DeepSeek Cuts Input Cache-Hit Pricing Across Its API Lineup

Skip to main content Bench LM LeaderboardCompareBenchmarksModelsResearchNewsletter Tools AI Prompt WriterStart with a goal, context, and constraintsPrompt OptimizerRewrite an existing prompt and inspect the diffBrowse all tools› AdvertiseSearch⌘K Browse Last synced 2026-07-25 The DeepSeek API costs $0.435/$0.87 per million input/output tokens forDeepSeek V4 Pro and $0.14/$0.28 forV4 Flash. Cache-hit input falls to $0.003625 and $0.0028 respectively. Both V4 tiers ship a 1M-token context window. Citable stat 2 current DeepSeek V4 API tiers span $0.14–$0.435 per million input tokens and $0.28–$0.87 per million output tokens as of 2026-07-25. [...] | Model | API model ID | Input $/M | Cached input $/M | Output $/M | Context | Effective | Price source | --- --- --- --- | | DeepSeek V4 Pro | `deepseek-v4-pro`Current | $0.435 | $0.003625 | $0.87 | 1M | Apr 24, 2026 | Official current pricing | | DeepSeek V4 Flash | `deepseek-v4-flash`Current | $0.14 | $0.0028 | $0.28 | 1M | Apr

> (2) For all models, the input cache hit price has been reduced to 1/10 of the launch price. This price adjustment takes effect from 2026/4/26 12:15 UTC. There is no end date. Currently, it's 2% of the input price for DeepSeek V4 Flash and 0.8% with this new V4 Pro pricing, which is extremely low compared to competitors to the point that it affects the unit economics a bit and I thought it would be temporary. In the case of V4 Pro, the effective cost is ~$0.04/M input tokens given the caching (based on OpenRouter's metrics: ), which is significantly cheaper than even small models from competitors. [...] cache hit price has been reduced to 1/10 of the launch price. This price adjustment takes effect from 2026/4/26 12:15 UTC. There is no end date. Currently, it's 2% of the input price for DeepSeek V4 Flash and 0.8% with this new V4 Pro pricing, which is extremely low compared to competitors to the point that it affects the unit economics a bit and I thought it would be temporary. In t

> (2) For all models, the input cache hit price has been reduced to 1/10 of the launch price. This price adjustment takes effect from 2026/4/26 12:15 UTC. There is no end date. Currently, it's 2% of the input price for DeepSeek V4 Flash and 0.8% with this new V4 Pro pricing, which is extremely low compared to competitors to the point that it affects the unit economics a bit and I thought it would be temporary. In the case of V4 Pro, the effective cost is ~$0.04/M input tokens given the caching (based on OpenRouter's metrics: ), which is significantly cheaper than even small models from competitors. [...] | | | | --- | | | minimaxir 65 days ago | parent | context | favorite | on: DeepSeek makes the V4 Pro price discount permanent I'm more curious about the caching: > (2) For all models, the input cache hit price has been reduced to 1/10 of the launch price. This price adjustment takes effect from 2026/4/26 12:15 UTC. There is no end date. Currently, it's 2% of the input pric

DeepSeek announced on Monday that it is offering a 75% discount on its newly released DeepSeek-V4-Pro model to developers until 5 May 2026, and is simultaneously cutting the price of input cache hits across its entire API suite to one-tenth of previous levels, effective immediately. The discount was announced in a post on X. The move intensifies a pricing competition with US AI providers that DeepSeek first triggered in January 2025 with its R1 model, which claimed frontier-level reasoning performance at a fraction of the cost of comparable OpenAI products. [...] The pricing context is important. At full price, before any promotional discount, DeepSeek-V4-Pro already costs $0.145 per million input tokens and $3.48 per million output tokens, undercutting OpenAI’s GPT-5.5, Google’s Gemini 3.1 Pro, and Anthropic’s Claude Opus 4.7 on per-token basis. The 75% promotional discount on input tokens reduces the V4-Pro input price to approximately $0.036 per million tokens. The Flash variant,

Quick Answer DeepSeek API pricing centers on two V4 models. V4 Flash costs $0.14 per million input tokens and $0.28 output. V4 Pro costs $1.74/$3.48 at standard rates, with a promotional discount currently active. Cache hits cost 1/10 of standard input. Both models support 1M token context and 384K max output. DeepSeek V4 arrived on April 24, 2026, the same day OpenAI shipped GPT-5.5, in what was almost certainly a deliberate scheduling collision. Two models replaced the entire lineup: V3.2, R1, and both legacy API aliases. [...] ## How does DeepSeek caching work? DeepSeek uses automatic disk-based prefix caching. When your prompt starts with tokens that match a recently processed prefix, those tokens are served from cache at 1/10 of the standard input price. No SDK changes. No cache-control headers. No opt-in flag. It just works. On V4 Flash, cached input costs $0.0028 per MTok, down from $0.14 for cache misses. That’s a 98% discount. The reduction took effect April 26, 2026, two

Log inSign up ## Post user avatar DeepSeek @deepseek\_ai 🔥DeepSeek Input Cache Price Drop! Effective immediately, the price for input cache hits across the ENTIRE DeepSeek API series is reduced to just 1/10th of the original price! Build more efficiently for less. 📌Reminder: The DeepSeek-V4-Pro 75% OFF promotion is still active until May 5th, 2026, 15:59 (UTC Time). 4:35 PM · Apr 26, 20261.6MViews user avatar rahul @ErRahul337 Apr 26 Great news for individual developers. This will significantly improve the adoption 11K user avatar b/acc, context platform engineer @AccBalanced Apr 26 Begun, the token cache price wars have 30K user avatar John Greg @JohnGregQuantum Apr 26 [...] John Greg @JohnGregQuantum Apr 26 DeepSeek the big 🐋 whale is dropping cached input to 1/10th, which isn’t a discount, that's just simple charging less for long context and that's huge not an extra charge like other ai models like ( Claud