Context Window
123,000
Input tokens
Full-context input ≈ $0.03
Model Cost Profile
Developer: baidu· Tokenizer: Other · Quantization: bf16
Canonical ID: baidu/ernie-4.5-300b-a47b
Pricing updated Apr 24, 2026
Live Pricing
Input: $0.2800
Output: $1.10
Last synced Apr 24, 2026 · MMLU score via public benchmark data
Baidu's ERNIE 4.5 300B A47B model features an extensive context window of 123,000 tokens, making it suitable for applications requiring in-depth analysis and understanding of lengthy documents or conversations. With an input price of $0.28 per million tokens and an output price of $1.10 per million tokens, teams can effectively budget for high-volume processing tasks, such as content generation, summarization, and complex query handling. This model is particularly advantageous for enterprises needing to integrate advanced natural language processing capabilities into their products while managing operational costs efficiently.
Context Window
123,000
Input tokens
Full-context input ≈ $0.03
Max Output
12,000
Completion tokens
Input Price / 1M
$0.2800
Prompt tokens
Output Price / 1M
$1.10
Completion tokens
Top Benchmark
81.1
GPQA score — highest of MMLU, GPQA, MATH, HumanEval
Evaluation scores for Baidu: ERNIE 4.5 300B A47B . The “Top Benchmark” shown above is the highest score across MMLU, GPQA, MATH & HumanEval.
Price History
Current Input / 1M
$0.2800
Current Output / 1M
$1.10
Performance History
Current TPS
0.00
Current Latency
0ms
Uptime
100.0%
| Usage Type | Price / 1M Tokens |
|---|---|
| Input (Prompt) | $0.2800 |
| Output (Completion) | $1.10 |
Estimate monthly spend for Baidu: ERNIE 4.5 300B A47B based on your workload.
Estimated Monthly Cost
$20
25M input + 12M output tokens
Quick links for cost-down decisions before production rollout.