DeepSeek V4 Pro is DeepSeek's flagship Mixture-of-Experts (MoE) model, featuring 1.6 trillion total parameters, 49 billion activated parameters, and a 1 million-token context window. It delivers exceptional performance in reasoning, coding, mathematics, and software engineering, making it ideal for demanding AI workloads. Built on the same architecture as DeepSeek V4 Flash, it adds a hybrid attention system for more efficient long-context processing. It supports High and XHigh reasoning modes (with XHigh corresponding to maximum reasoning), making it well suited for complex tasks such as full codebase analysis, multi-step agent workflows, large-scale information synthesis, and enterprise-grade automation.
Pricing
USD · live rate| Pricing | USD / M |
|---|---|
| Input | $0.43 |
| Output | $0.86 |
| Cache hit | $0.0036 |
| Image input | — |
Providers
Same model, multi-channel live comparison · best values highlighted| Provider | Context | Max output | Input /M | Output /M | Cache /M | Latency | Throughput |
|---|---|---|---|---|---|---|---|
| Tokenpony | 1M | 384K | $1.71 | $3.43 | $0.01 | 762ms | 19 t/s |
| Ali | 1M | 384K | $1.71 | $3.43 | $0.14 | 2592ms | 70 t/s |
| DeepSeek | 1M | 384K | $0.43 | $0.86 | $0.0036 | 324ms | 37 t/s |
Usage trends
API example
Model Center normalizes requests and responses across providers behind one OpenAI-compatible API.
Call this model directly or through the OpenAI SDK — one API key for every model in the catalog.
from openai import OpenAI
client = OpenAI(
base_url="https://router-integration.test.cogfoundry.ai/api/v1",
api_key="$MODEL_CENTER_API_KEY",
)
completion = client.chat.completions.create(
model="deepseek/deepseek-v4-pro",
messages=[{"role": "user", "content": "Which number is larger, 9.11 or 9.8?"}],
stream=True,
)
for chunk in completion:
if chunk.choices and chunk.choices[0].delta.content is not None:
print(chunk.choices[0].delta.content, end="", flush=True)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://router-integration.test.cogfoundry.ai/api/v1",
apiKey: process.env.MODEL_CENTER_API_KEY,
});
const stream = await client.chat.completions.create({
model: "deepseek/deepseek-v4-pro",
messages: [{ role: "user", content: "Which number is larger, 9.11 or 9.8?" }],
stream: true,
});
for await (const chunk of stream) {
process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
}curl https://router-integration.test.cogfoundry.ai/api/v1/chat/completions \
-H "Authorization: Bearer $MODEL_CENTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek/deepseek-v4-pro",
"messages": [{"role": "user", "content": "Which number is larger, 9.11 or 9.8?"}],
"stream": true
}'from openai import OpenAI
client = OpenAI(
base_url="https://router-integration.test.cogfoundry.ai/api/v1",
api_key="$MODEL_CENTER_API_KEY",
)
completion = client.completions.create(
model="deepseek/deepseek-v4-pro",
prompt="Which number is larger, 9.11 or 9.8?",
stream=True,
)
for chunk in completion:
if chunk.choices and chunk.choices[0].text:
print(chunk.choices[0].text, end="", flush=True)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://router-integration.test.cogfoundry.ai/api/v1",
apiKey: process.env.MODEL_CENTER_API_KEY,
});
const stream = await client.completions.create({
model: "deepseek/deepseek-v4-pro",
prompt: "Which number is larger, 9.11 or 9.8?",
stream: true,
});
for await (const chunk of stream) {
process.stdout.write(chunk.choices[0]?.text ?? "");
}curl https://router-integration.test.cogfoundry.ai/api/v1/completions \
-H "Authorization: Bearer $MODEL_CENTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek/deepseek-v4-pro",
"prompt": "Which number is larger, 9.11 or 9.8?",
"stream": true
}'import requests
response = requests.post(
"https://router-integration.test.cogfoundry.ai/api/v1/messages",
headers={"Authorization": "Bearer $MODEL_CENTER_API_KEY", "Content-Type": "application/json"},
json={
"model": "deepseek/deepseek-v4-pro",
"max_tokens": 1024,
"messages": [{"role": "user", "content": "Which number is larger, 9.11 or 9.8?"}],
},
)
print(response.json()["content"][0]["text"])const response = await fetch("https://router-integration.test.cogfoundry.ai/api/v1/messages", {
method: "POST",
headers: {
Authorization: "Bearer $MODEL_CENTER_API_KEY",
"Content-Type": "application/json",
},
body: JSON.stringify({
model: "deepseek/deepseek-v4-pro",
max_tokens: 1024,
messages: [{ role: "user", content: "Which number is larger, 9.11 or 9.8?" }],
}),
});
const data = await response.json();
console.log(data.content[0].text);curl https://router-integration.test.cogfoundry.ai/api/v1/messages \
-H "Authorization: Bearer $MODEL_CENTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek/deepseek-v4-pro",
"max_tokens": 1024,
"messages": [{"role": "user", "content": "Which number is larger, 9.11 or 9.8?"}]
}'