DeepSeek V4 Flash
AffordableEfficiency-optimized DeepSeek V4 at 284B total / 13B active for fast, high-throughput inference.
1M-token context with hybrid attention and configurable reasoning modes. Ideal for coding assistants, chat systems, and agent workflows where speed and cost matter.
▼
DeepSeek V4 Flash is somewhat expensive at $0.09/M tokens input and $0.19/M tokens output. Cached input reads are priced at $0.02/M tokens, making repeated context cheaper. The model supports extended reasoning, a 1M context window.
Benchmarks
This model hasn't been evaluated by Artificial Analysis yet. Benchmark scores will appear once they're published.
Specifications
Performance
Providers
Misc
Compare with
GPT 5.6 Solvs DeepSeek V4 FlashGPT 5.6 Lunavs DeepSeek V4 Flash
Claude Fable 5vs DeepSeek V4 FlashClaude Opus 4.8vs DeepSeek V4 FlashClaude Sonnet 5vs DeepSeek V4 FlashClaude Haiku 4.5vs DeepSeek V4 Flash
Gemini 3.6 Flashvs DeepSeek V4 FlashGemini 3.5 Flashvs DeepSeek V4 FlashGemini 3.5 Flash-Litevs DeepSeek V4 FlashGemma 4 31Bvs DeepSeek V4 Flash
Grok 4.5vs DeepSeek V4 FlashGrok Build 0.1vs DeepSeek V4 FlashGrok 4.1 Fastvs DeepSeek V4 Flash
Muse Spark 1.1vs DeepSeek V4 Flash
DeepSeek V4 Provs DeepSeek V4 Flash
MiniMax M3vs DeepSeek V4 Flash
GLM 5.2vs DeepSeek V4 Flash
Qwen3.7 Maxvs DeepSeek V4 FlashQwen3.7 Plusvs DeepSeek V4 FlashQwen3 Coder Nextvs DeepSeek V4 Flash
Nemotron 3 Ultravs DeepSeek V4 Flash
Mistral Small 4vs DeepSeek V4 FlashFrequently Asked Questions about DeepSeek V4 Flash▼
When was DeepSeek V4 Flash released?
▼
DeepSeek V4 Flash was released on April 24, 2026.
Who created DeepSeek V4 Flash?
▼
DeepSeek V4 Flash was created by DeepSeek.
How much does DeepSeek V4 Flash cost?
▼
DeepSeek V4 Flash costs $0.09/M input tokens and $0.19/M output tokens.
What is DeepSeek V4 Flash API pricing?
▼
The DeepSeek V4 Flash API is priced at $0.09 per million input tokens and $0.19 per million output tokens. You can access DeepSeek V4 Flash through idapt.app alongside 200+ other AI models in one workspace.
Is DeepSeek V4 Flash a reasoning model?
▼
Yes, DeepSeek V4 Flash is a reasoning model. It can think step-by-step through complex problems before providing an answer, often yielding better results on difficult tasks like math, coding, and multi-step logic.
Does DeepSeek V4 Flash support image or vision input?
▼
No, DeepSeek V4 Flash does not currently support image or vision input. It is a text-only model.
Does DeepSeek V4 Flash support audio?
▼
No, DeepSeek V4 Flash does not support audio input.
What is the context window of DeepSeek V4 Flash?
▼
DeepSeek V4 Flash has a context window of 1M tokens, meaning it can process approximately 786,431 words of context at once.
Is DeepSeek V4 Flash open source?
▼
DeepSeek V4 Flash is a proprietary model developed by DeepSeek. The model weights and training data are not publicly available.
Where can I use DeepSeek V4 Flash?
▼
You can chat with DeepSeek V4 Flash on idapt.app — no separate API key required. idapt is an AI workspace with 200+ models, agents, computers, and tasks. You can also access DeepSeek V4 Flash through DeepSeek's own API or platform.