Baidu API Pricing (Updated 2025)

This page tracks Baidu API pricing for all 3 models. Prices are shown per 1,000 tokens (cost per token) with clear examples so you can estimate spend quickly.

Current Prices (per 1,000 tokens)

Model
Input ($/1K tokens)
Output ($/1K tokens)
Context Length
ernie-4.5-21b-a3b
$0.000070
$0.000280
120,000
ernie-4.5-300b-a47b
$0.000280
$0.001100
123,000
ernie-4.5-vl-28b-a3b
$0.000140
$0.000560
30,000

* Some models use tiered pricing based on prompt length. Displayed prices are for prompts ≤ 200k tokens.

What does "cost per token" mean?

Tokens are the basic units that AI models use to process text. Generally, 1,000 tokens ≈ ~750 words. The cost per token determines how much you pay for each unit of text processed by the model.

Formula: Total Cost = (tokens / 1,000) × price per 1K tokens

Examples

Example usage: A 500-word prompt + 300-word response ≈ ~1,067 tokens total.

  • • 1,000 tokens ≈ ~750 words of text
  • • Short email: ~200-400 tokens
  • • Blog post: ~1,000-3,000 tokens
  • • Research paper: ~10,000+ tokens

Compare with Other Providers

See how Baidu compares with other AI providers including OpenAI, Anthropic, Google, and more.

View full pricing comparison →

Frequently Asked Questions

Currently, ernie-4.5-21b-a3b is the most affordable at $0.000070 per 1,000 input tokens.
Count your input tokens (prompt) and expected output tokens (response). Use the formula: (input_tokens/1000 × input_price) + (output_tokens/1000 × output_price). Our pricing calculator can help automate this.
Baidu pricing varies by model. Input costs range from $0.000070 to $0.000280 per 1,000 tokens. See the table above for specific model pricing.