DeepSeek V4.1 Flash · requesty

Name: DeepSeek V4.1 Flash
Brand: DeepSeek
Price: 0.3 USD
Availability: InStock

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 on DeepInfra in FP8 at $0.20 input, $0.006 cache read and $0.60 output per 1M tokens, with a flex tier at 0.8x. Open weights are published on Hugging Face. Ideal for coding agents, long context RAG, high throughput batch processing and multimodal assistants.

Modelo base Todos os modelos desta base Todos os modelos do provedor ao provedor

Entrada, $/1M $0.30

Saída, $/1M $1.20

Leitura de cache $0.01

Gravação de cache —

Contexto 1 048 576

Aceita imagens, texto

Última verificação 04.11.2026 12:00:14 UTC

Fonte página do provedor

Alertas de preço

Entre para seguir o preço

API

API compatível com OpenAI: os SDKs oficiais da OpenAI funcionam com esta URL base. Substitua YOUR_API_KEY pela sua chave do provedor.

URL base da API	`https://router.requesty.ai/v1`
Endpoint	`https://router.requesty.ai/v1/chat/completions`
ID do modelo	`together/deepseek-v4.1-flash`

curl

curl https://router.requesty.ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "together/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": "together/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": "together/deepseek-v4.1-flash",
    "messages": [
      {
        "role": "user",
        "content": "Hello!"
      }
    ],
    "max_tokens": 256
  }),
});
console.log(await r.json());

Requisição (JSON)

{
  "model": "together/deepseek-v4.1-flash",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ],
  "max_tokens": 256
}

Resposta (JSON)

{
  "id": "chatcmpl-...",
  "object": "chat.completion",
  "model": "together/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
  }
}

O endereço vem da lista de modelos do provedor; confira na documentação dele.

Documentação da API do provedor

Source: AI Rate Card, https://airatecard.com/pt/c/offer%3Arequesty%7Ctogether/deepseek-v4.1-flash, prices checked 2026-11-04; seller's page: https://requesty.ai

Dados técnicos

ID: offer:requesty|together/deepseek-v4.1-flash