ERNIE 4.5 VL 424B A47B pricing & benchmarks
Released Jun 30, 2025 · served by 1 provider
What ERNIE 4.5 VL 424B A47B is
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...
- Model ID:
baidu/ernie-4.5-vl-424b-a47b - Modality: text+image->text
- Knowledge cutoff: 2025-03-31
- Tool calling: not supported · Structured output: not supported
- Weights:
baidu/ERNIE-4.5-VL-424B-A47B-PTon Hugging Face
Providers and prices for ERNIE 4.5 VL 424B A47B
The same model costs different amounts depending on who serves it. Prices are per 1M tokens, cheapest first. Uptime and throughput are OpenRouter's rolling measurements, not vendor claims.
| Provider | Input | Output | Context | Quant | Uptime 24h | Throughput |
|---|---|---|---|---|---|---|
| Novitacheapest | $0.420 | $1.25 | 123K | fp16 | 100.0% | — |
FAQ
How much does the ERNIE 4.5 VL 424B A47B API cost?
$0.420 per 1M input tokens and $1.25 per 1M output tokens. A typical workload of 1M input + 300K output tokens costs about $0.80.
Is ERNIE 4.5 VL 424B A47B free?
No. It is a paid model starting at $0.420 per 1M input tokens, though some providers offer trial credits.
Which provider is cheapest for ERNIE 4.5 VL 424B A47B ?
Novita at $0.420 input / $1.25 output per 1M tokens (fp16 quantization).
Can I self-host ERNIE 4.5 VL 424B A47B ?
Yes — weights are published as baidu/ERNIE-4.5-VL-424B-A47B-PT on Hugging Face, so you can run it on your own hardware.