Identity
- Status
- retired
- Developer ID
deepseek-ai/DeepSeek-V4-Flash- Released
- Apr 24, 2026
- Version
- DeepSeek-V4-Flash
- License
- mit
DeepSeekV4 Flash
DeepSeek-V4-Flash is an open-weight language model published by DeepSeek.
- Token context
- 1,049K tokens
- Inputs
- Text
- Outputs
- Text
- Released
- Apr 24, 2026
Providers & Pricing
Estimate workload cost →| Provider | Input / 1M | Output / 1M | Cache read / 1M | Cache write / 1M | Observed | Evidence |
|---|---|---|---|---|---|---|
 DeepinfraAvailable | $0.090 | $0.18 | $0.018 | — | Oct 19, 2026 | Provider-reported |
DeepSeekAvailable | $0.22 | $0.66 | $0.007 | — | Sep 2, 2026 | Official fact |
 OpenrouterAvailable | $0.0868 | $0.1736 | $0.0174 | — | Aug 28, 2026 | Provider-reported |
Benchmarks
All benchmark results →| ARC-AGI-1verified-v1-613c385b0c93 | 89.00 | — | — | DeepSeek V4 Flash 0731 (Max)unknown | Original sourcewinner eligible | Third-party benchmark |
| ARC-AGI-2verified-v2-be40992860f9 | 61.39 | — | — | DeepSeek V4 Flash 0731 (Max)unknown | Original sourcewinner eligible | Third-party benchmark |
| LiveBench2026-06-25-90f8d44da965 | 78.08 | 21,079 | 1,270 | deepseek-v4-flash-0731average per case | Recomputedwinner eligible | Third-party benchmark |
| LiveBench2026-06-25-90f8d44da965 | 69.67 | 34,434 | 1,270 | deepseek-v4-flashaverage per case | Recomputedwinner eligible | Third-party benchmark |
| LMArena Text Arenatext-2026-10-15-a64ca3b12b6e | 1,431.84 | — | 51,987 | deepseek-v4-flash; 95% CI [1427.81979734, 1435.85552908]; votes 51987; rank 92unknown | Original sourcewinner eligible | Third-party benchmark |
At a Glance
Model Facts
Capacity
- Token context
- 1,049K tokens
- Maximum output
- Unknown
- Total parameters
- 290.9B
- Active parameters
- 13B
- Knowledge cutoff
- Not reported
Interface and Access
- Inputs
- Text
- Outputs
- Text
- API available
- Yes
- Open weights
- Yes
- Self-hostable
- Yes
- Reasoning
- Yes
- Vision
- No
- Tool calling
- No
- Capabilities
- chat, generation, reasoning
This page represents one developer model product. Dated API snapshots, serving endpoints, pricing, regions, quantizations, and service tiers attach as versioned aliases or provider details and never create duplicate public model records.
Version Lineage
PredecessorUnknown
SuccessorsUnknown
Aliasesdeepseek-ai/DeepSeek-V4-Flash, deepseek-ai/DeepSeek-V4-Flash
Explicit Unknowns
- Maximum output
- Knowledge cutoff
Primary Evidence
Sources and Observation Date
deepseek-ai/DeepSeek-V4-Flash developer model repositoryDeepSeek · observed Aug 28, 2026deepseek-ai/DeepSeek-V4-Flash README.md at 60d8d70770c6DeepSeek · observed Aug 28, 2026Deepinfra catalogDeepinfra · observed Oct 19, 2026deepseek-ai/DeepSeek-V4-Flash Hugging Face inference-provider mappingHugging Face · observed Aug 28, 2026DeepSeek Models & PricingDeepSeek · observed Sep 10, 2026OpenRouter deepseek/deepseek-v4-flash model APIOpenRouter · observed Aug 28, 2026deepseek-ai/DeepSeek-V4-Flash config.json at 60d8d70770c6DeepSeek · observed Aug 28, 2026deepseek-ai/DeepSeek-V4-Flash immutable Hub API metadataDeepSeek · observed Aug 28, 2026DeepSeek V4 Preview ReleaseDeepSeek · observed Aug 28, 2026deepseek-ai/DeepSeek-V4-Flash tokenizer_config.json at 60d8d70770c6DeepSeek · observed Aug 28, 2026Fireworks Ai catalogFireworks Ai · observed Oct 19, 2026Hugging Face catalogHugging Face · observed Sep 2, 2026
