DeepSeek V4 Pro

DeepSeek's most capable V4 model with extended context and reasoning.

deepseek-v4-pro
STABLEGet StartedView uptime
1,050,000 context
Released April 24, 2026
Starting at $0.43/M input tokens
Starting at $0.87/M output tokens
Streaming
Tools
Reasoning
JSON Output
No ratings yetSign in to rate

All Providers for DeepSeek V4 Pro

LLM Gateway routes requests to the best providers that are able to handle your prompt size and parameters.

DeepSeek
Context: 1.1M
Input
$0.435
/M tokens
Cache Read
$0.0036
/M tokens
Output
$0.87
/M tokens
Get Started
Runware
Context: 1.0M
Input
$0.961
/M tokens
Cache Read
$0.079
/M tokens
Output
$1.922
/M tokens
Get Started
Together AI
Context: 163.8k
Input
$1.74
/M tokens
Cache Read
$0.2
/M tokens
Output
$3.48
/M tokens
Get Started
Alibaba Cloud
Context: 1M
Input
$2.4
/M tokens
Cache Read
$0.2
/M tokens
Output
$4.8
/M tokens
Get Started
DeepInfra
Context: 64kQuant: fp4
Input
$1.74
/M tokens
Cache Read
$0.145
/M tokens
Output
$3.48
/M tokens
Get Started
ByteDance
Context: 1.0M
Input
$1.74
/M tokens
Cache Read
$0.145
/M tokens
Output
$3.48
/M tokens
Get Started
Nebius AI
Context: 1.0MQuant: fp8
Input
$1.75
/M tokens
Cache Read
/M tokens
Output
$3.5
/M tokens
Get Started

Frequently asked questions

What is DeepSeek V4 Pro?

DeepSeek's most capable V4 model with extended context and reasoning. You can access it through LLM Gateway's OpenAI-compatible API with automatic provider routing, fallback, and cost analytics.

How much does DeepSeek V4 Pro cost?

Pricing for DeepSeek V4 Pro on LLM Gateway starts at $0.43 per million input tokens and $0.87 per million output tokens, depending on the provider. The pricing table above always reflects the current per-provider rates.

What is the context length of DeepSeek V4 Pro?

DeepSeek V4 Pro supports a context window of up to 1,050,000 tokens on its largest provider deployment.

Which providers serve DeepSeek V4 Pro?

DeepSeek V4 Pro is served by DeepSeek, Runware, Together AI, Alibaba Cloud, DeepInfra, ByteDance, Nebius AI through LLM Gateway. Requests are automatically routed to the best available provider, with fallback when a provider has issues.

Does DeepSeek V4 Pro support tool calling and structured outputs?

Yes. DeepSeek V4 Pro supports both tool (function) calling and structured JSON outputs through LLM Gateway.

When was DeepSeek V4 Pro released?

DeepSeek V4 Pro was released on April 24, 2026.