Back to all models

DeepSeek V3.2

Latest DeepSeek V3 with tools and improved performance.

deepseek-v3.2
STABLEGet StartedView uptime
163,840 context
Starting at $0.23/M (20% off) input tokens
Starting at $0.34/M (20% off) output tokens
Streaming
Tools
Reasoning
JSON Output

Select Provider

All Providers for DeepSeek V3.2

LLM Gateway routes requests to the best providers that are able to handle your prompt size and parameters.

DeepSeek
Context: 163.8k15% off
Input
$0.28$0.238
15% off
/M tokens
Cached
$0.028$0.0238
15% off
/M tokens
Output
$0.42$0.357
15% off
/M tokens
Get Started
NovitaAI
Context: 163.8k
Input
$0.269
/M tokens
Cached
$0.1345
/M tokens
Output
$0.4
/M tokens
Get Started
Alibaba Cloud
Context: 131.1k20% off
Input
$0.57$0.456
20% off
/M tokens
Cached
$0.114$0.0912
20% off
/M tokens
Output
$1.71$1.368
20% off
/M tokens
Get Started
ByteDance
Context: 131.1k
Input
$0.28
/M tokens
Cached
$0.056
/M tokens
Output
$0.42
/M tokens
Get Started
Nebius AI
Context: 163.8k
Input
$0.3
/M tokens
Cached
—
/M tokens
Output
$0.45
/M tokens
Get Started
DeepInfra
Context: 160k
Input
$0.26
/M tokens
Cached
$0.13
/M tokens
Output
$0.38
/M tokens
Get Started