Capabilities
7-day heat trend
−5.3%Pricing breakdown
Typical 3:1 output-to-input mix, per 1M tokens
Estimated monthly cost by workload
Market position
- Cheaper than 25% of tracked models
- Faster than 27% of tracked models
- Efficiency rank: #252 of 1105
Best suited for
General-purpose text generation, chat, summarization and content workloads where broad capability and low cost matter most.
About ernie-4.5-300b-a47b
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...
ernie-4.5-300b-a47b is a Text model from Baidu Wenxin (CN). HotON.ai tracks it at $0.28 per 1M input tokens and $1.11 per 1M output tokens, with a 131K-token context window, ~136 tokens/sec throughput and 99.8% availability. Its composite efficiency score is 89/100 at an estimated $0.001 per successful task.
Compare ernie-4.5-300b-a47b
Related market news
Frequently asked questions
How much does ernie-4.5-300b-a47b cost per 1M tokens?+
ernie-4.5-300b-a47b is tracked at $0.28 per 1M input tokens and $1.11 per 1M output tokens. A typical 3:1 output-to-input workload blends to roughly $0.90 per 1M tokens. Figures are illustrative demo data.
What is ernie-4.5-300b-a47b best for?+
General-purpose text generation, chat, summarization and content workloads where broad capability and low cost matter most.
How fast is ernie-4.5-300b-a47b?+
ernie-4.5-300b-a47b delivers about 136 tokens/sec with 99.8% tracked availability, suitable for latency-sensitive, real-time applications.
Is ernie-4.5-300b-a47b cheaper than other AI models?+
Within the HotON.ai tracked set, ernie-4.5-300b-a47b is cheaper than 25% of models on input price and ranks #252 of 1105 by overall efficiency.
Related models
Pricing is real (via the TestKey catalog, updated daily). Quality (Arena Elo) is real where the model is ranked on LMArena. Speed, availability and efficiency are modeled estimates.