Context
123K tokens (~62 books)
Input $/1M
$0.42
Output $/1M
$1.25
Type
multimodal
License
Open Source
Benchmarks
0 tested
Data as of
About
ERNIE-4.5-VL-424B-A47B is a multimodal Mixture-of-Experts (MoE) model from Baidu’s ERNIE 4.5 series, featuring 424B total parameters with 47B active per token. It is trained jointly on text and image data...
No benchmark data available yet.
Links
Research
Documentation
Community
Source Code
BenchGecko API
ernie-4-5-vl-424b-a47b
Specifications
- Typemultimodal
- Context123K tokens (~62 books)
- ReleasedJun 2025
- LicenseOpen Source
- StatusActive
- Cost / Message~$0.002
Available On
Share & Export
Frequently Asked Questions
ERNIE 4.5 VL 424B A47B is an open-source multimodal AI model by baidu, released in June 2025. Context window: 123K tokens.
Related Models
Qwen3 Coder Next FP8 · AlibabaQwen2.5 Coder 32B Instruct AWQ · AlibabaSpeaker Diarization Community 1 · PyannoteGemma 3 12B (free) · Google DeepMindQwen3 Next 80B A3B Instruct (free) · Alibaba QwenBenchmarks
Key facts · as of 2026-10-05
- ERNIE 4.5 VL 424B A47B by baidu. Not enough public benchmark scores to rank yet.
- List price $0.42 input · $1.25 output per 1M tokens (as of 2026-10-05).
- Sold by 1 provider (as of 2026-10-05): Novita (fp16) $0.42 in / $1.25 out.
How to cite · data as of 2026-10-05
ERNIE 4.5 VL 424B A47B · benchmarks, pricing and providers. BenchGecko, data as of 2026-10-05. https://benchgecko.ai/model/ernie-4-5-vl-424b-a47b
Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP