Models & Pricing
The prices listed below are in units of per 1M tokens. A token, the smallest unit of text that the model recognizes, can be a word, a number, or even a punctuation mark. We will bill based on the total number of input and output tokens by the model.
Model Details
| MODEL | deepseek-chat | deepseek-reasoner | deepseek-reasoner(1) | |
| BASE URL | https://api.deepseek.com | https://api.deepseek.com/ v3.2_speciale_expires_on_20251215 | ||
| MODEL VERSION | DeepSeek-V3.2 (Non-thinking Mode) | DeepSeek-V3.2 (Thinking Mode) | DeepSeek-V3.2-Speciale （Thinking Mode Only） | |
| CONTEXT LENGTH | 128K | |||
| MAX OUTPUT | DEFAULT: 4K MAXIMUM: 8K | DEFAULT: 32K MAXIMUM: 64K | DEFAULT: 128K MAXIMUM: 128K | |
| FEATURES | Json Output | ✓ | ✓ | ✗ |
| Tool Calls | ✓ | ✓ | ✗ | |
| Chat Prefix Completion（Beta） | ✓ | ✓ | ✗ | |
| FIM Completion（Beta） | ✓ | ✗ | ✗ | |
| PRICING | 1M INPUT TOKENS (CACHE HIT) | $0.028 | ||
| 1M INPUT TOKENS (CACHE MISS) | $0.28 | |||
| 1M OUTPUT TOKENS | $0.42 | |||
- (1) Users can access the DeepSeek-V3.2-Speciale model by setting
base_url="https://api.deepseek.com/v3.2_speciale_expires_on_20251215". This model only supports thinking mode and will be available until December 15, 2025, 15:59 UTC.
Deduction Rules
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.
Product prices may vary and DeepSeek reserves the right to adjust them. We recommend topping up based on your actual usage and regularly checking this page for the most recent pricing information.