DeepSeek-V3.2-Exp (Non-thinking Mode)
Pricing & Specs
DeepSeek · $0.28 input / $0.42 output per 1M tokens · 128K context window
No longer offered on OpenMark
DeepSeek-V3.2-Exp (Non-thinking Mode) is no longer offered on OpenMark (deprecated or superseded upstream). Its specs are kept here for reference. If you're still running it in production, it's worth benchmarking current alternatives: newer models are often cheaper AND better on the same task.
DeepSeek-V3.2-Exp (Non-thinking Mode) API Pricing
| Tokens | Price |
|---|---|
| Input | $0.28 / 1M tokens |
| Output | $0.42 / 1M tokens |
| Cached input | $0.028 / 1M tokens |
What that means in practice
DeepSeek-V3.2-Exp (Non-thinking Mode) Specs
| Spec | Value |
|---|---|
| Context window | 128K tokens |
| Input modalities | text |
| Output modalities | text |
| Latency (measured by OpenMark) | ~999ms median response |
| Reasoning model | No |
| Tool / function calling | Yes |
| JSON mode | Yes |
| Streaming | Yes |
| Prompt caching | Yes |
Capabilities
FAQ
How much does DeepSeek-V3.2-Exp (Non-thinking Mode) cost?
DeepSeek-V3.2-Exp (Non-thinking Mode) costs $0.28 per 1M input tokens and $0.42 per 1M output tokens ($0.028 per 1M cached input tokens).
What is DeepSeek-V3.2-Exp (Non-thinking Mode)'s context window?
DeepSeek-V3.2-Exp (Non-thinking Mode) has a 128K-token context window.
Can I test DeepSeek-V3.2-Exp (Non-thinking Mode) on my own task?
DeepSeek-V3.2-Exp (Non-thinking Mode) is no longer offered on OpenMark, but you can benchmark its current alternatives from DeepSeek and other providers on your own task, free tier available.
Still using DeepSeek-V3.2-Exp (Non-thinking Mode)?
It's been superseded. Benchmark its current alternatives on your actual
workload. You'll likely find something cheaper AND better. Free tier available.