DeepSeek Models
Comprehensive benchmark scores, coding performance, latency metrics, and API pricing for all models developed by DeepSeek.
Available Models & Verified Benchmarks
Open-weight-adjacent DeepSeek flagship. High reasoning density per dollar.
DeepSeek Jul 31 2026 price-performance SKU. Public listings put it near $0.14/$0.28 per 1M tokens.
DeepSeek open-weight Mixture-of-Experts coding model supporting 338 programming languages and 128k context.
Open-weights reasoning model trained with large-scale RL.
Prior DeepSeek flagship. Baseline for v3 vs v4.
Auto-discovered from OpenRouter (deepseek/deepseek-v3.2). Preview until a second source matches.
Auto-discovered from OpenRouter (deepseek/deepseek-v3.2-exp). Preview until a second source matches.
Auto-discovered from OpenRouter (deepseek/deepseek-v3.1-terminus). Preview until a second source matches.
Auto-discovered from OpenRouter (deepseek/deepseek-chat-v3.1). Preview until a second source matches.
Auto-discovered from OpenRouter (deepseek/deepseek-r1-0528). Preview until a second source matches.
Auto-discovered from OpenRouter (deepseek/deepseek-chat-v3-0324). Preview until a second source matches.
Auto-discovered from OpenRouter (deepseek/deepseek-r1-distill-llama-70b). Preview until a second source matches.