DeepSeek API Pricing FAQ
What models are available?
DeepSeek offers two main models: deepseek-chat (DeepSeek-V3) and deepseek-reasoner (DeepSeek-R1).
What are the context lengths?
Both models support up to 64K tokens of context.
What is Chain of Thought (CoT)?
CoT is the reasoning content deepseek-reasoner provides before outputting the final answer. It helps the model to break down complex problems into smaller steps. For more information, see the Reasoning Model documentation.
What is Context Caching?
Context Caching can reduce costs by caching previously seen context, resulting in cheaper fees for cached inputs. Ideal for chatbots and long conversations. The service runs automatically, and billing is based on actual cache hits. For more details, check the Context Caching documentation.
How do the discount periods work?
DeepSeek offers significant discounts (50% off for deepseek-chat, 75% off for deepseek-reasoner) during off-peak hours (16:30-00:30 UTC daily).
How do deduction rules work?
The expense = number of tokens × price. The corresponding fees will be directly deducted from your topped-up balance or granted balance, with a preference for using the granted balance first when both balances are available. For more details, check the Deduction Rules documentation.