DeepSeek API Introduces Context Caching on Disk, Cutting Token Prices by ~90%
DeepSeek has launched a disk-based context caching service for its API, reducing cache-hit token pricing to $0.014 per million tokens versus $0.14 for cache misses—a 90% cost reduction. The system requires no code changes, runs automatically for prefix-matched inputs, and reduces first-token latency from ~13s to ~500ms on 128K prompts. DeepSeek attributes the feasibility of disk caching to the compact KV cache produced by its MLA (Multi-head Latent Attention) architecture in DeepSeek V2, which it claims makes it the first LLM API provider to deploy extensive disk caching at scale. The service supports up to 1 trillion tokens per day with no concurrency limits.
Related guides (3)
Related events (8)
DeepSeek-V4: a million-token context that agents can actually use
A Hugging Face blog post discusses DeepSeek-V4, highlighting its million-token context window as a practically usable capability for agentic applications. The post appears to analyze or announce DeepSeek-V4's long-context features in the context of agent workflows. No article body was available for deeper analysis.
DeepSeek-V3: 671B MoE Open-Source Model with 3x Speed Improvement
DeepSeek releases V3, a 671B parameter Mixture-of-Experts model with 37B activated parameters, trained on 14.8T tokens. The model runs at 60 tokens/second (3x faster than V2) and is fully open-source with weights and paper released. API pricing is set at $0.27/M input tokens and $1.10/M output tokens starting February 8, positioning it as a low-cost frontier alternative. DeepSeek signals future multimodal capabilities in the ecosystem.
DeepSeek Reasonix: Native Coding Agent with High Caching and Low Cost
DeepSeek Reasonix is a coding agent built natively on DeepSeek models, emphasizing high prompt caching rates and low inference cost. The project attracted significant Hacker News engagement (349 points, 171 comments), suggesting community interest in cost-efficient agentic coding workflows. It appears to be an open-source or community-developed tool rather than an official DeepSeek Labs release.
DeepSeek Releases V3.2-Exp with Sparse Attention Architecture and 50%+ API Price Cut
DeepSeek has released DeepSeek-V3.2-Exp, an experimental model built on V3.1-Terminus that introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism designed to improve long-context performance and reduce compute costs during training and inference. Benchmarks indicate V3.2-Exp performs on par with V3.1-Terminus while achieving efficiency gains. The release is accompanied by a 50%+ API price reduction effective immediately, open-weights release on Hugging Face, a technical report, and GPU kernel code in TileLang and CUDA.
DeepSeek API Major Upgrade: Function Calling, FIM, Chat Prefix Completion, JSON Output, and 8K Token Limit
DeepSeek has released a significant API update adding Function Calling (up to 128 parallel calls, OpenAI-compatible), JSON Output, Chat Prefix Completion, and FIM (Fill-In-the-Middle) Completion to both deepseek-chat and deepseek-coder models. The update also raises the max_tokens ceiling to 8K in the Beta API. Several features are in Beta and will be open-sourced once stable. The Function Calling and JSON Output implementations are explicitly designed to be compatible with the OpenAI API.
DeepSeek V4 Preview Release: 1.6T-param Pro and 284B Flash Models with 1M Context, Open-Sourced
DeepSeek has released DeepSeek-V4 as an open-weights preview, comprising two MoE variants: V4-Pro (1.6T total / 49B active parameters) and V4-Flash (284B total / 13B active parameters). Both models support 1M token context by default, enabled by a novel Token-wise compression and DeepSeek Sparse Attention (DSA) architecture. V4-Pro claims open-source SOTA on agentic coding benchmarks and world-class math/STEM/coding performance rivaling top closed-source models, while V4-Flash offers near-parity reasoning at lower cost and latency. The API is live today with OpenAI and Anthropic compatibility, and legacy model endpoints will be retired in July 2026.
DeepSeek to Make Permanent 75% Discount on Flagship AI Model
DeepSeek is permanently reducing pricing on its flagship AI model by 75%, signaling a sustained aggressive pricing strategy rather than a temporary promotional move. This continues the pattern of Chinese AI labs applying significant downward pressure on frontier model API pricing. The move has implications for competitive dynamics across the inference market and may force responses from other major providers.
DeepSeek-V3.1 Release: Hybrid Think/Non-Think Model with Agent-Focused Upgrades
DeepSeek has released V3.1, a hybrid inference model supporting both thinking and non-thinking modes in a single model, positioned as their first step toward the agent era. The model features improved tool use and multi-step agent task performance, with benchmarks showing gains on SWE-bench and Terminal-Bench, and faster thinking efficiency compared to DeepSeek-R1-0528. The base model received 840B tokens of continued pretraining for long-context extension, a new tokenizer, and open-source weights are available on HuggingFace. API updates include 128K context for both modes, Anthropic API format compatibility, and strict function calling support in beta.