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.

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.