YepAPI
Get your API key
DeepSeekText Generation/v1/ai/chatReasoning

DeepSeek V4 Pro 0813 API

Access DeepSeek V4 Pro 0813 through one API key. DeepSeek V4 Pro GA Release.

DeepSeek V4 Pro 0813 is the GA release of DeepSeek V4 Pro, a large-scale mixture-of-experts model. V4 Pro 0813 is the pick for long-document reasoning and coding where you want DeepSeek's flagship quality on a stable, generally available snapshot.

Full Docs Get API Key

Takes 30 seconds.

DeepSeek V4 Pro 0813 API pricing

Pay per request from your YepAPI balance — no subscription, no monthly minimum. Prices updated October 23, 2026.

Token typePrice
Input$0.97 / 1M tokens
Output (incl. reasoning)$2.92 / 1M tokens
Context window1.0M tokens
What it costsPer jobPer 1,000
Chat reply1K input + 500 output tokens$0.0024$2.43
RAG answer8K input + 800 output tokens$0.01$10.10
Agent step with tools30K input + 2K output tokens$0.035$34.94
Long document summary100K input + 2K output tokens$0.103$102.84

4,900+

Developers

2.3M+

API calls served

184

Endpoints

$0.01

Per call

Yep, that's it.

Try it live

Send a message and see DeepSeek V4 Pro 0813 respond in real time.

POST/v1/ai/chat

Maximum tokens in the response.

Real-time tokens

Hit "Send Request" to see the response

DeepSeek V4 Pro 0813 specs

ProviderDeepSeek
Model IDdeepseek/deepseek-v4-pro-0813
Endpoint/v1/ai/chat
TypeText Generation
Context window1.05M tokens
Max output944K tokens
ReasoningYes
OpenAI-compatibleYes — /v1/ai/chat/completions

How to get a DeepSeek V4 Pro 0813 API key

  1. 1

    Create an account

    Sign up at yepapi.com with Google or email. It takes about 30 seconds.

  2. 2

    Create an API key

    Open the dashboard, go to API Keys and create a key. Copy it — it starts with yep_sk_.

  3. 3

    Call DeepSeek V4 Pro 0813

    Send a request to /v1/ai/chat with the x-api-key header and model "deepseek/deepseek-v4-pro-0813".

  4. 4

    Pay as you go

    Usage is billed per request from your balance. Top up any amount; there is no subscription.

Strengths

✓
GA snapshot of V4 Pro

The generally available release of DeepSeek's flagship V4 Pro.

✓
Cheap input, long context

$0.97 per 1M input tokens over a 1,048,576-token window makes large-context work affordable.

✓
Very large output

Returns up to 943,718 output tokens per call.

✓
Tools and structured output

Function calling and JSON schema outputs.

Quick start

Copy this snippet and start making calls with DeepSeek V4 Pro 0813.

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-0813",
    "messages": [
      {
        "role": "user",
        "content": "Explain API gateways in 2 sentences."
      }
    ],
    "maxTokens": 256
  }),
});
const { data } = await res.json();
console.log(data.message.content);

DeepSeek V4 Pro 0813 vs similar models

Every model below runs on the same API key — switch by changing the model ID.

ModelProviderPriceContext
DeepSeek V4 Pro 0813DeepSeek$0.97 in / $2.92 out per 1M1.0M
DeepSeek V4 FlashDeepSeek$0.13 in / $0.27 out per 1M1.0M
DeepSeek V3.2DeepSeek$0.41 in / $0.62 out per 1M164K
DeepSeek V4.1 Flash EconomyDeepSeek$0.35 in / $1.42 out per 1M1.0M
DeepSeek V4.1 FlashDeepSeek$0.44 in / $1.77 out per 1M1.0M
DeepSeek R1 0528DeepSeek$0.74 in / $3.18 out per 1M164K
Nemotron 3 SuperNVIDIA$0 in / $0 out per 1M262K
Qwen3.7 FlashQwen$0.04 in / $0.19 out per 1M1M

Why use DeepSeek V4 Pro 0813 through YepAPI?

✓One API key for all models — no separate accounts
✓OpenAI SDK compatible — just change the base URL
✓No monthly minimums — pay per token
✓Switch models with one line of code
✓Full provider passthrough — citations, search results, and all extras included
✓Streaming and non-streaming support on every model
✓Works with Cursor, Claude, LangChain, and any LLM tool
✓Unified billing across all providers

DeepSeek V4 Pro 0813 API — pricing, context window & access

DeepSeek V4 Pro 0813 is the GA release of DeepSeek V4 Pro, a large-scale mixture-of-experts model. It pairs a 1,048,576-token context window with up to 943,718 output tokens per response, at $0.97 per 1M input and $2.92 per 1M output tokens through YepAPI.

