DeepSeek-V4-Flash

deepseek-v4-flash

Open sourceDeepSeek series

Overview

1M ContextRAGCode generationContext caching

DeepSeek-V4-Flash is a lightweight MoE text model built for online workloads at scale: 284B total parameters with only about 13B activated per inference. It keeps long-context comprehension while optimizing the reasoning path for everyday chat, retrieval-augmented generation, content production, customer support, coding assistance and long-running tasks. Its unit price is markedly lower than comparable models, making it a good fit for high-QPS, low-latency and cost-sensitive integrations.

Million-token context

A 1M-token context window loads project-scale codebases, very long documents and multi-turn conversations in a single pass.

Efficient MoE

284B total / 13B activated keeps each inference light, balancing quality against compute cost.

Exceptional value

Per-token cost is well below models in the same class.

High throughput, low latency

RPM 15K / TPM 1.20M for steady output under online and high-concurrency workloads.

Features

Web search✓

Structured output✓

Context caching✓

Batch✓

Prefix completion✓

Fine-tuning✕

Vision✕

Pricing

Off-peak prices are half of peak prices. Peak hours are Monday to Friday 9:00–12:00 and 14:00–18:00 Beijing time (UTC+8); all other times are off-peak.

Off-peak

Input¥1.5/M tokens

Input (cache hit)¥0.05/M tokens

Output¥4.5/M tokens

Peak

Input¥3/M tokens

Input (cache hit)¥0.1/M tokens

Output¥9/M tokens

Rate Limits & Context

Context Window1M

Max Output384K

RPM (requests/min)15K

TPM (tokens/min)1200K

API Reference

ENDPOINT

POST https://api.tokenfab.cn/v1/chat/completions

Request Example

curl https://api.tokenfab.cn/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $TOKENFAB_API_KEY" \
  -d '{
    "model": "deepseek-v4-flash",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "介绍一下你自己。"}
    ]
  }'

import os
from deepscope import Generation
import dashscope

dashscope.base_http_api_url = 'https://dashscope.aliyuncs.com/api/v1'

messages = [
    {'role': 'system', 'content': 'You are a helpful assistant.'},
    {'role': 'user', 'content': '介绍一下你自己。'}
]
response = Generation.call(
    # 可选，配置 DashScope API Key: api_key = "sk-xxx",
    api_key=os.getenv('DASHSCOPE_API_KEY'),
    model='deepseek-v4-flash',
    messages=messages,
    result_format='message',
    # 启用深度思考模式：
    enable_thinking=True,
)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.TOKENFAB_API_KEY,
  baseURL: "https://api.tokenfab.cn/v1"
});

const response = await client.chat.completions.create({
  model: "deepseek-v4-flash",
  messages: [
    { role: "system", content: "You are a helpful assistant." },
    { role: "user", content: "介绍一下你自己。" }
  ]
});

console.log(response.choices[0].message.content);

Response Example

JSON

{
  "id": "chatcmpl-2k8d91fz",
  "object": "chat.completion",
  "created": 1784950000,
  "model": "deepseek-v4-flash",
  "choices": [{
    "index": 0,
    "message": {
      "role": "assistant",
      "content": "我是 DeepSeek-V4-Flash，一款兼顾高性价比与高吞吐的 MoE 文本模型，总参数 284B、单次激活约 13B，支持百万级上下文窗口，适合大规模生产与在线业务使用。"
    },
    "finish_reason": "stop"
  }],
  "usage": {
    "prompt_tokens": 14,
    "completion_tokens": 46,
    "total_tokens": 60
  }
}

Request Parameters

Parameter	Type	Required	Description
model	string	✓	Model ID, e.g. deepseek-v4-flash
messages	array	✓	List of chat messages, each with role and content
temperature	float	—	Sampling temperature, 0–2, default 0.7
top_p	float	—	Nucleus sampling, 0–1, default 0.9
max_tokens	int	—	Maximum output tokens
stream	bool	—	Whether to stream the response, default false
tools	array	—	Tool definitions for function calling
tool_choice	string	—	Tool choice policy: auto / none / a named function