ai.canshu.com
中文
VRAM Calculator Advisor & TCO API Pricing Compare Models Leaderboard GPUs

Search models, GPUs, and tools

↑↓ Navigate · Enter Open · ★ Watchlist prioritized ai.canshu.com
Baidu 百度文心
Proprietary API Baidu 百度文心 · ernie-light-dt-1.0-intl · Text

ERNIE-Light-DT-1.0 Official Specifications, Pricing & Benchmarks

ERNIE-Light-DT-1.0 (ernie-light-dt-1.0-intl) by Baidu 百度文心, released 2026-11-10, featuring 1,024,000 context window, 131,072 max output tokens, and Text input.

📋 ERNIE-Light-DT-1.0 Official API & System Card Specifications

Verified against official Baidu 百度文心 developer documentation & pricing

API Model ID: ernie-light-dt-1.0-intl

1. Identity & Capabilities

API Spec
API Model ID
ernie-light-dt-1.0-intl
Release Date
2026-11-10
Weight License
Proprietary (Undisclosed)
Native Reasoning
✅ Supported
Function Calling & JSON Schema
✅ 原生支持
Batch API 异步批处理
✅ Supported (50% off)

2. Context, Output & Modalities

Limits
Max Context Window
1,024,000 tokens (1024K)
Max Output Tokens
131,072 tokens
Input Modalities
Text
Output Modalities
Text
Direct China Access
✅ Direct CN + RMB
Deployment Mode
Cloud API only (Proprietary)

3. Official Pricing & Cache

USD / 1M
Input / 1M Tokens
$ 1.13
Cached Input / 1M
$ 0.113 -90%
Output / 1M Tokens
$ 3.94

🎛️ Official Sampling & Reasoning Parameters

Recommended generation settings & API parameter constraints

Official Reasoning & Tool Config
temperature=0.7 top_p=0.95 max_tokens=65,536

Closest Self-Hostable Open-Weight Alternatives to ERNIE-Light-DT-1.0

Open-weight models with full HuggingFace weights for private GPU / Mac deployment

Compare with these →

Frequently Asked Questions

Is ERNIE-Light-DT-1.0 open-source or proprietary?

ERNIE-Light-DT-1.0 (ernie-light-dt-1.0-intl) is a proprietary commercial model by Baidu 百度文心. Weights and internal layer dimensions are undisclosed; it is accessed via cloud API.

What are the context limit and API pricing of ERNIE-Light-DT-1.0?

ERNIE-Light-DT-1.0 supports 1024K input context and 131,072 max output tokens, priced at $1.13/1M input ($0.113/1M cached) and $3.94/1M output.