ERNIE Light DT 1.0

ERNIE-Light-DT-1.0 is based on open-source GLM models and includes research findings from Baidu Search's Lightning large model. It features Baidu Sparse Attention (BSA), a unique sparse attention mechanism developed by...

Input / output price: $1.13 / $3.94 per 1M
Context: 1M tokens
Released: Nov 10, 2026

Try Respan for free

Agent setup

Paste into Claude Code, Cursor, or Codex

Help me set up the Respan gateway: fetch and follow https://www.respan.ai/docs/agent-setup.md. Use model "ernie-light-dt-1.0-intl".

from openai import OpenAI

client = OpenAI(

    base_url="https://api.respan.ai/api/",

    api_key="YOUR_RESPAN_API_KEY",

)

response = client.chat.completions.create(

    model="ernie-light-dt-1.0-intl",

    messages=[{"role": "user", "content": "Hello!"}],

)

print(response.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({

  baseURL: "https://api.respan.ai/api/",

  apiKey: "YOUR_RESPAN_API_KEY",

});

const response = await client.chat.completions.create({

  model: "ernie-light-dt-1.0-intl",

  messages: [{ role: "user", content: "Hello!" }],

});

console.log(response.choices[0].message.content);

curl https://api.respan.ai/api/chat/completions \

  -H "Authorization: Bearer YOUR_RESPAN_API_KEY" \

  -H "Content-Type: application/json" \

  -d '{

    "model": "ernie-light-dt-1.0-intl",

    "messages": [{"role": "user", "content": "Hello!"}]

}'

Read docs

Providers

One provider serves this model, priced per 1M tokens after gateway discounts.

Provider	Context	Input	Output	Cache read	Capabilities
OpenRouter`openrouter/baidu/ernie-light-dt-1.0-intl`	1M	$1.13/M	$3.94/M	$0.113/M

Is a provider down? OpenRouter status

Pricing

USD per 1M tokens on OpenRouter, after gateway discounts.

Input: $1.13 per 1M
Output: $3.94 per 1M
Cache read: $0.113 per 1M

Cost by volume

Total cost from 0 to 1T tokens.

$1.13/MOpenRouter

Throughput and latency

30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.

Output speed

Higher is better

828tokens/sacross providers

Faster than 95% of the other 554 models on the gateway

Time to first token

Lower is better

7.1sacross providers

Faster than 13% of the other 139 models on the gateway

Response latency

Lower is better

11sacross providers

Faster than 15% of the other 643 models on the gateway

Apps

Use ERNIE Light DT 1.0 in the tools you already run. Each guide points the app at the Respan gateway.

Setup guides for more apps are in the integration docs.

ERNIE Light DT 1.0 FAQ

Short answers, built from the data on this page.

ERNIE Light DT 1.0 is a model from Baidu, released on Nov 10, 2026. ERNIE-Light-DT-1.0 is based on open-source GLM models and includes research findings from Baidu Search's Lightning large model. It features Baidu Sparse Attention (BSA), a unique sparse attention mechanism developed by...

On the Respan gateway, ERNIE Light DT 1.0 costs $1.13 per 1M input tokens and $3.94 per 1M output tokens on OpenRouter, after gateway discounts.

ERNIE Light DT 1.0 is served by OpenRouter.

ERNIE Light DT 1.0 accepts up to 1M tokens of context.

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "ernie-light-dt-1.0-intl". To set it up with a coding agent, copy the agent setup prompt at the top of this page.