DeepSeek V4.1 Flash Economy

DeepSeek V4.1 Flash Economy is a lower-priced tier of DeepSeek V4.1 Flash for cost-sensitive and batch workloads. Half price off-peak, with a 1M token context window.

POST/v1/ai/chat

$0.01/call

Overview

DeepSeek V4.1 Flash Economy is a lower-priced tier of DeepSeek V4.1 Flash for cost-sensitive and batch-style workloads. It is a reasoning model with tool calling and a 1M token context window, and it costs half as much outside peak hours.

Property	Value
Model ID	`deepseek/deepseek-v4.1-flash-economy`
Context Window	1,048,576 tokens
Max Output	384,000 tokens
Input Price	$0.35 / 1M tokens (peak), $0.18 off-peak
Output Price	$1.42 / 1M tokens (peak), $0.71 off-peak

Usage

const res = await fetch('https://api.yepapi.com/v1/ai/chat', {
  method: 'POST',
  headers: {
    'x-api-key': 'YOUR_API_KEY',
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    model: 'deepseek/deepseek-v4.1-flash-economy',
    messages: [{ role: 'user', content: 'Classify each of these 20 support tickets as billing, bug, feature request or other, and return the result as JSON.' }],
  }),
});
const { data } = await res.json();
console.log(data.message.content);

curl -X POST https://api.yepapi.com/v1/ai/chat \
  -H "x-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "deepseek/deepseek-v4.1-flash-economy", "messages": [{"role": "user", "content": "Classify each of these 20 support tickets as billing, bug, feature request or other, and return the result as JSON."}]}'

Request Body

Parameter	Type	Required	Description	Default
`model`	`string`	Yes	Model ID (e.g. `deepseek/deepseek-v4.1-flash-economy`)	—
`messages`	`Message[]`	Yes	Array of `{ role, content }` objects	—
`maxTokens`	`number`	No	Maximum tokens in the response	Model default
`temperature`	`number`	No	Sampling temperature (0.0–2.0)	`1.0`
`topP`	`number`	No	Nucleus sampling threshold	`1.0`
`frequencyPenalty`	`number`	No	Penalize repeated tokens	`0`
`presencePenalty`	`number`	No	Penalize tokens already present	`0`
`stream`	`boolean`	No	Enable SSE streaming	`false`

Info

All AI models use the /v1/ai/chat endpoint. Specify the model with the model field.

Response

{
  "ok": true,
  "data": {
    "model": "deepseek/deepseek-v4.1-flash-economy",
    "message": {
      "role": "assistant",
      "content": "[{\"ticket\": 1, \"label\": \"billing\"}, {\"ticket\": 2, \"label\": \"bug\"}, ... {\"ticket\": 20, \"label\": \"feature request\"}]"
    },
    "usage": {
      "promptTokens": 16,
      "completionTokens": 245,
      "totalTokens": 261
    }
  }
}

Pricing

The rate depends on when each request is made.

Period	Input $/M	Output $/M
Peak — Mon–Fri 09:00–12:00 and 14:00–18:00 China time (UTC+8)	$0.35	$1.42
Off-peak — all other hours, including weekends	$0.18	$0.71

Peak hours in UTC are Monday to Friday 01:00–04:00 and 06:00–10:00. Cached input tokens bill at a fraction of a cent per 1M. Aliases: deepseek-v4.1-flash-economy, deepseek-economy.

Info

This is a reasoning model with tool calling. Its thinking is returned in the reasoning field of the message (and of each streamed delta).

Streaming

Set "stream": true to receive Server-Sent Events. Each chunk contains a delta object:

data: {"delta":{"content":"Use"},"model":"deepseek/deepseek-v4.1-flash-economy","index":0}
data: [DONE]

Under the Hood

We handle auth, billing, and response normalization — you just send messages.