ERNIE 4.5 VL 424B A47B
Baidu · baidu/ernie-4.5-vl-424b-a47b
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...
ERNIE 4.5 VL 424B A47B ranks #187 of 348 models in the default AI Benchmark Hub order (quality first, then cost). At $0.83 blended per million tokens, it is cheaper than 56% of models with published API pricing. Its 123,000-token context window is 2.1× smaller than the catalog median (262,144 tokens).
Context
Max output: 16000
Pricing
Output / 1M: 1.25
Blend / 1M: 0.83
Quality
Provider
Moderated: no
Monthly cost at this blended rate
Estimated API spend if every token is billed at $0.83per million (the blend of this model's input and output prices). Real bills depend on the input/output mix.
| Tokens / month | Est. cost (USD) |
|---|---|
| 1,000,000 | $0.83 |
| 10,000,000 | $8.35 |
| 100,000,000 | $83.50 |
Related models
Same lab, similar price, or similar quality — useful next comparisons.
Closest API price
- Qwen2.5 Coder 32B Instruct$0.83 / 1M
- Inkling Small$0.82 / 1M
- Perceptron Mk1$0.82 / 1M
- Llama 3.1 Euryale 70B v2.2$0.85 / 1M
- Qwen3.7 Plus$0.80 / 1M · Q 78.7