Skip to main content
idapt
HomeCodeAI ModelsPricing
Sign inStart free
Baidu

ERNIE 4.5 VL 28B

$Affordable
Baidu
CompareChat

Compact vision-language MoE model from Baidu — 28B total, 3B active. Efficient multimodal model for Chinese-English visual tasks with fast inference.

Best forVision tasks

Benchmarks

No benchmarks available

This model hasn't been evaluated by Artificial Analysis yet. Benchmark scores will appear once they're published.

Specifications

Vision
Audio
Reasoning
MoE
Architecture
28B
Parameters
3B
Active
30K
Context
8K
Max output

Providers

CompareChat with ERNIE 4.5 VL 28B

Compare with

OpenAIGPT 6 Astravs ERNIE 4.5 VL 28BOpenAIGPT 5.6 Lunavs ERNIE 4.5 VL 28BAnthropicClaude Fable 5.1vs ERNIE 4.5 VL 28BAnthropicClaude Opus 5vs ERNIE 4.5 VL 28BAnthropicClaude Sonnet 5vs ERNIE 4.5 VL 28BAnthropicClaude Haiku 4.5vs ERNIE 4.5 VL 28BGoogleGemini 3.8 Flashvs ERNIE 4.5 VL 28BGoogleGemini 3.5 Flashvs ERNIE 4.5 VL 28BGoogleGemini 3.5 Flash-Litevs ERNIE 4.5 VL 28BGoogleGemma 4 31Bvs ERNIE 4.5 VL 28BxAIGrok 4.6vs ERNIE 4.5 VL 28BxAIGrok Build 0.1vs ERNIE 4.5 VL 28BxAIGrok 4.1 Fastvs ERNIE 4.5 VL 28BMetaMuse Spark 1.3vs ERNIE 4.5 VL 28BDeepSeekDeepSeek V4 Pro (0813)vs ERNIE 4.5 VL 28BDeepSeekDeepSeek V4 Flashvs ERNIE 4.5 VL 28BMiniMaxMiniMax M3vs ERNIE 4.5 VL 28BMoonshotAIKimi K3vs ERNIE 4.5 VL 28BMoonshotAIKimi K2.7 Codevs ERNIE 4.5 VL 28BZhipu AIGLM 5.3vs ERNIE 4.5 VL 28BZhipu AIGLM 5.3 Flashvs ERNIE 4.5 VL 28BQwenQwen3.8 Max (0902)vs ERNIE 4.5 VL 28BQwenQwen3.7 Plusvs ERNIE 4.5 VL 28BQwenQwen3 Coder Nextvs ERNIE 4.5 VL 28BNVIDIANemotron 3 Ultravs ERNIE 4.5 VL 28B
Frequently Asked Questions about ERNIE 4.5 VL 28B▼

Who created ERNIE 4.5 VL 28B?

▼

ERNIE 4.5 VL 28B was created by Baidu.

Is ERNIE 4.5 VL 28B a reasoning model?

▼

No, ERNIE 4.5 VL 28B is not a reasoning model. It responds directly without an extended internal thinking step. For tasks requiring deep chain-of-thought reasoning, consider models like Claude, o-series from OpenAI, or Gemini Thinking.

Does ERNIE 4.5 VL 28B support image or vision input?

▼

Yes, ERNIE 4.5 VL 28B supports vision/image input. You can share images in your conversation and the model will analyze and respond based on their content.

Does ERNIE 4.5 VL 28B support audio?

▼

No, ERNIE 4.5 VL 28B does not support audio input.

What is the context window of ERNIE 4.5 VL 28B?

▼

ERNIE 4.5 VL 28B has a context window of 30K tokens, meaning it can process approximately 22,500 words of context at once.

Is ERNIE 4.5 VL 28B open source?

▼

ERNIE 4.5 VL 28B is a proprietary model developed by Baidu. The model weights and training data are not publicly available.

What is ERNIE 4.5 VL 28B good at?

▼

Based on benchmark data, ERNIE 4.5 VL 28B excels at: visual analysis and image understanding. It is Baidu's capable model suitable for a wide range of tasks.

Where can I use ERNIE 4.5 VL 28B?

▼

You can chat with ERNIE 4.5 VL 28B on idapt.app — no separate API key required. idapt is an AI workspace with 200+ models, agents, computers, and tasks. You can also access ERNIE 4.5 VL 28B through Baidu's own API or platform.

  • Home
  • Pricing
  • AI Models
  • Image models
  • Voice models
  • Video models
  • Rankings
  • New models
  • Model status
  • Multi-Model Chat
  • Agents
  • Computers
  • Drive
  • Automations
  • AI Gateway
  • All features →
  • LLM cost calculator
  • Token counter
  • All free tools →
  • Blog
  • Use cases
  • Comparisons
  • Best of
  • Benchmarks
  • Demos
  • Changelog
  • Help center
  • FAQ
  • Privacy
  • Compare all models
  • Support
  • idapt Code
  • Developers
  • Quickstarts
  • API reference
  • API pricing
  • CLI
  • MCP
  • Downloads
  • Desktop
  • Badges and embeds
© idapt[email protected]TermsPrivacy PolicyLegal noticeReport content
X (Twitter)