Loading...
About
DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well...
Related Models
DeepSeek: DeepSeek V4 Pro2026-04-24DeepSeek V4 Pro (Reasoning, High Effort)2026-04-24DeepSeek: DeepSeek V4 Flash2026-04-24DeepSeek V4 Flash (Reasoning, High Effort)2026-04-24DeepSeek V4 Pro (Non-reasoning)2026-04-24DeepSeek V4 Flash (Non-reasoning)2026-04-24DeepSeek: DeepSeek V4 Flash (free)2026-04-24DeepSeek V3.2 (Reasoning)2025-12-01
Pricing
Input
$0.20
per 1M tokens
Output
$0.77
per 1M tokens
Blended
$0.34
per 1M tokens
Cheaper than 60% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.34
Monthly
$10.28
vs. Similar Models
Qwen: Qwen3 Next 80B A3B Instruct
$0.340%
Qwen3 VL 30B A3B (Reasoning)
$0.34-1%
DeepSeek V3.2 (Reasoning)
$0.34-2%
Grok 3 mini Reasoning (high)
$0.35+2%
Performance
Context Window
164K
tokens
Larger than 49% of models
Max Output
16K
tokens
10% of context
Context Window Comparison
DeepSeek: DeepSeek V3.2 Speciale
164KSame
DeepSeek: DeepSeek V3.1 Terminus
164KSame
DeepSeek: R1
164KSame