DeepSeek · Deepseek V4 Flash Base · active
DeepSeek-V4-Flash-Base
DeepSeek-V4-Flash-Base is an open-weight language model published by DeepSeek.
deepseek-ai/DeepSeek-V4-Flash-BaseProvider availability
Serving endpoints and pricing
This page represents one immutable developer model ID. Serving endpoints, pricing, regions, quantizations, and service tiers attach separately and never create duplicate model records.
Technical specification
Capabilities
Version lineage
Explicit unknowns
- Maximum output
- Knowledge cutoff
- API availability
- Provider pricing
Comparable peers
Related model comparisons
Questions
DeepSeek-V4-Flash-Base FAQs
What is DeepSeek-V4-Flash-Base?+
DeepSeek-V4-Flash-Base is an open-weight language model published by DeepSeek. It is developed by DeepSeek and its current sourced lifecycle status is active.
What inputs and outputs does DeepSeek-V4-Flash-Base support?+
DeepSeek-V4-Flash-Base's current record lists Text as input and Text as output.
How much context does DeepSeek-V4-Flash-Base support?+
The current record lists a 1,048,576-token context window and does not report a maximum output length.
Is DeepSeek-V4-Flash-Base available through an API?+
DeepSeek-V4-Flash-Base's current primary-source record does not establish API availability. No provider endpoint is treated as available without direct provider evidence.
How large is DeepSeek-V4-Flash-Base?+
The current record lists 292B total parameters and an unknown active parameter count. Its architecture is DeepseekV4ForCausalLM.
What capabilities and tasks does DeepSeek-V4-Flash-Base support?+
DeepSeek-V4-Flash-Base's recorded capabilities are generation. Its supported tasks are text.
Can DeepSeek-V4-Flash-Base be self-hosted?+
DeepSeek-V4-Flash-Base is an open-weight model. Self-hosting is supported, with no license recorded.
Does DeepSeek-V4-Flash-Base have related versions or aliases?+
No predecessor is recorded. No successor is recorded. Recorded aliases are deepseek-ai/DeepSeek-V4-Flash-Base.
Which models can DeepSeek-V4-Flash-Base be compared with?+
The current compatible peer set includes DeepSeek-V4-Flash, DeepSeek-V4-Pro, DeepSeek-V4-Pro-Base, DeepSeek-V3.2, and Llama-4-Maverick-17B-128E. Compatibility requires shared sourced modalities and tasks; it does not imply that one model is better. Browse model comparisons →
How current is the Model Markets record for DeepSeek-V4-Flash-Base?+
DeepSeek-V4-Flash-Base was last verified Aug 28, 2026 from DeepSeek's primary source, “deepseek-ai/DeepSeek-V4-Flash-Base developer model repository.” The evidence is classified as official fact.
Primary evidence