DeepSeek · DeepSeek V4
DeepSeek V4 Flash
deepseek/deepseek-v4-flash
Fast DeepSeek V4 lane for economical reasoning, coding and long-context work.
Model specifications
- Context window
- 1M tokens
- Output limit
- 384K tokens
- Release date
- 2026-04-24
- Input modalities
- text
- Output modalities
- text
- Last updated
- 2026-04-24
Provider pricing
USD per 1M tokens. Limits may differ from the underlying model.
Checked 2026-08-06
OpenRouter
deepseek/deepseek-v4-flash
- Input
- $0.0882
- Output
- $0.18
- Context
- 1.05M
SiliconFlow
deepseek-ai/DeepSeek-V4-Flash
- Input
- $0.14
- Output
- $0.28
- Context
- 1M
Promotions, plan quotas, cache pricing and regional taxes are not included. Recheck the provider before purchase.
DeepSeek V4 Flash FAQ
Is DeepSeek V4 Flash an open-weight model?
Yes. DeepSeek V4 Flash is tracked as open weight; review the linked license and model source before redistribution or production deployment.
What is the context window for DeepSeek V4 Flash?
DeepSeek V4 Flash has a tracked context window of 1M tokens and a maximum output of 384K tokens. Provider limits can be lower.
What input does DeepSeek V4 Flash support?
The current record lists text input and text output. Check the exact provider route before relying on a modality in production.
How much does DeepSeek V4 Flash cost?
This page compares 2 tracked provider offerings in USD per 1M tokens where public prices are available. Promotions, cache rates, taxes and plan quotas may differ.