Comparable Peers
Related Model Comparisons
| A | Pair | B | Context |
|---|---|---|---|
DeepSeek V4 FlashDeepSeek | vs | DeepSeek V4.1 FlashDeepSeek | family variantstext |
DeepSeek V4 FlashDeepSeek | vs | DeepSeek V4 Flash BaseDeepSeek | family variantstext |
DeepSeek V4 FlashDeepSeek | vs |  Gemini 3.8 Flash CyberGoogle DeepMind | cross-developer peerstext |
DeepSeek V4 FlashDeepSeek | vs |  GLM 5.3 FlashZ.ai | cross-developer peerstext |
DeepSeek V4 FlashDeepSeek | vs | DeepSeek V4 Flash Vision ExpDeepSeek | family variantstext |
DeepSeek V4 FlashDeepSeek | vs | DeepSeek V4 Pro 0813DeepSeek | family variantstext |
DeepSeek V4 FlashDeepSeek | vs | Gemini 2.5 FlashGoogle DeepMind | cross-developer peerstext |
DeepSeek V4 FlashDeepSeek | vs | Gemini 3 FlashGoogle DeepMind | cross-developer peerstext |
DeepSeek V4 FlashDeepSeek | vs | Gemini 3.5 FlashGoogle DeepMind | cross-developer peerstext |
DeepSeek V4 FlashDeepSeek | vs | Gemini 3.7 FlashGoogle DeepMind | cross-developer peerstext |
DeepSeek V4 FlashDeepSeek | vs |  Sonar Reasoning ProPerplexity | cross-developer peerstext |
DeepSeek V4 FlashDeepSeek | vs | GLM 5.2Z.ai | cross-developer peerstext |
Questions
DeepSeek V4 Flash FAQs
What is DeepSeek V4 Flash?+
DeepSeek-V4-Flash is an open-weight language model published by DeepSeek. It is developed by DeepSeek and its current sourced lifecycle status is retired.
What inputs and outputs does DeepSeek V4 Flash support?+
DeepSeek V4 Flash's current record lists Text as input and Text as output.
How much context does DeepSeek V4 Flash support?+
The current record lists a 1,049K-token context window and does not report a maximum output length.
Is DeepSeek V4 Flash available through an API?+
DeepSeek V4 Flash is marked as API-available. The directly sourced provider records currently include Deepinfra, DeepSeek, Fireworks Ai, Hugging Face, and Openrouter.
How large is DeepSeek V4 Flash?+
The current record lists 290.9B total parameters and 13B active parameters. Its architecture is DeepseekV4ForCausalLM.
What capabilities and tasks does DeepSeek V4 Flash support?+
DeepSeek V4 Flash's recorded capabilities are chat, generation, and reasoning. Its supported tasks are text.
How much does DeepSeek V4 Flash cost through an API?+
The lowest directly sourced prices currently attached to DeepSeek V4 Flash are $0.0868 per million input tokens through Openrouter and $0.1736 per million output tokens through Openrouter. Prices are provider-specific and should be checked against each cited observation date.
Can DeepSeek V4 Flash be self-hosted?+
DeepSeek V4 Flash is an open-weight model. Self-hosting is supported, and the recorded license is mit.
Does DeepSeek V4 Flash have related versions or aliases?+
No predecessor is recorded. No successor is recorded. Recorded aliases are deepseek-ai/DeepSeek-V4-Flash.
Which models can DeepSeek V4 Flash be compared with?+
The current compatible peer set includes DeepSeek V4.1 Flash, DeepSeek V4 Flash Base, Gemini 3.8 Flash Cyber, GLM 5.3 Flash, and DeepSeek V4 Flash Vision Exp. Compatibility requires shared sourced modalities and tasks; it does not imply that one model is better. Browse model comparisons →