DeepSeek API: models and pricing
Pick up to 3 models · pricing, context and capabilities · simulate your product cost
Data updated on November 14, 2026· 230 models
16 DeepSeek chat models available by API, newest first, with price per million tokens, context and capabilities. Data as of 11/14/2026.
The cheapest DeepSeek API model is DeepSeek V4.1 Flash 1017 ($0.038 input and $0.500 output per million tokens). The newest is DeepSeek V4.1 Flash 1017. Prices range from $0.038 to $0.900 per million input tokens. Data as of 11/14/2026.
Input price range
$0.038 – $0.900
per million input tokens
Cheapest model
DeepSeek V4.1 Flash 1017
$0.038 / $0.500
≈ $2.57/month in the example
Newest model
DeepSeek V4.1 Flash 1017
$0.038 / $0.500
≈ $2.57/month in the example
Cached input
$0.010 −74 %
per million tokens on DeepSeek V4.1 Flash 1017; 13 models with cache price
Prices are input / output in USD per million tokens. Example: 10,000 requests a month of 1,500 input + 400 output tokens.
DeepSeek vs other AI APIs: the cheapest of each
The cheapest recent model of each provider, next to DeepSeek V4.1 Flash 1017.
| Provider | Model | Input $/1M | Output $/1M | |
|---|---|---|---|---|
| DeepSeek | DeepSeek V4.1 Flash 1017 | $0.038 | $0.500 | |
| Qwen | Qwen3.7 Flash | $0.030 | $0.130 | Compare |
| Gemma 4 26B A4B | $0.068 | $0.225 | Compare | |
| OpenAI | GPT-6 Luna Pro | $0.100 | $0.500 | Compare |
| Anthropic | Claude Haiku 5.5 | $0.100 | $0.500 | Compare |
| Mistral | Ministral 3 3B 2512 | $0.100 | $0.100 | Compare |
| Moonshot | Kimi K3 | $0.192 | $16.00 | Compare |
| xAI | Grok Build 0.1 | $1.00 | $2.00 | Compare |
| # | Model | Provider | Input $/1M | Output $/1M | Context | Capabilities | Released |
|---|---|---|---|---|---|---|---|
| 1 | DeepSeek V4.1 Flash 1017 | DeepSeek | $0.038 | $0.500 | 1 M | 10/17/2026 | |
| 2 | DeepSeek V4.1 Flash | DeepSeek | $0.051 | $0.203 | 1 M | 09/10/2026 | |
| 3 | DeepSeek V4 Flash Vision Exp | DeepSeek | $0.440 | $1.32 | 1 M | 08/21/2026 | |
| 4 | DeepSeek V4 Pro 0813 | DeepSeek | $0.111 | $4.44 | 1 M | 08/13/2026 | |
| 5 | DeepSeek V4 Flash 0731 | DeepSeek | $0.043 | $0.300 | 1 M | 07/31/2026 | |
| 6 | DeepSeek V4 Pro 0423 | DeepSeek | $0.900 | $1.50 | 1 M | 04/24/2026 | |
| 7 | DeepSeek V4 Flash 0423 | DeepSeek | $0.090 | $0.180 | 1 M | 04/24/2026 | |
| 8 | DeepSeek V3.2 | DeepSeek | $0.260 | $0.380 | 164 K | 12/01/2025 | |
| 9 | DeepSeek V3 | DeepSeek | $0.257 | $1.03 | 164 K | 12/01/2025 | |
| 10 | DeepSeek V3.2 Exp | DeepSeek | $0.270 | $0.410 | 164 K | 09/29/2025 | |
| 11 | DeepSeek V3.1 Terminus | DeepSeek | $0.270 | $1.00 | 164 K | 09/22/2025 | |
| 12 | DeepSeek V3.1 | DeepSeek | $0.250 | $0.950 | 164 K | 08/21/2025 | |
| 13 | R1 | DeepSeek | $0.700 | $2.50 | 64 K | 08/05/2025 | |
| 14 | R1 0528 | DeepSeek | $0.500 | $2.15 | 164 K | 05/28/2025 | |
| 15 | DeepSeek V3 0324 | DeepSeek | $0.290 | $1.14 | 164 K | 03/24/2025 | |
| 16 | R1 Distill Llama 70B | DeepSeek | $0.800 | $0.800 | 8 K | 01/01/2025 |
More free tools
See allFrequently asked questions
How much does the DeepSeek API cost?
It depends on the model: from $0.038 to $0.900 per million input tokens. The cheapest is DeepSeek V4.1 Flash 1017 ($0.038 / $0.500); the newest is DeepSeek V4.1 Flash 1017 ($0.038 / $0.500). Data as of 11/14/2026.
Is the DeepSeek API free?
No: the DeepSeek API is pay-as-you-go, billed per million tokens. The cheapest model, DeepSeek V4.1 Flash 1017, costs $0.038 per million input tokens and $0.500 per million output tokens, so light use costs cents. Any free credits depend on DeepSeek's own offer.
Does the DeepSeek API charge less for cached input?
Yes, on 13 of its 16 models. For example, DeepSeek V4.1 Flash 1017 charges $0.010 per million cached input tokens instead of $0.038: 74% less. The cache applies when you resend the same beginning of a prompt, like a long system prompt or a document.
How much does the DeepSeek API cost per month?
For 10,000 requests a month of 1,500 input tokens and 400 output tokens: DeepSeek V4.1 Flash 1017 costs about $2.57 and DeepSeek V4.1 Flash 1017 about $2.57. Each model's page has a calculator for your own numbers.
How many DeepSeek models are available by API?
16 chat models in the catalog, as of 11/14/2026. 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.