智商指数
86.2 #40
AAQI 86.0
输出速度
60 t/s
ITL 16.7 ms/tok
混合价格 (3:1)
$0.05 /1M
输入 $0.05/M · 输出 $0.05/M
上下文
64K
≈ 160 页 A4 · 最大输出 2,048
Quality Domain Radar
6-Axis Frontier Evaluation vs Category Average & Flagship
LTX-2.3 Fast
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
- ~3× faster than the Pro tier
- Cheapest per-clip price in the LTX line
- Drop-in compatibility with Pro prompts
需要注意的权衡
- 1080p ceiling — no 4K or native audio
- Noticeable detail loss on complex motion
- Short clip lengths only
杀手级用例
Interactive previz
Live prompt iteration for directors and editors.
Social content at scale
Bulk short clips where turnaround beats fidelity.
Pro-tier drafting
Storyboard in Fast, re-render finals on Pro.
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": "lightricks/ltx-2-3-fast",
"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="lightricks/ltx-2-3-fast",
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: "lightricks/ltx-2-3-fast",
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
LTX-2.3 Fast — distilled video model
- Distilled sampler — draft clips in seconds, not minutes
- Same conditioning interface as the Pro tier
- Optimized for preview-then-upscale workflows
- Lower per-clip cost for high-volume iteration
发布日期
2026年10月8日
架构
LTX-2.3 Fast — distilled video model
参数量
Not disclosed
开源协议
Proprietary
上下文窗口
64,000 tokens
最大输出
2,048 tokens
模态
text + video
缓存价格
读 $0.01 · 写 $0.05 /1M
推理
—
输入价格
$0.05/M
输出价格
$0.05/M
输出速度
60 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{llmpodium2026ltx23fast,
title = {Benchmark Analysis and Intelligence Evaluation of LTX-2.3 Fast},
author = {LLMPodium Research},
year = {2026},
url = {https://llmpodium.com/models/ltx-2-3-fast}
}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 Lightricks 模型
替代模型推荐
基于能力、定价和基准测试得分与 LTX-2.3 Fast 最接近的替代模型。