Baidu - Closed weights

ERNIE 4.5 Turbo VL pricing and specs

Name: ERNIE 4.5 Turbo VL
Author: Baidu

ERNIE 4.5 Turbo VL is a closed-weights model from Baidu that costs $0.42 per 1M input tokens and $1.27 per 1M output tokens on the first-party API, with a 128K-token context window.

Last verified October 17, 2026 from intl.cloud.baidu.com. All sources

Input / 1M: $0.42
Output / 1M: $1.27
Context: 128K tokens
Weights: Closed

Pricing per 1M tokens

Item	Price / 1M tokens	Applies to
Input	$0.42	Standard requests
Output	$1.27	Standard requests
Cache read	$0.11	Standard requests

Note: Visual understanding (image + text input) model on Baidu AI Cloud international (Qianfan), pricing page updated 2026-09-07. cache read is the listed 'Cache Hit' price; no cache write or batch price listed. Context length stated as '128k' (max input 123k), recorded as 128000; max output [2, 16384]. The release date is left blank: Baidu's April 25, 2025 Create press release announces ERNIE 4.5 Turbo but does not name the VL endpoint, and no Baidu release note read states its launch date. Not listed in the Vercel AI Gateway model list on 2026-10-17.

Specs

Context window: 128,000 tokens
Max output: 16,384 tokens
Provider: Baidu
API model id: ernie-4.5-turbo-vl
Weights: Closed weights

What ERNIE 4.5 Turbo VL costs in practice

Worked from the standard list rates above, with the math shown so you can swap in your own token counts.

One agent session

1M input tokens and 100K output tokens, no caching.

Input1M x $0.42 = $0.42
Output0.1M x $1.27 = $0.127

$0.547per session

A chat app

10,000 requests a day at 2K input and 500 output tokens each.

Input20M x $0.42 = $8.40
Output5M x $1.27 = $6.35

$14.75per day

$442.50 per 30-day month

The same session at a 90% cache hit

90% of the input is read from the prompt cache. The one-time cache write premium is not included.

Cached input0.9M x $0.11 = $0.099
Uncached input0.1M x $0.42 = $0.042
Output0.1M x $1.27 = $0.127

$0.268per session

Compare with

Model	Input / 1M	Output / 1M	Context	Why listed
ERNIE 4.5 Turbo VL (this page)	$0.42	$1.27	128K	-
ERNIE 4.5 Turbo VL (32K)Baidu	$0.42	$1.27	32K	Similar output price, same provider
GLM-5.3-FlashXZ.ai	$0.37	$1.25	1M	Similar output price
GPT-5.4 nanoOpenAI	$0.20	$1.25	400K	Similar output price
DeepSeek V4.1 FlashDeepSeek	$0.30	$1.20	1M	Similar output price
ERNIE 4.5 Turbo (128K)Baidu	$0.11	$0.45	128K	Same provider
ERNIE 4.5 Turbo (32K)Baidu	$0.11	$0.45	32K	Same provider
ERNIE 5.1Baidu	$0.56	$2.53	128K	Same provider
ERNIE 5.0Baidu	$0.84	$3.38	128K	Same provider

Unlimited OCR: Baidu's Open-Source Solution for Long Document ParsingUnlimited OCR is Baidu's open-source vision-language model that parses 100+ page documents in one pass without memory blowup. How it works and when to use it.

FAQ

How much does ERNIE 4.5 Turbo VL cost per million tokens?

ERNIE 4.5 Turbo VL costs $0.42 per 1M input tokens and $1.27 per 1M output tokens on Baidu's first-party API, per intl.cloud.baidu.com on October 17, 2026. Per 1M tokens, cache reads cost $0.11.

What is ERNIE 4.5 Turbo VL's context window?

ERNIE 4.5 Turbo VL has a 128,000-token context window and returns up to 16,384 output tokens per response.

Are ERNIE 4.5 Turbo VL's weights open?

No. ERNIE 4.5 Turbo VL is a closed-weights model. You call it through Baidu's API as ernie-4.5-turbo-vl.

Sources

Last verified October 17, 2026 from intl.cloud.baidu.com.

Newsletter

One email per week. New model releases, price cuts and what they mean for your bill.