<- All Models

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...

164K context·$0.27 in·$0.40 out·Dec 2025 release·Reasoning, Tools / functions, Web search

Providers

Where DeepSeek V3.2 runs in Big-AGI, with each service's own model ID and USD-per-1M-token rates. The summary above prefers the creator's claim; rates below are each service's own.

ServiceModel IDContextInputOutputCache read

deepseek/deepseek-v3.2

164K

$0.27

$0.40

$0.13

deepseek.v3.2

164K

-

-

-

deepseek-v3.2

131K

$0.57

$1.71

-

Usage mix in Big-AGI: OpenRouter 100%Specs as reported by each service · usage over the last 2 days · refreshed hourly

Run DeepSeek V3.2 in Big-AGI.

Connect your own key on any of the services above, at their rates, no markup - and run it side by side with every other model.

Launch Big-AGI

© 2026 Token Fabrics·Built with passion in San Diego