DeepSeek · API pricing
DeepSeek API pricing
3 DeepSeek models on one OpenAI-compatible API, billed per token from a prepaid balance — no subscription. From €0.0672 per 100k input tokens and €0.1344 per 100k output tokens, margin and VAT included. DeepSeek V4 Flash 0731 and DeepSeek V4.1 Flash run on EU-sovereign infrastructure; DeepSeek V4 Pro is fast access, through US providers.
- Models live
- 3
- Input from
- €0.0672
- per 100k tokens
- Output from
- €0.1344
- per 100k tokens
- Largest context
- 1M
- DeepSeek V4.1 Flash
DeepSeek API pricing per model
per 100k tokens · margin and VAT included · from our live catalog when this page is built
| Model | Input | Output | Cached in | Context | Max output | Jurisdiction |
|---|---|---|---|---|---|---|
DeepSeek V4 Flash 0731deepseek-v4-flash-0731tools | €0.0672 | €0.1344 | €0.0135 | 256K | 32K | EU sovereign |
DeepSeek V4.1 Flashdeepseek-v4.1-flashtoolsvision | €0.1008 | €0.3024 | €0.0202 | 1M | 80K | EU sovereign |
DeepSeek V4 Prodeepseek-v4-protools | €0.2453 | €0.5124 | — | 1M | — | Fast access (US) |
Input, output and cached input are the prices debited from your prepaid balance per 100,000 tokens, margin and VAT included. Context is the window as served on Frontière AI; max output is the provider's cap on max_tokens (— when it sets none we know of). Tool calling is measured with a real call per model.
Where each DeepSeek model runs, and what DeepSeek's own API does with your data →DeepSeek API cost calculator
Pick a model and a workload, or type your own token counts: the estimate uses the prices in the table above, margin and VAT included.
Example workload
Roughly 1,000 tokens ≈ 750 English words.
Per request
€0.0015
Per day
€1.48
Per month
€44.35
30 days
A €10 top-up covers about 6,764 requests · DeepSeek V4 Flash 0731
Where the money goes
- Input€30.24 · 68%
- Output€14.11 · 32%
Estimate, margin and VAT included, from the prices on this page. You are billed on the tokens the provider reports for each call, debited from a prepaid balance — no subscription.
Same workload on every model
| Model | Per request | Per month | |
|---|---|---|---|
| DeepSeek V4 Flash 0731EU sovereign | €0.0015 | €44.35 | Selected |
| DeepSeek V4.1 FlashEU sovereign | €0.0026 | €77.11 | |
| DeepSeek V4 ProFast access (US) | €0.0055 | €164.18 |
Call DeepSeek models
The API is OpenAI-compatible: keep your SDK, change base_url and the key, and pass the model id. One key covers the whole catalog.
curl https://getfrontiereai.eu/api/v1/chat/completions \
-H "Authorization: Bearer $FRONTIERE_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-v4-flash-0731",
"messages": [{"role": "user", "content": "Bonjour"}]
}'import os
from openai import OpenAI
client = OpenAI(
base_url="https://getfrontiereai.eu/api/v1",
api_key=os.environ["FRONTIERE_KEY"],
)
reply = client.chat.completions.create(
model="deepseek-v4-flash-0731",
messages=[{"role": "user", "content": "Bonjour"}],
)
print(reply.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://getfrontiereai.eu/api/v1",
apiKey: process.env.FRONTIERE_KEY,
});
const reply = await client.chat.completions.create({
model: "deepseek-v4-flash-0731",
messages: [{ role: "user", content: "Bonjour" }],
});
console.log(reply.choices[0].message.content);Frequently asked
How much does the DeepSeek API cost?
On Frontière AI, DeepSeek models cost from €0.0672 to €0.2453 per 100,000 input tokens and from €0.1344 to €0.5124 per 100,000 output tokens, depending on the model — margin and VAT included, that is the amount debited from your prepaid balance. The table lists each model's price; the calculator turns it into a monthly cost for your workload.
Which DeepSeek model is the cheapest?
DeepSeek V4 Flash 0731, the cheapest on both input (€0.0672) and output (€0.1344) per 100k tokens.
Which DeepSeek model has the largest context window?
DeepSeek V4.1 Flash, with 1M tokens of context as served on Frontière AI.
Is the DeepSeek API hosted in Europe on Frontière AI?
Partly. Scaleway (France) for DeepSeek V4 Flash 0731 and AKI.IO (Germany) for DeepSeek V4.1 Flash: these are labeled EU sovereign. DeepSeek V4 Pro is served by US providers and labeled fast access — the API flags it before you call.
Is there a subscription or a minimum spend?
No subscription. You top up a prepaid balance from €10 and each call is debited at the per-token price. Calls are refused once the balance reaches zero; a call already running can take it slightly below — deducted from your next top-up.
Do I need to change my code to call DeepSeek models?
No, if your code already uses an OpenAI SDK: point base_url at https://getfrontiereai.eu/api/v1, use a Frontière AI key and pass the model id, for example “deepseek-v4-flash-0731”. Streaming and tool calling are relayed as-is.
How are cached input tokens billed?
DeepSeek V4 Flash 0731 and DeepSeek V4.1 Flash have a discounted rate for prompt tokens the provider serves from its cache (€0.0135 per 100k tokens on DeepSeek V4 Flash 0731). The provider reports these tokens on each call and we bill them at that rate; on a model without a cache rate, every input token is billed at the input rate.
Other providers
Per-token prices for every publisher in our catalog
All model prices on one page →Start calling DeepSeek in minutes
Create an account, top up €10, change two lines of code.