computetrail

All models ·deepseek

DeepSeek: DeepSeek V4 Pro 0423

Provider: deepseek · deepseek/deepseek-v4-pro

Input
$0.87 /1M
Output
$1.74 /1M
Cache read
$0.0725 /1M
Context
1,048,576 tokens

How DeepSeek: DeepSeek V4 Pro 0423 pricing compares

At $1.74 / 1M output tokens, DeepSeek: DeepSeek V4 Pro 0423 is the 11th-cheapest of 14 deepseek models we track. It's cheaper than 54% of the 392 paid models on computetrail (179th-cheapest overall). Output costs 2.0× its input price ($0.87 / 1M in). For a typical 3:1 input-to-output workload that works out to about $1.09 / 1M blended. Reading cached input costs 92% less than fresh input, so prompt caching cuts repeat-context cost sharply. Its 1,048,576 tokens context window ranks 58th-largest of 392 models with a published limit.

Output price history

$3.20$0.79406-2907-2908-27

Across 60 daily snapshots since 2026-06-29, the output price has risen 100.0% — from $0.87 to $1.74 / 1M.

Similar-priced models

ModelProviderOutput $/1MContext
Z.ai: GLM 4.7z-ai$1.75204,800
Z.ai: GLM 4.5Vz-ai$1.865,536
DeepSeek: DeepSeek V3.1deepseek$1.65163,840
Google: Gemini 3.7 Flashgoogle$1.8751,048,576
Google: Gemini 3.6 Flash (batch)google$1.8751,048,576
Qwen: Qwen3.5-27Bqwen$1.56262,144

Prices are recorded daily from public provider data via OpenRouter and normalized to USD per 1M tokens. See methodology.