Through YepAPI you call DeepSeek V4 Pro 0813 on an OpenAI-compatible endpoint with a single key — the same key that reaches GPT-6, Claude, Gemini, Grok and the SEO, SERP and scraping APIs. Input: text.

What is DeepSeek V4 Pro 0813?

DeepSeek V4 Pro 0813 is the GA release of DeepSeek V4 Pro, a large-scale mixture-of-experts model. It offers a 1,048,576-token context window and up to 943,718 output tokens at $0.97 / $2.92 per 1M tokens, with the low input rate making it well suited to long-context reasoning. It accepts text as input, handles up to 1,048,576 tokens of context and returns up to 943,718 output tokens per call.

Build with DeepSeek V4 Pro 0813 via YepAPI

YepAPI serves DeepSeek V4 Pro 0813 on the OpenAI-compatible /v1/ai/chat endpoint. Point your base URL at YepAPI, add your key, and set the model string to deepseek-v4-pro-0813 (or the full deepseek/deepseek-v4-pro-0813). Function calling, structured outputs and reasoning settings pass straight through, and switching to any other model on the platform is a one-string change per request.

DeepSeek V4 Pro 0813 API pricing — $0.97 / 1M input, $2.92 / 1M output

DeepSeek V4 Pro 0813 costs $0.97 per 1M input tokens and $2.92 per 1M output tokens through YepAPI, pay per token with no minimums. Failed calls are never charged, and every request is itemised in your dashboard API Logs so you can see exactly what a very long response cost.

DeepSeek V4 Pro 0813 use cases

V4 Pro 0813 is the pick for long-document reasoning and coding where you want DeepSeek's flagship quality on a stable, generally available snapshot.

Start generating in 30 seconds

Pay per call, no subscriptions.

Get API Key

What developers say

“Switched from SerpAPI and cut our SERP costs by 80%. Same data quality, way simpler billing.”

Marcus T.

SEO Platform Founder

“One API key for AI models, SERP data, and web scraping. Saved us from managing 4 separate providers.”

Priya S.

Full-Stack Developer

“The $5 free credit let us prototype our entire rank tracking feature before committing. No other API does that.”

Jake R.

Indie Hacker

Frequently asked questions

DeepSeek V4 Pro 0813 is the GA release of DeepSeek V4 Pro, a large-scale mixture-of-experts model. V4 Pro 0813 is the pick for long-document reasoning and coding where you want DeepSeek's flagship quality on a stable, generally available snapshot.

DeepSeek V4 Pro 0813 costs $0.97 per 1M input tokens and $2.92 per 1M output tokens through YepAPI, billed per request with no monthly fee. For example, a chat reply (1K input + 500 output tokens) costs about $0.0024.

Sign up at yepapi.com (Google or email, about 30 seconds), open the dashboard and create an API key. The same key works for DeepSeek V4 Pro 0813 and every other model — no separate DeepSeek account or waitlist.

Use "deepseek/deepseek-v4-pro-0813" as the model on /v1/ai/chat. The short alias "deepseek-v4-pro-0813" also works.

Yes. Point the OpenAI SDK at https://api.yepapi.com/v1/ai with your YepAPI key and set model to "deepseek/deepseek-v4-pro-0813". Streaming works the same way, so existing OpenAI code only needs the base URL and key changed.

DeepSeek V4 Pro 0813 supports a 1.0M token context window with up to 944K output tokens per request.

Ready to use DeepSeek V4 Pro 0813?

Pay per call, no subscriptions.

Get API Key Read Docs

Explore more models

DeepSeek V3.2

DeepSeek

Access DeepSeek V3.2 through one API key. Latest DeepSeek model.

164K ctx$0.41/M in

DeepSeek V4.1 Flash Economy

DeepSeek

Access DeepSeek V4.1 Flash Economy through one API key. DeepSeek's economy tier, half price off-peak.

1.0M ctx$0.35/M in

DeepSeek V4.1 Flash

DeepSeek

Access DeepSeek V4.1 Flash through one API key. DeepSeek Ultra-Cheap Sparse MoE.

1.0M ctx$0.44/M in

Seed 2.0 Pro

ByteDance

Access Seed 2.0 Pro through one API key. ByteDance's flagship Seed 2.0 reasoning model.

262K ctx$0.74/M in

Claude Opus 5.5

Anthropic

Access Claude Opus 5.5 through one API key. Anthropic Flagship for Reasoning & Coding.

1M ctx$5.91/M in

Seed 2.1 Turbo

ByteDance

Access Seed 2.1 Turbo through one API key. ByteDance Multimodal Coding Agent.

262K ctx$0.74/M in

More Text Generation models

All DeepSeek models →All AI models →