Model Price Index
Updated 2026-07-14 · Changelog

DeepSeek-V4 Flash

DeepSeek

DeepSeek's V4 model with switchable thinking and non-thinking modes, tool use, and JSON output

$0.14

Input

$0.28

Output

per 1M tokens

Ratesper 1M tokens

Input$0.14
Output$0.28
Cache Read$0.0028

Estimate Your Monthly Cost

A request with input and output tokens, requests / month at a % cache hit rate $12.60/mo

Compare all models at this workload →

Excludes cache writes and batch discounts.

Route Comparisonper 1M tokens

RouteInputOutputCache Read
Direct — DeepSeekverified 2026-07-07$0.14$0.28$0.0028
via OpenRouterverified 2026-07-07$0.09$0.18$0.018

OpenRouter adds a 5.5% platform fee on pay-as-you-go credits (verified 2026-07-08).

Specifications

API Model IDdeepseek-v4-flash
Context Window1M tokens
Max Output384K tokens
Modalitiestext
Capabilitiestool-use · streaming · json-mode · code · reasoning

More DeepSeek Text / Chat Models

DeepSeek-V4 Pro · DeepSeek-V3.2 Chat · DeepSeek-V3.2 Reasoner