DeepSeek V3.2
ActiveHybrid-reasoning DeepSeek model with thinking and non-thinking modes, sparse attention, and tool-use
View current API pricing for this model
Input, output, and cached rates with source and verification time, plus same-workload cost examples.
Input / 1M tokens
$0.62
Output / 1M tokens
$1.85
Record updated 2026-10-05
Modality:LLM
Context:163,840 tokens
Release:Dec 1, 2025
Pricing
Platform
Scope
Input
Output
Details
Aws_bedrock
Standard
$0.62
$1.85
164k context · 82k max output
How much are you overpaying?
Enter your monthly spend on this model to see what the same workload could cost on cheaper alternatives.
$
Enter a monthly spend to see the listed-rate comparison.
Latest changes
No recent changes.
Benchmarks
No benchmark data available.
⚡DeepSeek V3.2 Comparisons & Scenario Guides
Popular Price & Spec Comparisons
Related Scenario Rankings
AI Cost Optimization
Does this change your best option?
Check your models and usage for free. See the relevant official changes, estimated cost, and a practical next step.