Models

October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding

DeepSeek V4.1 Flash model for reasoning and agentic coding

Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work

DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes

Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding

Open MoE flagship with million-token context for coding and long agent runs

Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work

DeepSeek V4 Pro initial snapshot with million-token context and support for thinking and non-thinking modes

Initial DeepSeek V4 Flash snapshot for economical reasoning, coding, and million-token agent workloads

High-accuracy OCR model for extracting text from documents, screenshots, receipts, and natural scenes

Hybrid-reasoning DeepSeek model with thinking and non-thinking modes, sparse attention, and tool-use

DeepSeek chat model for instruction following, coding, and analysis

DeepSeek reasoning model for multi-step analysis, math, coding, and tools

DeepSeek chat model for instruction following, coding, and analysis

Hybrid-reasoning DeepSeek model with thinking and non-thinking modes

DeepSeek R1 0528 distilled into Qwen3 8B for mathematics, coding, and reasoning

May 2025 DeepSeek R1 update with improved mathematics, coding, and reasoning

DeepSeek chat model for instruction following, coding, and analysis

March 2025 checkpoint of DeepSeek-V3 with improved reasoning and coding

Classic open reasoning model for transparent math, coding, and deliberate problem solving

R1 reasoning distilled into Qwen 2.5 32B for efficient open-weight step-by-step problem solving

Open DeepSeek MoE chat model for coding, math, and general reasoning

DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...

DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's...

DeepSeek R1 Distill Llama 70B is a distilled large language model based on [Llama-3.3-70B-Instruct](/meta-llama/llama-3.3-70b-instruct), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). The model combines advanced distillation techniques to achieve high performance across...

No provider description is available for this model yet.

DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.

DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....

DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of [DeepSeek V4 Flash 0731](https://openrouter.ai/deepseek/deepseek-v4-flash-0731) from DeepSeek, adding image understanding while matching the base model on text capabilities including agents,...

No provider description is available for this model yet.

DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....

DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...