LLM Reference

DeepSeek V4 Pro on Vercel AI Gateway

DeepSeek V4 · DeepSeek

ServerlessOpen Source

Last refreshed 2026-05-22. Next refresh: weekly.

Why use DeepSeek V4 Pro on Vercel AI Gateway?

Vercel AI Gateway offers DeepSeek V4 Pro with pay-as-you-go pricing at $0.43/1M input tokens. Vercel AI Gateway is a unified AI proxy providing a single OpenAI-compatible API endpoint to 275+ models from 25+ providers including Anthropic, OpenAI, Google, Meta, Mistral, DeepSeek, xAI, Alibaba, Amazon, ByteDance, Cohere, MiniMax, MoonshotAI, KwaiPilot, Black Forest Labs, Recraft, Voyage AI, NVIDIA, and more.

Compare DeepSeek V4 Pro across 5 providers to find the best fit for your use case
Input / 1M
$0.435
Output / 1M
$0.87
Cache
read $0.0036
Batch
Not sourced

Setup recipe

Python + curl
Install
pip install openai
Auth
export AI_GATEWAY_API_KEY=...
Call
import os
from openai import OpenAI
client = OpenAI(
    api_key=os.environ["AI_GATEWAY_API_KEY"],
Model ID
deepseek/deepseek-v4-pro

Request example

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)

Gotchas

  • Use provider model ID "deepseek/deepseek-v4-pro", not the LLMReference slug "deepseek-v4-pro".
  • creator/model-name e.g. kwaipilot/kat-coder-pro-v2
  • The examples expect AI_GATEWAY_API_KEY; rename it only if your application config maps the new variable.

Compare DeepSeek V4 Pro Across Providers

ProviderInput (per 1M)Output (per 1M)
DeepSeek Platform$0.43$0.87
Fireworks AI$1.74$3.48
OpenRouter$0.44$0.87
Vercel AI Gateway$0.43$0.87
Novita AI$1.64$3.38

Pricing

TypePrice (per 1M)
Input tokens$0.43
Output tokens$0.87

Capabilities

ReasoningFunction CallingTool UseStructured OutputsPrompt Caching

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. Key benchmarks: SWE-bench Verified 80.6%, SWE-bench Pro 55.4%, LiveCodeBench 93.5%, GPQA Diamond 90.1%, MMLU-Pro 87.5%, Terminal-Bench 2.0 67.9%, Chatbot Arena 1460 (2026-04-28). Current API pricing: $0.435/$0.87 per 1M input/output tokens (75% discount active until 2026-05-31 15:59 UTC); regular rate $1.74/$3.48.

FAQ

What does DeepSeek V4 Pro cost on Vercel AI Gateway?

On Vercel AI Gateway, DeepSeek V4 Pro costs $0.435 per 1M input tokens and $0.87 per 1M output tokens.

What is the context window for DeepSeek V4 Pro on Vercel AI Gateway?

DeepSeek V4 Pro supports a 1,000,000 token context window on Vercel AI Gateway.

How does Vercel AI Gateway compare to other DeepSeek V4 Pro providers?

DeepSeek V4 Pro is available from 5 providers. The cheapest input pricing is $0.435/1M tokens from DeepSeek Platform.

What API model ID do I use for DeepSeek V4 Pro on Vercel AI Gateway?

Use the model ID deepseek/deepseek-v4-pro when calling Vercel AI Gateway's API.

Who created DeepSeek V4 Pro?

DeepSeek V4 Pro was created by DeepSeek as part of the DeepSeek V4 model family.

Is DeepSeek V4 Pro open source?

DeepSeek V4 Pro is open source according to the seed data.

Get Started

Model Specs

Released2026-04-24
Parameters1.6T
Context1M
ArchitectureMixture of Experts (MoE) with CSA+HCA hybrid attention

Related Models on Vercel AI Gateway