DeepSeek V4 Pro

DeepSeek's flagship V4 mixture-of-experts model — strong reasoning and coding with a 1M token context window and up to 384K output tokens.

POST/v1/ai/chat

$0.01/call

Overview

DeepSeek's flagship V4 mixture-of-experts model — strong reasoning and coding with a 1M token context window and up to 384K output tokens.

Property	Value
Model ID	`deepseek/deepseek-v4-pro`
Context Window	1,048,576 tokens
Max Output	384,000 tokens
Input Price	$0.64 / 1M tokens
Output Price	$1.28 / 1M tokens

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-pro',
    messages: [{ role: 'user', content: 'Design a distributed rate-limiter that supports per-user, per-IP and per-API-key quotas.' }],
  }),
});
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-pro", "messages": [{"role": "user", "content": "Design a distributed rate-limiter that supports per-user, per-IP and per-API-key quotas."}]}'

Request Body

Parameter	Type	Required	Description	Default
`model`	`string`	Yes	Model ID (e.g. `deepseek/deepseek-v4-pro`)	—
`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-pro",
    "message": {
      "role": "assistant",
      "content": "Keep counters in Redis keyed by scope and window, use a sliding-window log for accuracy on the user tier and fixed windows for IP and key tiers where volume is high, and check the three scopes in order of cost so the cheapest rejection happens first."
    },
    "usage": {
      "promptTokens": 16,
      "completionTokens": 245,
      "totalTokens": 261
    }
  }
}

Streaming

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

data: {"delta":{"content":"Use"},"model":"deepseek/deepseek-v4-pro","index":0}
data: [DONE]

Under the Hood

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