智商指数
88.5 #25
AAQI 56.0
输出速度
175 t/s
ITL 5.7 ms/tok
混合价格 (3:1)
$0.31 /1M
输入 $0.15/M · 输出 $0.8/M
上下文
131K
≈ 328 页 A4 · 最大输出 8,192
Quality Domain Radar
6-Axis Frontier Evaluation vs Category Average & Flagship
Ling 3.1 Flash
Claude Mythos Preview (#1)
Average (68)
缺少直接基准测量时,雷达图各轴由类别得分近似得出 — 详见 评分方法。
优势与取舍
优势所在
- 175 tok/s — top-tier flash throughput
- $0.31 blended — among the cheapest frontier-adjacent models
- Strong math/coding for a speed-tier model
需要注意的权衡
- No dedicated reasoning mode
- Text-only — no vision or audio
- Weakest on long agentic traces
杀手级用例
High-volume APIs
Cheap, fast completions for consumer-scale products.
Router fast-path
First-response tier in cascading model routers.
Batch summarization
131K context plus low cost for bulk pipelines.
开发者快速上手与 API
请先设置
OPENROUTER_API_KEY — 获取 API 密钥curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "content-type: application/json" \
-d '{
"model": "inclusionAI/ling-3-1-flash",
"messages": [{"role": "user", "content": "Refactor this function for O(n) time and explain the change."}]
}'import os
from openai import OpenAI
client = OpenAI(
base_url="https://openrouter.ai/api/v1",
api_key=os.environ["OPENROUTER_API_KEY"],
)
resp = client.chat.completions.create(
model="inclusionAI/ling-3-1-flash",
messages=[{"role": "user", "content": "Refactor this function for O(n) time and explain the change."}],
)
print(resp.choices[0].message.content)const res = await fetch("https://openrouter.ai/api/v1/chat/completions", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.OPENROUTER_API_KEY}`,
"content-type": "application/json",
},
body: JSON.stringify({
model: "inclusionAI/ling-3-1-flash",
messages: [{ role: "user", content: "Refactor this function for O(n) time and explain the change." }],
}),
});
console.log((await res.json()).choices[0].message.content);OpenRouter-compatible endpoint — one API for 300+ models.
官方资源与链接
API 部署
对比托管商与延迟
Groq、Cerebras、Together、DeepInfra、Fireworks、Bedrock 与 Azure 的吞吐量、TTFT 和缓存定价。
GroqCerebrasTogether AIDeepInfraFireworks AIAWS BedrockAzure AI
各榜单得分
分类能力得分
基准测试分项
实时规格与架构
底层解析
Ling 3.1 Flash — high-throughput MoE
- Sparse MoE tuned for serving density
- 175 tok/s sustained output
- 131K context with cheap cache reads
- Non-reasoning fast path — no thinking tokens burned
发布日期
2026年10月12日
架构
Ling 3.1 Flash — high-throughput MoE
参数量
Not disclosed
开源协议
Proprietary
上下文窗口
131,000 tokens
最大输出
8,192 tokens
模态
text
缓存价格
读 $0.02 · 写 $0.19 /1M
推理
—
输入价格
$0.15/M
输出价格
$0.8/M
输出速度
175 t/s
首Token延迟
—
数据更新
2026年10月22日
每月账单预估
每月预估支出
$0.00
正在计算相对 GPT-4o 的节省额…
引用与嵌入
GitHub Markdown 徽章
Loading badge markdown...BibTeX
@misc{llmpodium2026ling31flash,
title = {Benchmark Analysis and Intelligence Evaluation of Ling 3.1 Flash},
author = {LLMPodium Research},
year = {2026},
url = {https://llmpodium.com/models/ling-3-1-flash}
}嵌入评分徽章
将实时 Podium 评分徽章添加到 GitHub 或 Hugging Face README —— 链接回实时排名。
预览
Markdown
Loading badge snippet...HTML
Loading badge snippet...更多 Ling 模型
替代模型推荐
基于能力、定价和基准测试得分与 Ling 3.1 Flash 最接近的替代模型。