About
DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...
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
$0.21
per 1M tokens
Output
$0.79
per 1M tokens
Blended
$0.35
per 1M tokens
Cheaper than 62% of models. Median price is $0.68/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.35
Monthly
$10.65
vs. Similar Models
Qwen: Qwen3.6 35B A3B
$0.350%
Qwen: Qwen3.5-35B-A3B
$0.350%
DeepSeek: DeepSeek V3
$0.35-1%
Grok 3 mini Reasoning (high)
$0.35-1%
Performance
Context Window
164K
tokens
Larger than 47% of models
Max Output
33K
tokens
20% of context
Context Window Comparison
DeepSeek V3.2 Speciale
164KSame
DeepSeek: DeepSeek V3.1 Terminus
164KSame
DeepSeek: R1
164KSame