DeepSeek V3.2 API
About
Build advanced reasoning agents with DeepSeek V3.2, a specialized AI model optimized for complex logic and chain-of-thought tasks. This model delivers cost-effective pricing at $0.49/1M input and $0.74/1M output tokens, native tool calling support, open weights architecture. Access DeepSeek V3.2 via the routing.run API with up to 164K output tokens.
Capabilities
Input Modalities
textimagevideo
Output Modalities
text
Limits
Context Window
164K
Tokens
Input Limit
164K
Tokens
Max Output
164K
Tokens
Pricing
Standard (per 1M tokens)
Input
$0.49
Output
$0.74
Frequently Asked Questions
DeepSeek V3.2 by routing.run costs $0.49 per 1M input tokens and $0.74 per 1M output tokens.
Model Details
ID
route/deepseek-v3.2
Provider
routing.runFamily
deepseek
Release Date
Dec 1, 2025
Knowledge Cutoff
Jul 1, 2024
API Integration
NPM Package
@ai-sdk/openai-compatible
Environment Variables
ROUTING_RUN_API_KEY
API Base URL
https://api.routing.run/v1