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
1.0M
Modalities
text

Capability Radar

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

Science is estimated from LLM Stats science scores or reasoning when no dedicated science benchmarks are available.

Rankings

No ranking data available

Benchmark Scores (LLM Stats)

(LLM Stats (zeroeval))

No benchmark data available

AA Evaluation Indices

(Artificial Analysis)

No AA evaluation data available

LLM Stats Category Scores

(LLM Stats (zeroeval))

No category score data available

Pricing

Input Price$0 / 1M tokens
Output Price$0 / 1M tokens
Blended Price (3:1)$0 / 1M tokens
Cache Read Price$0.0028 / 1M tokens

Speed

No speed data available

Provider Price Ranking

Provider Price Ranking

8 providers

Cheapest: DeepSeekMost Expensive: Helicone
ProviderInputOutput
1DeepSeekPRIMARY
$0
$0
2NanoGPT
$0.1
$0.425
3OrcaRouter
$0.14
$0.28
4OpenRouter
$0.2574
$1.0287
5ZenMux
$0.28
$0.42
6302.AI
$0.29
$0.43
7Kilo Gateway
$0.4
$1.3
8Helicone
$0.56
$1.68

Compare pricing across different API providers for this model.

External Sources