Skip to content
OpenKey

DeepSeek V4 Pro

DeepSeekReleased Apr 24, 2026

DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...

Try in playground
Context window
1.0M tokens
Max output
384K tokens
Input
text
Output
text
Tokenizer
DeepSeek
Released
Apr 24, 2026
Reasoning
optional

Pricing

Per 1M tokens. The provider price and our flat 3% fee are separate columns — what you pay is their sum.

Per 1M tokensProvider+ 3% feeYou pay
Input$0.435$0.013$0.448
Output$0.870$0.026$0.896
Cache read$0.0036$0.0001$0.0037

Benchmarks

Artificial Analysis

Intelligence index
44.3
Coding index
59.4
Agentic index
36.4

Design Arena

CategoryEloWin rateRank
Full-stackagents94822.1%#29
godotgamedevagents109734%#20
Web appsagents101726.6%#25
3Dmodels132761.1%#7
ASCII artmodels120047.2%#21
Codemodels128855%#19
Data vizmodels121948.5%#37
Game devmodels129656.2%#17
SVGmodels119347%#33
UI componentsmodels127251.9%#24
Websitesmodels127953.9%#22

Head-to-head preference voting. How we filter and rank

Supported parameters

  • frequency_penalty
  • include_reasoning
  • logit_bias
  • logprobs
  • max_tokens
  • min_p
  • presence_penalty
  • reasoning
  • repetition_penalty
  • response_format
  • seed
  • stop
  • structured_outputs
  • temperature
  • tool_choice
  • tools
  • top_k
  • top_logprobs
  • top_p

Call it

OpenAI-compatible: point your SDK at api.openkey.ai/v1 and use model deepseek/deepseek-v4-pro.

Code sample language
curl https://api.openkey.ai/v1/chat/completions \
  -H "Authorization: Bearer $OPENKEY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek/deepseek-v4-pro",
    "messages": [{"role": "user", "content": "Hello"}]
  }'
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.openkey.ai/v1",
    api_key=os.environ["OPENKEY_API_KEY"],
)

completion = client.chat.completions.create(
    model="deepseek/deepseek-v4-pro",
    messages=[{"role": "user", "content": "Hello"}],
)
print(completion.choices[0].message.content)
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.openkey.ai/v1",
  apiKey: process.env.OPENKEY_API_KEY,
});

const completion = await client.chat.completions.create({
  model: "deepseek/deepseek-v4-pro",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);

Questions

How much does DeepSeek V4 Pro cost via API?
Through OpenKey, DeepSeek V4 Pro costs $0.448 per 1M input tokens and $0.896 per 1M output tokens. That is the provider price ($0.435 / $0.870) plus a flat 3% fee — nothing else.
What is DeepSeek V4 Pro's context window?
DeepSeek V4 Pro accepts up to 1.0M tokens of context and returns up to 384K tokens per request.
Is DeepSeek V4 Pro OpenAI-compatible?
Yes. Send requests to OpenKey's /v1/chat/completions endpoint with model "deepseek/deepseek-v4-pro" using any OpenAI SDK — only the base URL and API key change.
What inputs does DeepSeek V4 Pro support?
DeepSeek V4 Pro accepts text input and produces text output.

More from DeepSeek

All DeepSeek models →