DeepseekDeepSeek V3Tool use

DeepSeek V3.2 Exp pricing

DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism designed to improve training and inference efficiency in long-context scenarios while maintaining output quality. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-t. Below you will find 2 current rows with input and output dollars per million. Right now the lowest input is $0.200 and the lowest output is $0.400.

164K context·2 providers·verified May 2, 2026
Best input$0.200per 1M tokens · Openrouter
Best output$0.400per 1M tokens · Openrouter

Pricing across providers

All figures are list prices per million tokens unless a column says otherwise. 2 offers are listed for DeepSeek V3.2 Exp. Best input in this view: Openrouter.

O
Openrouter
Input / 1M
$0.200
Output / 1M
$0.400
N
Novita
Input / 1M
$0.270
Output / 1M
$0.410

Input vs output · per provider

Cost calculator

The calculator uses the same dollars per million tokens as the table. Adjust sliders to see how DeepSeek V3.2 Exp cost scales with traffic.

Provider

In: $0.200/M·Out: $0.400/M

0.020000¢ / req

0.020000¢ / req

Daily
$4.00
Monthly
$120
Annual
$1.5K

Model specifications

Context length, caps, and capability flags for DeepSeek V3.2 Exp. Family: DeepSeek V3. Values follow the main provider (Deepseek) record in our index.

Context window
163,840 tokens
Max output
163,840 tokens
Vision (images)
No
Tool / function calling
Yes
Streaming
No
Released
Sep 2025
Primary provider
Deepseek
Model family
DeepSeek V3

Compare DeepSeek V3.2 Exp

Open a pair page to see DeepSeek V3.2 Exp next to another model with a shared provider matrix. 6 shortcuts below.

Frequently asked questions

Answers pull from the same numbers you see on this page. The short model note from our index: DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention...

Yes. DeepSeek V3.2 Exp is available on Openrouter, Novita.

Also from Deepseek

Other models by Deepseek with live pricing in our catalog.