DeepSeek API pricing, October 2026: every model per million tokens
Input, cached and output prices for every DeepSeek model, DeepSeek's list price next to ours, and what a chat turn and a long-document request cost on V4 Pro, V4.1 Flash and V4 Flash.
How the DeepSeek API is priced
DeepSeek bills API calls per token, at three rates per million tokens: input, cached input and output. The Flash models cost cents per million tokens and Pro costs about a dollar in, so the model you pick moves the bill more than anything else. A request costs its tokens times the rates of the model it named; there is no seat or plan price.
Every DeepSeek model
6 DeepSeek models. Each row shows our price and DeepSeek's list price.
| Model | Input | Cached | Output | List input | List cached | List output |
|---|---|---|---|---|---|---|
| DeepSeek V4 Pro 0813 | $0.75 | $0.0625 | $1.188 | $1.32 | $0.044 | $3.96 |
| DeepSeek V4.1 Flash | $0.06 | $0.0063 | $0.18 | $0.15 | $0.003 | $0.60 |
| DeepSeek V4 Flash 0423 | $0.0279 | $0.0056 | $0.0558 | $0.0465 | $0.0093 | $0.093 |
| DeepSeek V4 Flash 0731 | $0.084 | $0.0033 | $0.09 | $0.14 | $0.0028 | $0.28 |
| DeepSeek V4 Flash Vision Exp | $0.132 | $0.0042 | $0.396 | $0.22 | $0.007 | $0.66 |
| DeepSeek V4 Pro 0423 | $0.96 | $0.081 | $1.92 | $1.60 | $0.135 | $3.20 |
USD per million tokens. Ours from the live catalog; list is the price on DeepSeek's pricing page, the read date on each model page.
The lowest price here is DeepSeek V4 Flash 0423: $0.0279 in and $0.0558 out.
Two requests, worked
A chat turn of 2,000 input and 500 output tokens, and a long-document request of 50,000 input and 2,000 output. Both sizes are assumptions; nothing is counted at the cached rate.
| Model | Chat turn, list | Chat turn, here | Long document, list | Long document, here |
|---|---|---|---|---|
| DeepSeek V4 Pro 0423 | $0.0048 | $0.0029 | $0.0864 | $0.0518 |
| DeepSeek V4.1 Flash | $0.0006 | $0.0002 | $0.0087 | $0.0034 |
| DeepSeek V4 Flash 0423 | $0.0001 | $0.0001 | $0.0025 | $0.0015 |
Input tokens times the input rate plus output tokens times the output rate, per million.
DeepSeek V4 Pro 0423: $0.96 in and $1.92 out here, against $1.60 and $3.20 at list, 40% under on input and 40% on output.
DeepSeek V4.1 Flash: $0.06 in and $0.18 out here, against $0.15 and $0.60 at list, 60% under on input and 70% on output.
DeepSeek V4 Flash 0423: $0.0279 in and $0.0558 out here, against $0.0465 and $0.093 at list, 40% under on input and 40% on output.
Cached input
When a request repeats a prefix the API has seen, such as a long system prompt or a document, the response reports those tokens as cached and they bill at the cached rate in the first table. A model with no cached rate bills them at its input rate.
Calling it
Point the SDK at our base URL with your key. Every DeepSeek id in the table works with the same two values.
from openai import OpenAI
client = OpenAI(
base_url="https://api.uplinkswitch.com/v1",
api_key="sk-uplink-live-...",
)
completion = client.chat.completions.create(
model="deepseek-v4-pro",
messages=[{"role": "user", "content": "Summarize this in one line."}],
)
print(completion.choices[0].message.content)More in the SDK guide.
Questions
Is there a subscription? No. Credit is prepaid from $10, and each top-up locks your prices for 30 days. New accounts start with $1 free.
Which DeepSeek model should I use? Flash for chat, summaries and agent subtasks, where the price per million is low enough to stop counting. Pro for code and reasoning where Flash gets it wrong. Run the same prompt on both and compare.
Where is the full price list? On the DeepSeek pricing page, and every other model on the Models page. To see what your own usage would cost, re-price an export on the savings page.