/ Models

Language models

DeepSeek: DeepSeek V3.2

DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...

Maker
Deepseek
Context window
164K
Max output
66K
Input / 1M
$0.269
Output / 1M
$0.4
1M in + 1M out
$0.669

Everything else

Max output66K
Input / 1M$0.269
Output / 1M$0.4
Cache read / 1M$0.135
Cache write / 1M
1M in + 1M out$0.669
Takestext
Returnstext
Toolsyes
Reasoningoptional
Open weightsyes
Released2025-12-01
Knowledge cutoff
Retires
Catalog iddeepseek/deepseek-v3.2

Benchmarks

sourceepoch
eci146.59
confidenceLikely
accessibilityOpen weights (unrestricted)

Benchmark scores by Epoch AI, CC BY 4.0.

Using it

In 00, this model is picked per agent — and per tier, so the model that answers your customers need not be the one that writes your code. Get 00.

← all models