ERNIE-Light-DT-1.0 is a large language model made by Baidu, added to the catalog on 10 Nov 2026. It has a context window of 1,024,000 tokens and costs $1.13 per 1M input tokens and $3.94 per 1M output tokens. It accepts text and produces text. Typical uses: reviewing long documents, working with lengthy prompts and summarising multiple passages.
Price checked ยท source: OpenRouter
What ERNIE-Light-DT-1.0 is
Baidu ERNIE-Light-DT-1.0 is a text-in, text-out model. Its catalog description says it is based on open-source GLM models and includes research findings from Baidu Search's Lightning large model. It also identifies Baidu Sparse Attention (BSA), described as a sparse attention mechanism. The available description gives no further detail about how BSA works, so it does not establish specific task outcomes.
The model accepts text and produces text, with a context window of 1,024,000 tokens and a maximum output of 131,072 tokens. This context allowance can suit work that involves placing extensive text in a single request, such as reviewing long documents, combining material from multiple passages, or working through lengthy prompts. The output limit permits lengthy written responses, depending on the request.
Listed capabilities include tool use, structured outputs, response-format support, and reasoning. These options make the model relevant to workflows that call tools or need responses organized in a specified format, as well as text tasks involving reasoning. The catalog does not specify particular tools, supported schemas, or a formal definition of reasoning, so those details depend on the integration. The supplied modality listing covers text input and output; it does not list image or audio input or output.
Key features
- Accepts text and produces text
- Has a context window of 1,024,000 tokens
- Supports outputs of up to 131,072 tokens
- Supports tools, structured outputs, and response formats
- Includes reasoning support and Baidu Sparse Attention
Typical uses
- Reviewing long documents
- Working with lengthy prompts
- Summarising multiple passages
- Generating structured text
- Tool-assisted text workflows
ERNIE-Light-DT-1.0 pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $1.13 |
| Output, per 1M tokens | $3.94 |
| Cached input read, per 1M tokens | $0.113 |
No price change since it was added on 10 Nov 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0017 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.031 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.042 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.175 |
ERNIE-Light-DT-1.0 specifications
| Model id | baidu/ernie-light-dt-1.0-intl |
|---|---|
| Version | ernie-light-dt-1.0-intl-20261110 |
| Context window | 1,024,000 tokensAbout 768,000 English words |
| Max output | 131,072 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 10 Nov 2026 |
| Input types | text |
|---|---|
| Output types | text |
| Tool calling | Yes |
| Structured outputs | Yes |
| Reasoning effort control | Yes |
| Content moderation | Not applied by provider |
Sample outputs
The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.
No output has been recorded for ERNIE-Light-DT-1.0 yet.
Compare ERNIE-Light-DT-1.0
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.