DeepSeek

DeepSeek is a Chinese AI company founded in 2023, focused on general-purpose large language models. It keeps an open-source strategy and is a key driver of China's open LLM ecosystem. In 2024–2025, DeepSeek-V3 and DeepSeek-R1 drew global attention for high performance, low cost, and strong reasoning, popularizing affordable Chinese AI.

AI Tools

DeepSeek Harness

Everything is a plugin: build agents that keep working in real scenarios

DeepSeek

AI assistant and open-source large model by High-Flyer

AI Models

DeepSeek V4.1 Flash 1017

DeepSeek

DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name. 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 output from a 552B-parameter backbone, an asymmetric split that keeps per-token compute low relative to the model's total size. Image understanding is native to the architecture, with visual and text embeddings trained jointly from the start of pre-training rather than added afterward as in the earlier experimental V4 Flash Vision Exp. It is suited for coding, terminal, and computer-use agents, along with long-horizon tasks that must run to completion across many steps and long-context analysis. Compressed KV caching cuts cache memory to roughly a quarter of the previous Flash generation, significantly reducing costs on agentic workloads. DeepSeek positions it as the cost-efficient tier of the V4.1 family and reports that it exceeds V4 Pro on performance, speed, and task completion time.

Context: 1M
Max output: -
Released: 2026-10-17

Input: $0.15 /M
Output: $0.6 /M

DeepSeek V4.1 Flash

DeepSeek

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 output from a 552B-parameter backbone, an asymmetric split that keeps per-token compute low relative to the model's total size. Image understanding is native to the architecture, with visual and text embeddings trained jointly from the start of pre-training rather than added afterward as in the earlier experimental V4 Flash Vision Exp. It is suited for coding, terminal, and computer-use agents, along with long-horizon tasks that must run to completion across many steps and long-context analysis. Compressed KV caching cuts cache memory to roughly a quarter of the previous Flash generation, significantly reducing costs on agentic workloads. DeepSeek positions it as the cost-efficient tier of the V4.1 family and reports that it exceeds V4 Pro on performance, speed, and task completion time.

Context: 1M
Max output: -
Released: 2026-09-10

Input: $0.14 /M
Output: $0.42 /M

DeepSeek V4 Flash Vision Exp

DeepSeek

DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of DeepSeek V4 Flash 0731 from DeepSeek, adding image understanding while matching the base model on text capabilities including agents, reasoning, and world knowledge. It is a sparse mixture-of-experts model with 13B active parameters out of 284B total. It is suited for document and chart understanding, visual question answering, and multimodal agent workflows that interleave text and images.

Context: 1M
Max output: -
Released: 2026-08-21

Input: $0.2156 /M
Output: $0.6468 /M

DeepSeek V4 Pro 0813

DeepSeek

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

Context: 1M
Max output: -
Released: 2026-08-12

Input: $0.66 /M
Output: $1.98 /M

DeepSeek V4 Flash 0731

DeepSeek

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. This is the GA release of DeepSeek V4 Flash.

Context: 1M
Max output: -
Released: 2026-07-31

Input: $0.119 /M
Output: $0.238 /M

DeepSeek V4 Pro 0423

DeepSeek

DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding, and long-horizon agent workflows, with strong performance across knowledge, math, and software engineering benchmarks. Built on the same architecture as DeepSeek V4 Flash, it introduces a hybrid attention system for efficient long-context processing. Reasoning efforts high and xhigh are supported; xhigh maps to max reasoning. It is well suited for complex workloads such as full-codebase analysis, multi-step automation, and large-scale information synthesis, where both capability and efficiency are critical

Context: 1M
Max output: -
Released: 2026-04-24

Input: $0.8754 /M
Output: $1.7508 /M

DeepSeek V4 Flash 0423

DeepSeek

DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and high-throughput workloads, while maintaining strong reasoning and coding performance. The model includes hybrid attention for efficient long-context processing. Reasoning efforts high and xhigh are supported; xhigh maps to max reasoning. It is well suited for applications such as coding assistants, chat systems, and agent workflows where responsiveness and cost efficiency are important.

