Baidu: ERNIE 4.5 300B A47B baidu
Bottom Line
Baidu: ERNIE 4.5 300B A47B : $0.28/1M input, $1.10/1M output, 131K context, CPS grade B. ERNIE-4.5-300B-A47B is a 300B parameter Mixture-of-Experts (MoE) language model developed by Baidu as part of the ERNIE 4.5 series. It activates 47B parameters per token and supports text generation in...
API Pricing (per 1M tokens)
| Input | $0.28 |
| Output | $1.10 |
| Cache Read | — |
| Cache Write | — |
| Blended (3:1) | $0.48 |
Specs & Performance
| Context Length | 131K |
| Max Output | 12K |
| Intelligence | 8 |
| Coding | 15 |
| Math | 41 |
| Speed | — |
| TTFT | — |
| CPS Grade | B |
| Input / Output Modalities | text → text |
More from baidu
Looking for cheaper alternatives?
Find the cheapest model by task, or compare two models head-to-head.
FAQ
How much does the Baidu: ERNIE 4.5 300B A47B API cost?
Baidu: ERNIE 4.5 300B A47B costs $0.28/1M input tokens and $1.10/1M output tokens. Blended cost at a 3:1 ratio is about $0.48/1M tokens.
What is the context window of Baidu: ERNIE 4.5 300B A47B ?
Baidu: ERNIE 4.5 300B A47B supports a 131K token context window with up to 12K output tokens.
Is Baidu: ERNIE 4.5 300B A47B worth it?
Baidu: ERNIE 4.5 300B A47B has a CPS grade of B (score 59), intelligence index 8, coding index 15. Use the compare page to benchmark against rivals.