baidu

Baidu: ERNIE 4.5 VL 424B A47B

ERNIE 4.5 VL 424B from Baidu is designed for both text and image inputs with an extensive context length of 123,000 tokens, enabling sophisticated reasoning tasks. It supports complex reasoning but lacks structured output or tools integration, focusing on natural language processing and multimodal understanding. Given its price at $0.42 per million input tokens and $1.25 per million output tokens, this model is cost-effective for applications requiring extended context analysis and reasoning capabilities. However, with no independent benchmark coverage to date, its performance remains unproven in comparison studies, making it a solid choice primarily for those who can afford the price without needing detailed benchmark data.

Quality Score
79/100
price + capability + benchmarks
Input Price
$0.42
per 1M tokens
Output Price
$1.25
per 1M tokens
Context Window
123,000
tokens
Model ID
baidu/ernie-4.5-vl-424b-a47b
Vendor
baidu
Released
June 2025
Tokenizer
Other
Input Modalities
image, text
Output Modalities
text
Max Output
16,000 tokens
Tool Calling
not supported
Structured Output
not supported
Reasoning Mode
✓ supported
Vision
✓ accepts images
Audio
no
Moderated
no

What it costs in practice

Computed from the current $0.42/M input and $1.25/M output rates. Run your own numbers →

JobTokensCost
Summarize a 50-page report 30k in / 1.5k out $0.01
Classify 1,000 customer emails 500k in / 50k out $0.27
A month of a busy support chatbot 5M in / 2M out $4.60

Price & spec history

Tracked daily by PicksByModel since 2026-07-17.

DateInput /MOutput /MContext
2026-07-22 $0.42 $1.25 123,000
2026-07-17 $0.42 $1.25 131,072

Quick answers

How much does Baidu: ERNIE 4.5 VL 424B A47B cost?
$0.42 per million input tokens and $1.25 per million output tokens.
What is Baidu: ERNIE 4.5 VL 424B A47B 's context window?
123,000 tokens, roughly 184 pages of text in a single request.
Does Baidu: ERNIE 4.5 VL 424B A47B support tool calling?
It supports a reasoning mode.
Can Baidu: ERNIE 4.5 VL 424B A47B process images?
Yes, it accepts image input.