Skip to main content

DeepSeek-V3.2 (Non-thinking)

DeepSeekDeepSeekOpen WeightMIT · Commercial OK

Description

DeepSeek-V3.2 in non-thinking mode. A powerful language model with 685B parameters using DeepSeek Sparse Attention (DSA) for efficient long-context processing. Supports JSON output, tool calls, and chat prefix completion. This is the standard chat mode without extended reasoning.

Release Date
2025-12-01
Parameters
685.0B
Context Length
164K
Modalities
text

Capability Radar

0
general
0
coding
0
reasoning
0
scienceest.
0
agents
0
multimodal

Science uses a reasoning proxy when dedicated science benchmarks are unavailable.

Rankings

No ranking data available

Benchmark Scores (LLM Stats)

No benchmark data available

AA Evaluation Indices

No AA evaluation data available

LLM Stats Category Scores

No category score data available

Pricing

Input Price$0.28 / 1M tokens
Output Price$0.42 / 1M tokens
Blended Price (3:1)$0.315 / 1M tokens

Speed

No speed data available

Available Providers

(LS internal units)
ProviderInput PriceOutput Price
DeepSeek280K420K

External Sources