DeepSeek API: models and pricing
Pick up to 3 models · pricing, context and capabilities · simulate your product cost
Data updated on September 30, 2026· 217 models
15 DeepSeek chat models available by API, newest first, with price per million tokens, context and capabilities. Data as of 09/30/2026.
| # | Model | Provider | Input $/1M | Output $/1M | Context | Capabilities | Released |
|---|---|---|---|---|---|---|---|
| 1 | DeepSeek V4.1 Flash | DeepSeek | $0.300 | $1.20 | 1 M | 09/10/2026 | |
| 2 | DeepSeek V4 Flash Vision Exp | DeepSeek | $0.216 | $0.647 | 1 M | 08/21/2026 | |
| 3 | DeepSeek V4 Pro 0813 | DeepSeek | $0.660 | $1.98 | 1 M | 08/12/2026 | |
| 4 | DeepSeek V4 Flash 0731 | DeepSeek | $0.018 | $0.320 | 1 M | 07/31/2026 | |
| 5 | DeepSeek V4 Flash 0423 | DeepSeek | $0.140 | $0.280 | 1 M | 04/24/2026 | |
| 6 | DeepSeek V4 Pro 0423 | DeepSeek | $0.955 | $1.91 | 1 M | 04/24/2026 | |
| 7 | DeepSeek V3.2 | DeepSeek | $0.280 | $0.420 | 164 K | 12/01/2025 | |
| 8 | DeepSeek V3 | DeepSeek | $0.257 | $1.03 | 164 K | 12/01/2025 | |
| 9 | DeepSeek V3.2 Exp | DeepSeek | $0.270 | $0.410 | 164 K | 09/29/2025 | |
| 10 | DeepSeek V3.1 Terminus | DeepSeek | $0.300 | $1.00 | 164 K | 09/22/2025 | |
| 11 | DeepSeek V3.1 | DeepSeek | $0.250 | $0.950 | 164 K | 08/21/2025 | |
| 12 | R1 0528 | DeepSeek | $0.500 | $2.15 | 164 K | 05/28/2025 | |
| 13 | DeepSeek V3 0324 | DeepSeek | $0.290 | $1.14 | 164 K | 03/24/2025 | |
| 14 | R1 Distill Llama 70B | DeepSeek | $0.800 | $0.800 | 8 K | 01/01/2025 | |
| 15 | R1 | DeepSeek | $0.700 | $2.50 | 64 K | 01/01/2025 |
Frequently asked questions
How much does the DeepSeek API cost?
It depends on the model: from $0.018 to $0.955 per million input tokens. The cheapest is DeepSeek V4 Flash 0731 ($0.018 / $0.320); the newest is DeepSeek V4.1 Flash ($0.300 / $1.20). Data as of 09/30/2026.
How many DeepSeek models are available by API?
15 chat models in the catalog, as of 09/30/2026. Each one has its own sheet with pricing, context and capabilities.
Where do the prices come from and how often are they updated?
From the public catalogs of OpenRouter, models.dev and LiteLLM, which publish each provider's list prices. They sync once a day and the last update date is shown above the comparison.
What does price per million tokens mean?
It is what the provider charges per million tokens you send (input) or the model generates (output). A token is roughly 4 characters. Output almost always costs more than input.
Sources: OpenRouter, models.dev and LiteLLM. Prices in USD per million tokens, list price, no volume discounts. Prompt tokens are an estimate; each provider's tokenizer may differ.