Claude Fable 5 vs Qwen3.8 Max
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
两者都接收文本和图像输入,返回文本,且都接近百万 token 大关(claude-fable-5 为 1000000,而 qwen3.8-max 为 983616),因此真正的区别在于价格表:claude-fable-5 的输入成本高出 5x($10 对比 $2),输出成本高出约 8.3x($50 对比 $6),缓存读取高出 4x($1 对比 $0.25)。当你想要其始终开启的思考功能——该功能无法禁用,因此会按该 $50 的输出费率收取推理费用——时,请选择 claude-fable-5;对于大批量的长上下文工作,请选择 qwen3.8-max,它具有略大的 131072 最大输出,对比 128000。
Benchmark 成绩
35 项两边都有成绩,其中 2 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 | Qwen3.8 Max | Δ | |
|---|---|---|---|
| 输入 / 1M token | $10 | $2 | 5× |
| 输出 / 1M token | $50 | $6 | 8.3× |
| 缓存读取 / 1M token | $1 | $0.25 | 4× |
| 缓存写入 | 1.25x (5m) / 2x (1h) | 1.25x | - |
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 | Qwen3.8 Max | |
|---|---|---|
| 工具调用 | 是 | 是 |
| 思考控制 | 始终开启 | 是,但供应商未公布调节参数 |
| 结构化输出 | 是 | 是 |
| 提示词缓存 | 显式(由你标记前缀) | 隐式 + 显式 |
| 缓存有效期 | 5m default, 1h option | explicit: 5m, reset on hit |
| 最小缓存前缀 | 1024 个 token | 1024 个 token |
规格
| Claude Fable 5 | Qwen3.8 Max | |
|---|---|---|
| 输入模态 | 文本 图像 | 文本 图像 |
| 输出模态 | 文本 | 文本 |
| 发布日期 | 2026-06-09 | 2026-08-03 |
| 知识截止日期 | 2026-01 | - |
| 上下文窗口 | 1M | 984K |
| 最大输出 | 128K | 131K |
| 思考参数 | output_config.effort (thinking.type is adaptive-only and needs no configuration) | - |
| 可选值 | effort
both "enabled" and "disabled" return 400 | - |
| 默认值 | thinking always on (adaptive) effort
| - |
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 · Qwen3.8 Max
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
Qwen3.8 Max 通过 · 3 sentences
Enabling reasoning makes the model produce additional hidden steps before responding, and those tokens are billable. It also tends to lengthen each interaction because the model works through more possibilities before settling on an answer. Therefore, the bill doubled mainly due to higher compute and token usage per request, not necessarily because the number of requests doubled.
输出 378 tok (+305 思考) 延迟 8.6 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
Qwen3.8 Max 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)): if xs[i] == xs[i - 1]: cur += 1 else: cur = 1 best = max(best, cur) return best ``` The bug is that the original code starts `best` and `cur` at `0`, so it counts adjacent equal *transitions* rather than the number of items in the run. A run of length `n` has only `n - 1` equal-neighbor transitions, so single-element inputs return `0`, and runs that reach the end are undercounted by one. Initializing the current run to `1` for the first element, resetting it to `1` on a break, and updating `best` from that count fixes the off-by-one.
输出 1616 tok (+1411 思考) 延迟 34.7 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
Qwen3.8 Max 通过 · 5/5 fields, guidance null
{ "company": "Meridian Robotics", "quarter": "September quarter", "revenue_usd_m": 412, "growth_pct": 11, "guidance": null }
输出 1199 tok (+1141 思考) 延迟 24.4 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
Qwen3.8 Max 通过 · 120 words, 0 banned, 1 question
Today, our API gateway adds prompt caching across major model providers. It stores prompts and responses in one fast cache layer. Teams can lower token spend, reduce latency, and repeat reliable answers. The feature supports OpenAI, Anthropic, Google, and Mistral through one configuration. You can set retention rules, scope access, and invalidate entries quickly. How does your team maintain consistent results during provider outages? Approved cached responses keep applications stable while fallback routes recover. The dashboard shows hit rates, savings, latency, and provider usage. Engineers receive audit trails for every cached prompt, enabling safer testing. Product managers can compare cost trends before and after cache adoption. Start with a small route, then safely expand caching to production traffic right now.
输出 2744 tok (+2591 思考) 延迟 46.3 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="qwen3.8-max", # 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: "qwen3.8-max", // 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": "qwen3.8-max", # 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: "qwen3.8-max", // 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("qwen3.8-max") // 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 Qwen3.8 Max 哪个更便宜?
按「输入 / 1M token」算,Qwen3.8 Max 更便宜($2 对 $10,相差 5.0×)。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 Qwen3.8 Max 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 Qwen3.8 Max 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。