Model - One API Access 500+ AI Models - CometAPI

DeepSeek V4 Pro

DeepSeek V4 Pro

Output:$0.832/M

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.

DeepSeek V4 Flash

DeepSeek V4 Flash

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.

DeepSeek-OCR2

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

DeepSeek-V3.2

DeepSeek-V3.2

Output:$0.3456/M

DeepSeek v3.2 is the latest production release in the DeepSeek V3 family: a large, reasoning-first open-weight language model family designed for long-context understanding, robust agent/tool use, advanced reasoning, coding and math.

DeepSeek R2

DeepSeek R2

deepseek-r2 coming soon

DeepSeek-Reasoner

DeepSeek-Reasoner

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.

DeepSeek-OCR

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.

DeepSeek-Chat

DeepSeek-Chat

The most popular and cost-effective DeepSeek-V3 model. 671B full-blood version. This model supports a maximum context length of 64,000 tokens.