Using DeepSeek V4 Pro on Vercel AI Gateway
Implementation guide · DeepSeek V4 · DeepSeek
Vercel AI Gateway exposes DeepSeek V4 Pro through model ID deepseek/deepseek-v4-pro. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.
Last refreshed 2026-06-29. Next refresh: weekly.
Quick Start
- 1
- 2Use the Vercel AI Gateway SDK or REST API to call
deepseek/deepseek-v4-pro— see the documentation for request format. - 3
Code Examples
pip install openaiAI_GATEWAY_API_KEYdeepseek/deepseek-v4-procreator/model-name e.g. kwaipilot/kat-coder-pro-v2
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["AI_GATEWAY_API_KEY"],
base_url="https://ai-gateway.vercel.sh/v1"
)
response = client.chat.completions.create(
model="deepseek/deepseek-v4-pro",
messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)Pricing on Vercel AI Gateway
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.43 |
| Output tokens | $0.87 |
Capabilities
About DeepSeek V4 Pro
DeepSeek V4 Pro is DeepSeek's flagship open-weights model, released April 24 2026 under the MIT license. Architecture: 1.6T total / 49B active parameters, MoE with Compressed Sparse Attention (CSA) + Heavily Compressed Attention (HCA) hybrid — requiring only 27% of inference FLOPs vs standard 1M-context transformers — plus Manifold-Constrained Hyper-Connections (mHC) and Muon Optimizer. Context window: 1,000,000 tokens; max output: 384,000 tokens (Think Max mode requires >=384K context). Text-only (no vision/image input). Supports three reasoning modes: Non-Think, Think High, Think Max. Function calling, tool use, and structured outputs supported.