Skip to content
LLMs
DeepSeek logo

DeepSeek: DeepSeek V4 Pro 0423

by DeepSeek

DeepSeek: DeepSeek V4 Pro 0423 is a large language model from DeepSeek. It costs $1.60 per million input tokens and $3.20 per million output tokens. Its context window is 1.0M tokens.

ReasoningTool callingStructured outputPrompt cachingOpen weights
Input / 1M tokens
$1.60
Output / 1M tokens
$3.20
Cached input / 1M
$0.135

On repeated prefixes

Context window
1.0M

tokens

Who serves it cheapest

15 hosts serve DeepSeek V4 Pro 0423. Same weights, same API - the price difference is pure margin and routing.

Providers serving DeepSeek: DeepSeek V4 Pro 0423, cheapest first
ProviderInput / 1MOutput / 1MContextThroughputUptime 24h
StreamLakeCheapestfp8$0.951$1.901.0M-98.2%
Baidufp8$0.953$1.911.0M-98.5%
GMICloudfp8$0.957$1.911.0M-97.5%
DigitalOcean$1.04$2.091.0M-99.9%
Cloudflare$1.15$2.551.0M-90.2%
DeepInfrafp8$1.30$2.601.0M-99.0%
Alibabafp8$1.42$2.831M-99.8%
SiliconFlowfp8$1.50$3.141.0M-95.3%
Novitafp8$1.60$3.201.0M-100.0%
Venice$1.65$3.301M-90.6%
AtlasCloudfp4$1.68$3.381.0M-99.7%
BaseTenfp4$1.74$3.481.0M-99.7%
Parasailfp8$1.74$3.481.0M-99.7%
Azure$1.91$3.831.0M-98.8%
NextBitfp8$2.00$4.001.0M-99.7%

The spread between StreamLake and NextBit is 2.1× for identical weights. Quantization and context limits differ, so check both columns before switching.

Benchmarks

Independent scores published alongside the catalogue.

Intelligence index
30.9
Coding index
59.4
Agentic index
27.7

About DeepSeek V4 Pro 0423

DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...

Specifications

DeepSeek: DeepSeek V4 Pro 0423 specifications
Model IDdeepseek/deepseek-v4-pro
ProviderDeepSeek
Context window1.0M tokens
Max output393K tokens
Input modalitiestext
Output modalitiestext
Knowledge cutoff-
Open weightsYes - deepseek-ai/DeepSeek-V4-Pro
ReleasedApril 24, 2026

Cheaper alternatives

Models that cost less than DeepSeek V4 Pro 0423 while keeping at least half its context window and every input modality it supports.

Frequently asked

How much does DeepSeek: DeepSeek V4 Pro 0423 cost?

$1.60 per million input tokens and $3.20 per million output tokens. Cached input reads cost $0.135 per million tokens.

What is the context window of DeepSeek: DeepSeek V4 Pro 0423?

1.0M tokens, with up to 393K tokens of output per request.

Which provider serves DeepSeek: DeepSeek V4 Pro 0423 cheapest?

StreamLake at $0.951 per million input tokens - 2.1× cheaper than NextBit, the most expensive of the 15 hosts serving it.

Confirm against the source: DeepSeek official pricing.