Percentage of input tokens that are cached (up to 90% cheaper).
Estimated Monthly Cost
Based on 1 requests
Understanding DeepSeek API Pricing
DeepSeek has disrupted the AI market with its incredibly low pricing for high-performance models. DeepSeek-V3 offers GPT-4 class performance at a fraction of the cost, while DeepSeek-R1 provides advanced reasoning capabilities.
DeepSeek API Pricing Overview
| Model | Input Price ($/1M) | Output Price ($/1M) | Cached Input ($/1M) |
|---|---|---|---|
| DeepSeek Models | |||
| DeepSeek-V3 | $0.14 | $0.28 | $0.014 |
| DeepSeek-R1 (Reasoning) | $0.55 | $2.19 | $0.14 |
DeepSeek-V3: The Efficiency King
DeepSeek-V3 is designed for general-purpose tasks, coding, and chat. Its pricing is extremely competitive, making it an excellent choice for high-volume applications.
- Input: $0.14 per 1M tokens
- Output: $0.28 per 1M tokens
- Context Caching: Massive savings with a 90% discount on cached inputs ($0.014/1M).
DeepSeek-R1: Advanced Reasoning
DeepSeek-R1 is a reasoning model capable of complex problem-solving, math, and logic tasks, similar to OpenAI's o1 series but at a much lower price point.
Comparison: DeepSeek vs. OpenAI
DeepSeek-V3 is significantly cheaper than GPT-4o ($5.00/$15.00) and even undercuts GPT-4o mini ($0.15/$0.60) on output costs. For developers looking to maximize ROI, DeepSeek is a compelling alternative.
DeepSeek API Pricing FAQs
Got questions? We've got answers. Here are the most common questions we get from potential clients.