ERNIE 4.5 300B A47B Intelligence, Performance & Price Analysis
Model summary
Intelligence
Artificial Analysis Intelligence Index
Speed
Output tokens per second
Input Price
USD per 1M tokens
Output Price
USD per 1M tokens
Verbosity
Output tokens from Intelligence Index
Metrics are compared against models of the same class:
- Non-reasoning models → compared only with other non-reasoning models
- Reasoning models → compared across both reasoning and non-reasoning
- Open weights models → compared only with other open weights models of the same size class:
- Tiny: ≤4B parameters
- Small: 4B–40B parameters
- Medium: 40B–150B parameters
- Large: >150B parameters
- Proprietary models → compared across proprietary and open weights models of the same price range, using a blended 3:1 input/output price ratio:
- <$0.15 per 1M tokens
- $0.15–$1 per 1M tokens
- >$1 per 1M tokens
| Reasoning | No This page shows the non-reasoning version of this model. A reasoning variant may also exist. |
|---|---|
| Input modality | Supports: text This information is still being updated |
| Output modality | Supports: text This information is still being updated |
| Context window | 131k ~197 A4 pages of size 12 Arial font |
| Total parameters | 300B |
| Active parameters | 47B Number of parameters active per token during inference |
| License | Apache 2.0 |
| Model weights | Hugging Face |
ERNIE 4.5 300B A47B is below average in intelligence, but reasonably priced when comparing to other open weight non-reasoning models of similar size. It's also notably slow, however highly concise. The model supports text input, outputs text, and has a 131k tokens context window.
ERNIE 4.5 300B A47B scores 15 on the Artificial Analysis Intelligence Index, placing it below average among comparable models (averaging 22). When evaluating the Intelligence Index, it generated 2.3M tokens, which is very concise in comparison to the average of 8.1M.
Pricing for ERNIE 4.5 300B A47B is $0.28 per 1M input tokens (moderately priced, average: $0.56) and $1.10 per 1M output tokens (moderately priced, average: $1.59). In total, it cost $8.09 to evaluate ERNIE 4.5 300B A47B on the Intelligence Index.
At 34 tokens per second, ERNIE 4.5 300B A47B is notably slow (53).
Intelligence
Artificial Analysis Intelligence Index
Artificial Analysis Intelligence Index by Open Weights / Proprietary
Intelligence Evaluations
Openness
Artificial Analysis Openness Index: Results
Intelligence Index Comparisons
Intelligence vs. Price
Intelligence Index Token Use & Cost
Output Tokens Used to Run Artificial Analysis Intelligence Index
Cost to Run Artificial Analysis Intelligence Index
Context Window
Context Window
Pricing
Pricing: Input and Output Prices
Intelligence vs. Price (Log Scale)
Pricing Comparison of ERNIE 4.5 300B A47B API Providers
Speed
Measured by Output Speed (tokens per second)
Output Speed
Output Speed vs. Price
Latency
Measured by Time (seconds) to First Token
Latency: Time To First Answer Token
End-to-End Response Time
Seconds to output 500 Tokens, calculated based on time to first token, 'thinking' time for reasoning models, and output speed
End-to-End Response Time
Model Size (Open Weights Models Only)
Model Size: Total and Active Parameters
Frequently Asked Questions
Common questions about ERNIE 4.5 300B A47B
ERNIE 4.5 300B A47B was released on June 30, 2025.
ERNIE 4.5 300B A47B was created by Baidu.
ERNIE 4.5 300B A47B scores 15 on the Artificial Analysis Intelligence Index, placing it below average among other open weight non-reasoning models of similar size (median: 22).
ERNIE 4.5 300B A47B generates output at 33.5 tokens per second (based on the median across providers serving the model), which is at the lower end compared to other open weight non-reasoning models of similar size (median: 52.8 t/s).
ERNIE 4.5 300B A47B has a time to first token (TTFT) of 7.34s (based on the median across providers serving the model), which is at the higher end compared to other open weight non-reasoning models of similar size (median: 1.90s).
ERNIE 4.5 300B A47B costs $0.28 per 1M input tokens (very competitive, median: $0.60) and $1.10 per 1M output tokens (very competitive, median: $2.33), based on the median across providers serving the model.
ERNIE 4.5 300B A47B costs $0.28 per 1M input tokens and $1.10 per 1M output tokens (based on the median across providers serving the model). For a blended rate (3:1 input to output ratio), this is $0.48 per 1M tokens. Pricing may vary by provider. Compare provider pricing
When evaluated on the Intelligence Index, ERNIE 4.5 300B A47B generated 2.3M output tokens, which is very competitive compared to other open weight non-reasoning models of similar size (median: 8.1M).
No, ERNIE 4.5 300B A47B is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
ERNIE 4.5 300B A47B supports text input.
ERNIE 4.5 300B A47B supports text output.
No, ERNIE 4.5 300B A47B does not support image input. It can only process text.
No, ERNIE 4.5 300B A47B is not multimodal. It only supports text input.
ERNIE 4.5 300B A47B has a context window of 130k tokens. This determines how much text and conversation history the model can process in a single request.
Yes, ERNIE 4.5 300B A47B is open weights. The model weights are publicly available and can be downloaded for self-hosting.
ERNIE 4.5 300B A47B has 300 billion parameters (47 billion active).
ERNIE 4.5 300B A47B is a Mixture of Experts (MoE) model with 300 billion total parameters, but only 47 billion active parameters are used during inference.
ERNIE 4.5 300B A47B is released under the Apache 2.0 license. This license allows commercial use. View license
ERNIE 4.5 300B A47B achieves a score of 15 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Yes, ERNIE 4.5 300B A47B is available via API through 2 providers. Compare API providers
ERNIE 4.5 300B A47B is available through 2 API providers. Compare providers