DeepSeek-V4-Flash (Non-Reasoning)
Pricing & Specs
DeepSeek · $0.44 input / $1.32 output per 1M tokens · 1M context window
No longer offered on OpenMark
DeepSeek-V4-Flash (Non-Reasoning) is no longer offered on OpenMark (deprecated or superseded upstream).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-V4-Flash (Non-Reasoning) API Pricing
| Tokens | Price |
|---|---|
| Input | $0.44 / 1M tokens |
| Output | $1.32 / 1M tokens |
| Cached input | $0.014 / 1M tokens |
Peak pricing (01:00-04:00 and 06:00-10:00 UTC). Off-peak rates are half of peak rates; registry uses peak.
What that means in practice
DeepSeek-V4-Flash (Non-Reasoning) Specs
| Spec | Value |
|---|---|
| Context window | 1M tokens |
| Max output tokens | 384K tokens |
| Input modalities | text |
| Output modalities | text |
| Reasoning model | No |
| Tool / function calling | Yes |
| JSON mode | Yes |
| Streaming | Yes |
| Prompt caching | Yes |
Notes
Retired. Legacy name still accepted but requests are served by DeepSeek-V4.1-Flash and billed at Flash price. Use deepseek-v4.1-flash. Calls deepseek-chat (V4 Flash) with reasoning disabled. Non-reasoning mode of deepseek-v4-flash. Off-peak pricing also available; registry uses peak rates for benchmarking.
FAQ
How much does DeepSeek-V4-Flash (Non-Reasoning) cost?
DeepSeek-V4-Flash (Non-Reasoning) costs $0.44 per 1M input tokens and $1.32 per 1M output tokens ($0.014 per 1M cached input tokens).
What is DeepSeek-V4-Flash (Non-Reasoning)'s context window?
DeepSeek-V4-Flash (Non-Reasoning) has a 1M-token context window. Maximum output is 384K tokens.
Can I test DeepSeek-V4-Flash (Non-Reasoning) on my own task?
DeepSeek-V4-Flash (Non-Reasoning) 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-V4-Flash (Non-Reasoning)?
It's been superseded. Benchmark its current alternatives on your actual
workload. You'll likely find something cheaper AND better. Free tier available.