Skip to content
LLMs
DeepSeek logo

DeepSeek: DeepSeek V3.2

by DeepSeek

DeepSeek: DeepSeek V3.2 is a large language model from DeepSeek. It costs $0.269 per million input tokens and $0.400 per million output tokens. Its context window is 164K tokens.

ReasoningTool callingStructured outputPrompt cachingOpen weights
Input / 1M tokens
$0.269
Output / 1M tokens
$0.400
Cached input / 1M
$0.134

On repeated prefixes

Context window
164K

tokens

Who serves it cheapest

15 hosts serve DeepSeek V3.2. Same weights, same API - the price difference is pure margin and routing.

Providers serving DeepSeek: DeepSeek V3.2, cheapest first
ProviderInput / 1MOutput / 1MContextThroughputUptime 24h
GMICloudCheapestfp8$0.209$0.310164K-99.9%
StreamLakefp8$0.214$0.322128K-98.7%
DeepInfrafp4$0.260$0.380164K-99.2%
AtlasCloudfp8$0.260$0.380164K-99.6%
Venice$0.268$0.390160K-99.1%
SiliconFlowfp8$0.259$0.420164K-97.2%
Novitafp8$0.269$0.400164K-99.9%
Baidufp8$0.280$0.420131K-100.0%
DigitalOcean$0.300$0.960164K-93.9%
Alibabafp8$0.370$1.11131K-99.1%
Friendli$0.500$1.50164K-100.0%
Google$0.560$1.68164K-99.2%
Phala$1.00$1.00164K-98.7%
Mara$3.00$4.5033K-79.5%
SambaNova$3.00$4.5033K-90.8%

The spread between GMICloud and SambaNova is 14× for identical weights. Quantization and context limits differ, so check both columns before switching.

Benchmarks

Independent scores published alongside the catalogue.

Coding index
44.2

About 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...

Specifications

DeepSeek: DeepSeek V3.2 specifications
Model IDdeepseek/deepseek-v3.2
ProviderDeepSeek
Context window164K tokens
Max output66K tokens
Input modalitiestext
Output modalitiestext
Knowledge cutoff-
Open weightsYes - deepseek-ai/DeepSeek-V3.2
ReleasedDecember 1, 2025

Cheaper alternatives

Models that cost less than DeepSeek V3.2 while keeping at least half its context window and every input modality it supports.

Frequently asked

How much does DeepSeek: DeepSeek V3.2 cost?

$0.269 per million input tokens and $0.400 per million output tokens. Cached input reads cost $0.134 per million tokens.

What is the context window of DeepSeek: DeepSeek V3.2?

164K tokens, with up to 66K tokens of output per request.

Which provider serves DeepSeek: DeepSeek V3.2 cheapest?

GMICloud at $0.209 per million input tokens - 14× cheaper than SambaNova, the most expensive of the 15 hosts serving it.

Confirm against the source: DeepSeek official pricing.