D

DeepSeek Models

Browse models from DeepSeek
DeepSeek is a large model developed by DeepSeek Company. DeepSeek-v3.1 was released in 2025, with deepseek-chat corresponding to non-thinking mode and deepseek-reasoner corresponding to thinking mode, and context has been expanded to 128K for both. - **Adheres to OpenAI Chat format calls**
D

DeepSeek-OCR2

Per Request:$0.04
DeepSeek-OCR 2 is a model released by DeepSeek on January 27, 2026, using the innovative DeepEncoder V2 method, which allows AI to dynamically rearrange parts of an image based on its meaning, rather than just mechanically scanning from left to right. While maintaining high data compression efficiency, the model has achieved significant breakthroughs in multiple benchmarks and production metrics. The model can cover complex document pages with only 256 to 1120 vision tokens, achieving an overall score of 91.09% in the OmniDocBench v1.5 evaluation
D

DeepSeek-V3.2

Context:128K
Input:$0.216/M
Output:$0.3456/M
DeepSeek v3.2 è l'ultima release di produzione della famiglia DeepSeek V3: una famiglia di grandi modelli linguistici a pesi aperti, incentrata sul ragionamento, progettata per la comprensione di contesti lunghi, l'uso robusto di agenti/strumenti, il ragionamento avanzato, la programmazione e la matematica.
D

DeepSeek V4

D

DeepSeek V4

Coming soon
Input:$60/M
Output:$240/M
coming soon
D

DeepSeek-V3

D

DeepSeek-V3

Input:$0.216/M
Output:$0.88/M
The most popular and cost-effective DeepSeek-V3 model. 671B full-blood version. This model supports a maximum context length of 64,000 tokens.
D

DeepSeek-V3.1

D

DeepSeek-V3.1

Input:$0.44/M
Output:$1.32/M
DeepSeek V3.1 is the upgrade in DeepSeek’s V-series: a hybrid “thinking / non-thinking” large language model aimed at high-throughput, low-cost general intelligence and agentic tool use. It keeps OpenAI-style API compatibility, adds smarter tool-calling, and—per the company—lands faster generation and improved agent reliability.
D

DeepSeek R2

D

DeepSeek R2

Coming soon
Input:$60/M
Output:$240/M
deepseek-r2 coming soon
D

DeepSeek-R1T2-Chimera

D

DeepSeek-R1T2-Chimera

Input:$0.2416/M
Output:$0.2416/M
A 671B parameter Mixture of Experts text generation model, merged from DeepSeek-AI's R1-0528, R1, and V3-0324, supporting up to 60k tokens of context.
D

DeepSeek-Reasoner

D

DeepSeek-Reasoner

Input:$0.44/M
Output:$1.752/M
DeepSeek-Reasoner is DeepSeek’s reasoning-first family of LLMs and API endpoints designed to (1) expose internal chain-of-thought (CoT) reasoning to callers and (2) operate in “thinking” modes tuned for multi-step planning, math, coding and agent/tool use.
D

DeepSeek-OCR

D

DeepSeek-OCR

Per Request:$0.04
DeepSeek-OCR is an optical character recognition model for extracting text from images and documents. It processes scanned pages, photos, and UI screenshots to produce transcriptions with layout cues such as line breaks. Common uses include document digitization, invoice and receipt intake, search indexing, and enabling RPA pipelines. Technical highlights include image-to-text processing, support for scanned and photographed content, and structured text output for downstream parsing.
D

DeepSeek-Chat

D

DeepSeek-Chat

Context:64K
Input:$0.216/M
Output:$0.88/M
The most popular and cost-effective DeepSeek-V3 model. 671B full-blood version. This model supports a maximum context length of 64,000 tokens.