Context: 1M
Max output: -
Released: 2026-04-24

Input: $0.14 /M
Output: $0.28 /M

DeepSeek V3.2

DeepSeek

DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism that reduces training and inference cost while preserving quality in long-context scenarios. A scalable reinforcement learning post-training framework further improves reasoning, with reported performance in the GPT-5 class, and the model has demonstrated gold-medal results on the 2025 IMO and IOI. V3.2 also uses a large-scale agentic task synthesis pipeline to better integrate reasoning into tool-use settings, boosting compliance and generalization in interactive environments. Users can control the reasoning behaviour with the reasoning enabled boolean. Learn more in our docs

Context: 163.8K
Max output: -
Released: 2025-12-01

Input: $0.28 /M
Output: $0.42 /M

DeepSeek V3.2 Exp

DeepSeek

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 designed to improve training and inference efficiency in long-context scenarios while maintaining output quality. Users can control the reasoning behaviour with the reasoning enabled boolean. Learn more in our docs The model was trained under conditions aligned with V3.1-Terminus to enable direct comparison. Benchmarking shows performance roughly on par with V3.1 across reasoning, coding, and agentic tool-use tasks, with minor tradeoffs and gains depending on the domain. This release focuses on validating architectural optimizations for extended context lengths rather than advancing raw task accuracy, making it primarily a research-oriented model for exploring efficient transformer designs.

Context: 163.8K
Max output: -
Released: 2025-09-29

Input: $0.27 /M
Output: $0.41 /M

DeepSeek V3.1 Terminus

DeepSeek

DeepSeek-V3.1 Terminus is an update to DeepSeek 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 performance in coding and search agents. It is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes. It extends the DeepSeek-V3 base with a two-phase long-context training process, reaching up to 128K tokens, and uses FP8 microscaling for efficient inference. Users can control the reasoning behaviour with the reasoning enabled boolean. Learn more in our docs The model improves tool use, code generation, and reasoning efficiency, achieving performance comparable to DeepSeek-R1 on difficult benchmarks while responding more quickly. It supports structured tool calling, code agents, and search agents, making it suitable for research, coding, and agentic workflows.

Context: 163.8K
Max output: -
Released: 2025-09-22

Input: $0.27 /M
Output: $1 /M

DeepSeek V3.1

DeepSeek

DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context training process, reaching up to 128K tokens, and uses FP8 microscaling for efficient inference. Users can control the reasoning behaviour with the reasoning enabled boolean. Learn more in our docs The model improves tool use, code generation, and reasoning efficiency, achieving performance comparable to DeepSeek-R1 on difficult benchmarks while responding more quickly. It supports structured tool calling, code agents, and search agents, making it suitable for research, coding, and agentic workflows. It succeeds the DeepSeek V3-0324 model and performs well on a variety of tasks.

Context: 163.8K
Max output: -
Released: 2025-08-21

Input: $0.25 /M
Output: $0.95 /M

R1 0528

DeepSeek

May 28th update to the original DeepSeek R1 Performance on par with OpenAI o1, but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass. Fully open-source model.

Context: 163.8K
Max output: -
Released: 2025-05-28

Input: $0.5 /M
Output: $2.15 /M

DeepSeek V3 0324

DeepSeek

DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the DeepSeek V3 model and performs really well on a variety of tasks.

Context: 163.8K
Max output: -
Released: 2025-03-24

Input: $0.29 /M
Output: $1.14 /M

R1 Distill Llama 70B

DeepSeek

DeepSeek R1 Distill Llama 70B is a distilled large language model based on Llama-3.3-70B-Instruct, using outputs from DeepSeek R1. The model combines advanced distillation techniques to achieve high performance across multiple benchmarks, including: - AIME 2024 pass@1: 70.0 - MATH-500 pass@1: 94.5 - CodeForces Rating: 1633 The model leverages fine-tuning from DeepSeek R1's outputs, enabling competitive performance comparable to larger frontier models.

Context: 8.2K
Max output: -
Released: 2025-01-23

Input: $0.8 /M
Output: $0.8 /M

R1

DeepSeek

DeepSeek R1 is here: Performance on par with OpenAI o1, but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass. Fully open-source model & technical report. MIT licensed: Distill & commercialize freely!

Context: 64K
Max output: -
Released: 2025-01-20

Input: $0.7 /M
Output: $2.5 /M

DeepSeek V3

DeepSeek

DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations...

Context: 163.8K
Max output: -
Released: 2024-12-26