DeepSeek V3

deepseek

DeepSeek's updated V3 model released on March 24, 2025. A reliable general-purpose model with 131K context window and tool support. Offers excellent cost-effectiveness for standard chat and completion tasks. Superseded by V3.1 and V3.2 series with improved capabilities.

Try Now

Capabilities

Tool Use

Example Use Cases

General-purpose chat tasks

Tool use with moderate complexity

Cost-effective text generation

Technical Specifications

Context Window

131,072 tokens

Max Output

32,768 tokens

Cache Miss Cost

$0.216 per 1M tokens

Non-Reasoning Cost

$0.88 per 1M tokens

Cache Read Cost

$0.18 per 1M tokens

Web Search Cost

$15 per 1K calls

Code Execution Cost

$0.19 per 1K calls

⚠️ Legacy

Made legacy on

Reason

Superseded by V3.1

Recommended Replacement

DeepSeek V3.2