← Model list
DeepSeek V3.2 TEE
deepseek·deepseek/deepseek-v3.2-2·GA·Open weights·deepseek series·NEW
Hybrid-reasoning DeepSeek model with thinking and non-thinking modes, sparse attention, and tool-use
At a glance
Reference price$1.00 / $1.00 per 1M
Cache read $0.10 · Chutes
Lowest paid$0.50 / $1.00
NanoGPT Gateway · 2× spread
Context131,072
⚠ Providers report 131,072–164,000; the table below is authoritative
Output limit65,536
Capabilities
ReasoningTool useStructured output✓ TemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
Text
Knowledge cutoff2024-07
Released / updated2025-12-01 / 2026-06-21
Quality & performance
Artificial Analysis doesn't cover this model (267 of 2059 have data). Quality data comes from independent evals covering widely used models.
Available at 2 providers2 with public prices
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
Your usage cost
1NanoGPT$120.00
2Chutes$142.00
The cheapest paid channel is the only channel.
Related models
DeepSeek V4 Flash Latestsame series$0.14 / $0.28DeepSeek V4 Flash 0423same series$0.138 / $0.275DeepSeek Latestsame series$1.10 / $2.50Qwen3-Next 80B-A3B Instructcheaper alternative$0.144 / $0.574Qwen3-Coder 30B-A3B Instructcheaper alternative$0.216 / $0.861Llama-3.1-8B-Instructcheaper alternative$0.15 / $0.45Qwen3 Coder Flashcheaper alternative$0.144 / $0.574
Price historyone sample accumulated per data sync
Input listOutput listMin blended