LLM Reference

ERNIE 4.5 Turbo VL on Baidu Qianfan

ERNIE 4.5 · Baidu AI

ServerlessOpen Source

Last refreshed 2026-05-09. Next refresh: weekly.

Why use ERNIE 4.5 Turbo VL on Baidu Qianfan?

Baidu Qianfan offers ERNIE 4.5 Turbo VL with pay-as-you-go pricing at $0.44/1M input tokens. Baidu Qianfan is Baidu Intelligent Cloud's foundation model and Agent development platform, providing hosted API access to ERNIE and Qianfan models for text generation, reasoning, multimodal understanding, embeddings, and agent workflows.

Input / 1M
$0.44
Output / 1M
$1.33
Cache
Not sourced
Batch
Not sourced

Setup recipe

Docs fallback
Install
Use the provider REST API or SDK
Auth
Create a provider API key
Call
model: ernie-4.5-turbo-vl
Model ID
ernie-4.5-turbo-vl

Request example

Curated snippets for this provider are not sourced yet. Use Baidu Qianfan documentation with model ID ernie-4.5-turbo-vl.

Gotchas

No curated gotchas have been sourced for this exact provider/model route yet.

Pricing

TypePrice (per 1M)
Input tokens$0.44
Output tokens$1.33

Capabilities

VisionMultimodalFunction CallingTool Use

About ERNIE 4.5 Turbo VL

ERNIE 4.5 Turbo VL is the vision-language variant of ERNIE 4.5 Turbo, launched April 24, 2025. Supports image and text inputs with strong visual understanding and multimodal reasoning at reduced cost. API model IDs: ernie-4.5-turbo-vl (primary, 128K context); ernie-4.5-turbo-vl-32k (32K context).

FAQ

What does ERNIE 4.5 Turbo VL cost on Baidu Qianfan?

On Baidu Qianfan, ERNIE 4.5 Turbo VL costs $0.44 per 1M input tokens and $1.33 per 1M output tokens.

What is the context window for ERNIE 4.5 Turbo VL on Baidu Qianfan?

ERNIE 4.5 Turbo VL supports a 128k token context window on Baidu Qianfan.

What API model ID do I use for ERNIE 4.5 Turbo VL on Baidu Qianfan?

Use the model ID ernie-4.5-turbo-vl when calling Baidu Qianfan's API.

Who created ERNIE 4.5 Turbo VL?

ERNIE 4.5 Turbo VL was created by Baidu AI as part of the ERNIE 4.5 model family.

Is ERNIE 4.5 Turbo VL open source?

ERNIE 4.5 Turbo VL is open source under Apache 2.0 according to the seed data.

Get Started

Model Specs

Released2025-04-24
Context128k
ArchitectureMixture of Experts

Related Models on Baidu Qianfan