Context Window
131,072
Input tokens
Full-context input ≈ $0.01
Model Cost Profile
Developer: baidu· Tokenizer: Other · Quantization: fp8
Canonical ID: baidu/ernie-4.5-21b-a3b-thinking
Pricing updated Apr 24, 2026
Live Pricing
Input: $0.0700
Output: $0.2800
Last synced Apr 24, 2026
Baidu's ERNIE 4.5 21B A3B Thinking model features an extensive context window of 131,072 tokens, making it suitable for complex applications such as long-form content generation, detailed report analysis, and comprehensive conversational agents. With an input price of $0.07 per 1 million tokens and an output price of $0.28 per 1 million tokens, teams can effectively manage costs while leveraging the model for high-volume tasks. This pricing structure allows organizations to scale their usage according to project needs, optimizing budget allocations for AI-driven solutions.
Context Window
131,072
Input tokens
Full-context input ≈ $0.01
Max Output
65,536
Completion tokens
Input Price / 1M
$0.0700
Prompt tokens
Output Price / 1M
$0.2800
Completion tokens
Top Benchmark
Pending
No benchmark data yet
Price History
Current Input / 1M
$0.0700
Current Output / 1M
$0.2800
Performance History
Not enough data yet. Performance tracking started recently — check back in a few days.
| Usage Type | Price / 1M Tokens |
|---|---|
| Input (Prompt) | $0.0700 |
| Output (Completion) | $0.2800 |
Estimate monthly spend for Baidu: ERNIE 4.5 21B A3B Thinking based on your workload.
Estimated Monthly Cost
$5.11
25M input + 12M output tokens
Quick links for cost-down decisions before production rollout.