Lightricks
LTX-2.3 Pro
Lightricks’ production video model — 4K output, synchronized audio and multi-shot control.
智商指数
89.1 #20
AAQI 89.0
输出速度
18 t/s
ITL 55.6 ms/tok
混合价格 (3:1)
$0.12 /1M
输入 $0.12/M · 输出 $0.12/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 Pro
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
- 4K + audio in a single pass — unique in class
- Multi-shot consistency for narrative content
- Precise camera and keyframe control
需要注意的权衡
- Pro-tier pricing per clip
- Closed weights — API only
- Queue latency at peak hours
杀手级用例
Production video pipelines
4K deliverables with baked audio for ads and shorts.
Multi-shot storytelling
Character-consistent sequences for narrative clips.
Post-production assists
Extend/reframe existing footage with keyframe control.
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-pro",
"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-pro",
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-pro",
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
实时对决
实时规格与架构
底层解析
LTX-2.3 Pro — video foundation model
- Native 4K generation with synchronized audio track
- Multi-shot sequencing — keeps characters consistent across cuts
- Camera-path and keyframe conditioning for directors
- Frame-accurate edit and extend modes
发布日期
2026年10月8日
架构
LTX-2.3 Pro — video foundation 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 $0.02 · 写 $0.12 /1M
推理
—
输入价格
$0.12/M
输出价格
$0.12/M
输出速度
18 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{llmpodium2026ltx23pro,
title = {Benchmark Analysis and Intelligence Evaluation of LTX-2.3 Pro},
author = {LLMPodium Research},
year = {2026},
url = {https://llmpodium.com/models/ltx-2-3-pro}
}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 Pro 最接近的替代模型。