and "disabled" return 400 | reasoning_effort
|
| 默认值 | thinking always on (adaptive) effort
| 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: Claude Fable 5 · Kimi K3
同一条提示词,两个模型,经网关实测
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
Kimi K3 通过 · 3 sentences
Reasoning models don't just answer questions—they "think" first, generating long internal chains of step-by-step logic before producing a response. Those hidden thinking steps are billed as output tokens (the most expensive kind, typically 3–5x the price of input tokens), and a single query can generate thousands of them even when the visible answer is only a paragraph long. So you're paying for dramatically more compute per request: the bill doubled because the model does far more work behind the scenes, not because usage increased.
输出 755 tok (+637 思考) 延迟 20.8 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。
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
Kimi K3 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 a fencepost error: `cur` counts *matching adjacent pairs* rather than *items in the run*, because it starts at 0 and only increments when `xs[i] == xs[i - 1]`. A run of length L contains L−1 equal pairs, so every run was undercounted by exactly one. For a single-element list (a run of length 1) the loop never runs and the function returns 0 instead of 1; likewise any run ending at the last index — e.g. the two `2`s in `[1, 2, 2]` — reported 1 instead of 2, making it look like no run existed at all. […]
输出 1837 tok (+1547 思考) 延迟 47.2 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。
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
Kimi K3 通过 · 5/5 fields, guidance null
{ "company": "Meridian Robotics", "quarter": "September quarter", "revenue_usd_m": 412, "growth_pct": 11, "guidance": null }
输出 924 tok (+863 思考) 延迟 25.9 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。
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
Kimi K3 通过 · 120 words, 0 banned, 1 question
Meet Prompt Cache, a new API gateway capability that stores prompt responses and serves them across OpenAI, Anthropic, Google, and Azure endpoints. It matches requests by model, prompt hash, tools, temperature, and tenant policy, so repeated work returns fast while sensitive contexts stay isolated. Teams set TTLs, stale rules, encryption scopes, and bypass flags per route. Analytics show hit rate, latency saved, token spend avoided, and drift risk by provider. What changes for developers? Keep one integration, add cache headers, and watch fallback logic respect consent, residency, and audit needs. During rollout, canary keys compare fresh answers with cached copies before promotion. Prompt Cache cuts vendor calls, steadies p95 latency, and gives platform owners controls for cost, quality, and compliance.
输出 1527 tok (+1354 思考) 延迟 37.9 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="claude-fable-5",
# model="kimi-k3", # 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)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",
// model: "kimi-k3", // 取消注释此行,注释上一行
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",
# "model": "kimi-k3", # 取消注释此行,注释上一行
"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",
// Model: "kimi-k3", // 取消注释此行,注释上一行
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")
// .model("kimi-k3") // 取消注释此行,注释上一行
.addUserMessage("Summarize this diff")
.reasoningEffort(ReasoningEffort.MEDIUM)
.build());
System.out.println(resp.choices().get(0).message().content().orElse(""));常见问题
Claude Fable 5 和 Kimi K3 哪个更便宜?
按「输入 / 1M token」算,Kimi K3 更便宜($3 对 $10,相差 3.3×)。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 Claude Fable 5 和 Kimi K3 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。
Claude Fable 5 和 Kimi K3 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。