vakati-tech.ai

// baidu

ERNIE-Light-DT-1.0

baidu/ernie-light-dt-1.0-intl

newreasoningtool callingprompt caching

ERNIE-Light-DT-1.0 costs $1.13 per 1M input tokens and $3.94 per 1M output tokens with a 1.0M-token context window.

A reasoning, tool-calling model from baidu, released Nov 10, 2026. LiveBench hasn't published a run for it, so this page carries measured price and specs only — no benchmark numbers.

Input / 1M
$1.13
Output / 1M
$3.94
Context
1.0M
LiveBench overall
Not evaluated

Specs and pricing

Input price

USD per 1M prompt tokens

$1.13
Output price

USD per 1M completion tokens, reasoning included

$3.94
Blended price

3:1 input:output — #108 most expensive of 352 listed models

$1.83
Cached input read

Blank means not priced separately — not free

$0.113
Cache write—
Context window1,024,000 tokens
Max output131,072 tokens
Input modalitiestext
Tool callingYes
Extended reasoningYes
Knowledge cutoff—
ListedNov 10, 2026

What ERNIE-Light-DT-1.0 costs to run

Monthly list cost across five workload shapes, using the published cached-input rate where there is one. A floor, not a quote — batch discounts and cache writes aren't included.

WorkloadPer month
Support chatbot

1.2K in / 400 out × 200K requests

$513.18/mo
RAG assistant

8K in / 600 out × 100K requests

$733.60/mo
Coding agent

40K in / 4K out × 20K requests

$649.68/mo
Document extraction

20K in / 1.5K out × 50K requests

$1,375/mo
Bulk classification

500 in / 20 out × 5M requests

$2,711/mo
Price your own workload

Compare ERNIE-Light-DT-1.0 with

Benchmarked models at a similar price.

Cheaper and stronger alternatives to ERNIE-Light-DT-1.0

ERNIE-Light-DT-1.0 FAQ

How much does ERNIE-Light-DT-1.0 cost?

ERNIE-Light-DT-1.0 lists at $1.13 per 1M input tokens and $3.94 per 1M output tokens, with cached input reads at $0.113 per 1M. A RAG assistant handling 100K requests a month (8K tokens in, 600 out) comes to about $733.60 at list price.

What is the context window of ERNIE-Light-DT-1.0?

ERNIE-Light-DT-1.0 accepts up to 1,024,000 tokens of context and can return up to 131,072 output tokens per response.

Does ERNIE-Light-DT-1.0 support tool calling?

Yes — ERNIE-Light-DT-1.0 supports tool (function) calling and exposes extended reasoning. It accepts text input.

How does ERNIE-Light-DT-1.0 score on benchmarks?

LiveBench has not published a run for ERNIE-Light-DT-1.0 yet. Until it does, compare it on price and specs, or run your own evaluation on your own tasks.

What is the API model ID for ERNIE-Light-DT-1.0?

On OpenRouter the model ID is "baidu/ernie-light-dt-1.0-intl". It was listed on Nov 10, 2026.

More from baidu

How these numbers are produced

  • Price and specs — provider list data from OpenRouter, refreshed every 15 minutes. “Blended” is a 3:1 input:output mix.
  • Scores and ranks — LiveBench release 2026-11-06. Ranks count only models that have a published run; a blank means “not evaluated”, never “bad”.
  • Cost per point — the measured dollars LiveBench spent on the run, divided by the score it earned.

Published benchmarks rank models on someone else's tasks. Before committing, see LLM & agent evaluation for building an eval on your own.