DeepSeek: deepseek-v3 API
A state-of-the-art 671B MoE model (37B active) featuring Multi-head Latent Attention (MLA) and auxiliary-loss-free load balancing. It provides a hybrid "Think/Non-think" mode, delivering SOTA performance in coding, math, and agentic tasks while remaining the most cost-efficient flagship in the 2026 market.
- Context window: 128,000 tokens
- Max output: 64,000 tokens
- Input: text
- Output: text
- Reasoning: Supported
- Tool calling: Supported
- File input: Supported
- Released: 2024-12-25
- Knowledge cutoff: 2025-08-31
Frequently Asked Questions
What is the context window of deepseek-v3?
deepseek-v3 supports a context window of up to 128,000 tokens.
Does deepseek-v3 support function calling?
Yes. deepseek-v3 supports tool / function calling.
Does deepseek-v3 support reasoning?
Yes. deepseek-v3 is a reasoning-capable model.
What is the knowledge cutoff of deepseek-v3?
The knowledge cutoff of deepseek-v3 is 2025-08-31.