DeepSeek model releases

The production release of DeepSeek's V4-Flash tier — the April V4-Flash preview retrained on a substantially improved post-training pipeline targeting coding, agents, reasoning, and tool use, with no change to the base architecture. Retains 284B total / 13B active parameters (MoE) and the 1M-token context window. DeepSeek reports the 0731 build scoring higher than its own larger V4-Pro-Preview on all nine agent and coding benchmarks it published — a vendor-reported result, with independent replication still limited at launch. Weights released on Hugging Face under the MIT license; API pricing held at $0.14 / $0.28 per Mtok. The upgrade is silent for existing callers: same endpoint, same key, same deepseek-v4-flash model name, zero migration cost.

Efficient V4 companion model with 284B total / 13B active parameters and the same one-million-token context window.

Preview-series sparse MoE flagship with a one-million-token context window and 1.6T total / 49B active parameters.

Reasoning-first agent model that adds DeepSeek Sparse Attention and thinking directly inside tool-use workflows.

High-compute reasoning variant of V3.2, positioned for olympiad-level math, programming, and other deep reasoning tasks.

Experimental checkpoint that introduced DeepSeek Sparse Attention as an efficiency bridge between V3.1-Terminus and V3.2.

Stability update to V3.1 focused on language consistency, code-agent reliability, and search-agent behavior.

Hybrid thinking/non-thinking release that upgraded tool calling, long-context training, and agent task performance.

Rumored successor to DeepSeek R1. Reports say development and launch timing were affected by hardware constraints around Huawei Ascend training and Nvidia availability; final specs, license, and release date remain unconfirmed.

Major R1 reasoning update with stronger math, programming, general logic, function calling, and reduced hallucinations.

Post-R1 V3 update with improved reasoning, front-end coding, Chinese writing, search, and function calling.

Breakout open reasoning model trained with large-scale reinforcement learning and released with weights under MIT.

The 671B/37B-active MoE release that made DeepSeek a central open-model lab before the R1 breakthrough.

Reasoning-preview model exposed in DeepSeek Chat ahead of the open DeepSeek-R1 release.

Unified DeepSeek V2 generation combining general-chat and coding strengths before the V3 series.

Open code-focused MoE built from DeepSeek-V2, expanding programming-language coverage and coding benchmark performance.

DeepSeek's first major MoE general model with Multi-head Latent Attention and low-cost API positioning.

Early DeepSeek sparse MoE research model that foreshadowed the later V2/V3 architecture direction.

First general DeepSeek language model family, with 7B and 67B base/chat checkpoints.

DeepSeek's first public code-model family, released before the general DeepSeek LLM line.