AI Rate CardDeepSeek V4.1 Flash · requesty
DeepSeek V4.1 Flash is a 552B parameter Mixture of Experts model built on a new Causal Encoder Decoder architecture that activates only 8B parameters for input and 16B for output, giving frontier level intelligence at a fraction of the cost. It is the smallest model in the new DeepSeek architecture family and the first Flash with native vision and multimodal understanding. V4.1 Flash beats DeepSeek V4 Pro on performance, cost, speed and task completion time and scores 88.1 on CyberGym. Its KV cache is compressed to 890 bytes per token, four times smaller than V4 Flash and over 400 times smaller than V1, cutting the cache hit costs that dominate agent workloads. 1M token context window, 384K max output, thinking and non thinking modes, tool calling, structured JSON output and prompt caching. Served in the EU via Sference at $0.50 input, $0.05 cache read and $1.50 output per 1M tokens, with no data retention and no training on user data. Open weights are published on Hugging Face. Ideal for EU hosted coding agents, long context RAG, high throughput batch processing and multimodal assistants.
Eingabe, $/1M $0.50
Ausgabe, $/1M $1.50
Cache-Lesen $0.05
Cache-Schreiben —
Kontext 1 048 576
Max. Ausgabe 393 216
Akzeptiert Bilder, Text
Zuletzt geprüft 04.11.2026 12:00:14 UTC
Quelle Seite des Anbieters
Preisalarme
API
OpenAI-kompatible API: Die offiziellen OpenAI-SDKs funktionieren mit dieser Basis-URL. Ersetzen Sie YOUR_API_KEY durch Ihren Schlüssel vom Anbieter.
| API-Basis-URL | |
|---|---|
| Endpunkt | |
| Modell-ID | |
curl
curl https://router.requesty.ai/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "sference/deepseek-v4.1-flash", "messages": [{"role": "user", "content": "Hello!"}], "max_tokens": 256}'Python
import requests
r = requests.post(
"https://router.requesty.ai/v1/chat/completions",
headers={"Authorization": "Bearer YOUR_API_KEY"},
json={
"model": "sference/deepseek-v4.1-flash",
"messages": [
{
"role": "user",
"content": "Hello!"
}
],
"max_tokens": 256
},
)
print(r.json())JavaScript
const r = await fetch("https://router.requesty.ai/v1/chat/completions", {
method: "POST",
headers: {Authorization: "Bearer YOUR_API_KEY", "Content-Type": "application/json"},
body: JSON.stringify({
"model": "sference/deepseek-v4.1-flash",
"messages": [
{
"role": "user",
"content": "Hello!"
}
],
"max_tokens": 256
}),
});
console.log(await r.json());Anfrage (JSON)
{
"model": "sference/deepseek-v4.1-flash",
"messages": [
{
"role": "user",
"content": "Hello!"
}
],
"max_tokens": 256
}Antwort (JSON)
{
"id": "chatcmpl-...",
"object": "chat.completion",
"model": "sference/deepseek-v4.1-flash",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "Hi! How can I help?"
},
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 9,
"completion_tokens": 12,
"total_tokens": 21
}
}Die Adresse stammt aus der Modellliste des Anbieters; bitte mit seiner Dokumentation abgleichen.
Source: AI Rate Card, https://airatecard.com/de/c/offer%3Arequesty%7Csference/deepseek-v4.1-flash, prices checked 2026-11-04; seller's page: https://www.requesty.ai/models/sference/deepseek-v4.1-flash
Technische Details
ID: offer:requesty|sference/deepseek-v4.1-flash