DeepSeek AI Models

A text model listed as a large mixture-of-experts release with a 1,048,576-token provider context window.

Context

1.05M

Input

$1.32

Output

$3.96

DeepSeek-V3.1 is a hybrid model that supports both thinking mode and non-thinking mode. Compared to the previous version, this upgrade brings improvements in multiple aspects:

Context

164K

Input

$0.25

Output

$0.95

This update maintains the model's original capabilities while addressing issues reported by users, including:

Context

164K

Input

$0.27

Output

$1

We introduce **DeepSeek-V3.2**, a model that harmonizes high computational efficiency with superior reasoning and agent performance. Our approach is built upon three key technical breakthroughs:

Context

164K

Input

$0.269

Output

$0.40

We are excited to announce the official release of DeepSeek-V3.2-Exp, an experimental version of our model. As an intermediate step toward our next-generation architecture, V3.2-Exp builds upon V3.1-Terminus by introducing DeepSeek Sparse Attention—a sparse attention mechanism designed to explore and validate optimizations for training and inference efficiency in long-context scenarios.

Context

164K

Input

$0.27

Output

$0.41

We present a preview version of **DeepSeek-V4** series, including two strong Mixture-of-Experts (MoE) language models — **DeepSeek-V4-Pro** with 1.6T parameters (49B activated) and **DeepSeek-V4-Flash** with 284B parameters (13B activated) — both supporting a context length of **one million tokens**.

Context

1.02M

Input

$0.0826

Output

$0.1652

**DeepSeek-V4-Flash-0731** is the official release of **DeepSeek-V4-Flash**, superseding the preview version, with substantially enhanced agentic capabilities. It has the same model structure as DeepSeek-V4-Flash-DSpark, i.e. it comes with a speculative decoding module attached.

Context

1.05M

Input

$0.14

Output

$0.28

This model always redirects to the latest model in the DeepSeek V4 Flash family.

Context

1.02M

Input

$0.0786

Output

$0.1572

We present a preview version of **DeepSeek-V4** series, including two strong Mixture-of-Experts (MoE) language models — **DeepSeek-V4-Pro** with 1.6T parameters (49B activated) and **DeepSeek-V4-Flash** with 284B parameters (13B activated) — both supporting a context length of **one million tokens**.

Context

1.05M

Input

$1.32

Output

$3.96