DeepSeek

DeepSeek

deepseek-v4-pro

DeepSeek V4 Pro

DeepSeek V4 Pro is available after commercial review or workspace setup.

Model detailAccess reviewDense Transformer

Params

V4 Pro

Context

256K

Max Output

64K

License

Proprietary

API Surface

/v1/chat/completions

Access

Access review

Why pick it

  • Access is enabled only after workspace setup or commercial review.
  • Pricing appears only when verified by the live service catalog.

Pricing

TierPublicCachedNote
Realtime$0.58 / $0.58$0.203Current published price
Batch$0.58 / $0.58$0.203Published batch rates appear here when available
Pricing is synced from the live BatchIn catalog.

Quick start

This model is not yet open for public testing. Contact the team for the right access path.

Python
from openai import OpenAI

client = OpenAI(
    base_url="https://api.batchin.tech/v1",
    api_key="BATCHIN_API_KEY"
)

resp = client.chat.completions.create(
    model="deepseek-v4-pro",
    messages=[{"role": "user", "content": "Summarize why this model is a fit for my workload"}]
)

print(resp.choices[0].message.content)
JavaScript
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.batchin.tech/v1",
  apiKey: process.env.BATCHIN_API_KEY,
});

const resp = await client.chat.completions.create({
  model: "deepseek-v4-pro",
  messages: [{ role: "user", content: "Summarize why this model is a fit for my workload" }],
});

console.log(resp.choices[0]?.message?.content);
cURL
curl https://api.batchin.tech/v1/chat/completions \
  -H "Authorization: Bearer ***" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4-pro",
    "messages": [{"role":"user","content":"Summarize why this model is a fit for my workload"}]
  }'

Specs

Architecture

Dense Transformer

Vendor

DeepSeek

Context window

256K

Max output

64K

Best for

deepseek
managed
preview

Related models

Back to model center
DeepSeek

DeepSeek

deepseek-v4-flash

DeepSeek V4 Flash

DeepSeek V4 Flash is available after commercial review or workspace setup.

View detail
Z.ai

z.ai

glm-5-1

GLM-5.1

Open flagship route for coding, reasoning, and long-horizon agent execution

View detail
Qwen

Qwen

qwen-3-6-plus

Qwen 3.6 Plus

Higher-end Qwen model for customers who need the latest proprietary capability

View detail
DeepSeek

DeepSeek

deepseek-v3-2

DeepSeek V3.2

DeepSeek V3.2 is available after commercial review or workspace setup.

View detail