Baidu: ERNIE 4.5 VL 28B A3B

Public pricingIntelligence 79/100Small memoryالرؤيةاستخدام الأدوات

Baidu: ERNIE 4.5 VL 28B A3B هو نموذج متعدد الوسائط مخصص لـفهم الرؤية واللغة. يجمع بين معالجة الإدخال متعدد الوسائط، فهم الصور وسياق بحجم 30K tokens وملف منخفض التكلفة لتقديم عمل موثوق في vision-language understanding and content analysis. وهو خيار عملي عندما تكون الجودة والسرعة والتكلفة مهمة، خصوصًا للفرق التي تحتاج إلى مخرجات ثابتة ونشر مرن ومساحة للتوسع.

Input

$0.14/1M

Output

$0.56/1M

Cached

$0.01/1M

Batch

$0.05/1M

Calculate your ERNIE 4.5 VL 28B A3B bill.

Set your workload — see cost at your exact volume.

What would ERNIE 4.5 VL 28B A3B cost you?

Adjust the workload to see your monthly bill.

1,00010,00050,000250,0001M10M

Technical specifications

ERNIE 4.5 VL 28B A3B at a glance.

Memory

30,000

tokens

Max reply

8,000

tokens

Memory tier

Small

a few emails or a short document

Tokenizer

—

Released

Jun 2025

Training cutoff

Feb 2025

Availability

Public pricing

Status

active

What it can do

Capabilities & limits.

  • Understands images
  • Deep step-by-step thinking
  • Uses tools / calls functions
  • Strict JSON output
  • Streams replies
  • Fine-tunable on your data

When to pick ERNIE 4.5 VL 28B A3B

  • Screenshot analysis, image understanding, or document OCR.
  • Agentic workflows that call tools or APIs.
  • High-volume workloads where unit cost matters.
  • Multimodal pipelines mixing text + images.

When to look elsewhere

  • Your inputs routinely exceed short documents.

Alternatives

Similar models to compare.

FAQ

ERNIE 4.5 VL 28B A3B — the questions we see most.

Pricing, capabilities, alternatives — generated from the same data that powers the calculator above.

Get instant answers from our AI agent

At a typical workload of 50,000 conversations a month with 1,500-token prompts and 800-token replies, ERNIE 4.5 VL 28B A3B costs roughly $33 per month. Input is $0.14 /1M tokens and output is $0.56 /1M tokens.
ERNIE 4.5 VL 28B A3B has a 30,000-token context window (small memory — a few emails or a short document). That means you can fit about 5,625 words of input and history in a single call.
Beyond text generation, ERNIE 4.5 VL 28B A3B supports understanding images, calling functions / tools, strict JSON output, fine-tuning on your own data. It streams replies by default.
ERNIE 4.5 VL 28B A3B was released in June 2025, with training data cut off around February 2025.
Models in a similar class include ERNIE 4.5 VL 424B A47B, Qwen VL Plus, Gemma 4 31B. The "Similar models" section below this FAQ links into each.

Still unsure?

Compare ERNIE 4.5 VL 28B A3B against 100+ other models.

Open the full wizard — pick a use case, set your usage, and see side-by-side monthly costs in under a minute.

Open the comparison wizard