computetrail

All models ·deepseek

DeepSeek: DeepSeek V4 Flash 0423

Provider: deepseek · deepseek/deepseek-v4-flash

Input
$0.0795 /1M
Output
$0.159 /1M
Cache read
$0.0159 /1M
Context
1,048,576 tokens

How DeepSeek: DeepSeek V4 Flash 0423 pricing compares

At $0.159 / 1M output tokens, DeepSeek: DeepSeek V4 Flash 0423 is the 2nd-cheapest of 14 deepseek models we track. It's cheaper than 94% of the 392 paid models on computetrail (26th-cheapest overall). Output costs 2.0× its input price ($0.0795 / 1M in). For a typical 3:1 input-to-output workload that works out to about $0.10 / 1M blended. Reading cached input costs 80% less than fresh input, so prompt caching cuts repeat-context cost sharply. Its 1,048,576 tokens context window ranks 59th-largest of 392 models with a published limit.

Output price history

$0.280$0.09806-2907-2908-27

Across 60 daily snapshots since 2026-06-29, the output price has fallen 11.7% — from $0.18 to $0.159 / 1M.

Similar-priced models

ModelProviderOutput $/1MContext
Qwen: Qwen3.5-9Bqwen$0.15262,144
Cohere: Command R7B (12-2024)cohere$0.15128,000
Microsoft: Phi 4microsoft$0.1416,384
Amazon: Nova Micro 1.0amazon$0.14128,000
NVIDIA: Nemotron 3.5 Lightningnvidia$0.2262,144
NVIDIA: Nemotron 3 Nano 30B A3Bnvidia$0.2262,144

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