DeepSeek V4 Flash (0731)
StandardThe GA release of DeepSeek's efficiency-optimized V4 Flash, re-post-trained for coding, reasoning, and agent workflows.
284B total / 13B active sparse MoE with a 1.3M-token context. The July 31 checkpoint keeps the low price and adds more stable tool use and agent behavior.
▼
DeepSeek V4 Flash (0731) is somewhat expensive at $0.07/M tokens input and $0.18/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
Specifications
Performance
Providers
Misc
Compare with
GPT 6 Astravs DeepSeek V4 Flash (0731)GPT 5.6 Lunavs DeepSeek V4 Flash (0731)
Claude Fable 5.1vs DeepSeek V4 Flash (0731)Claude Opus 5vs DeepSeek V4 Flash (0731)Claude Sonnet 5vs DeepSeek V4 Flash (0731)Claude Haiku 4.5vs DeepSeek V4 Flash (0731)
Gemini 3.8 Flashvs DeepSeek V4 Flash (0731)Gemini 3.5 Flashvs DeepSeek V4 Flash (0731)Gemini 3.5 Flash-Litevs DeepSeek V4 Flash (0731)Gemma 4 31Bvs DeepSeek V4 Flash (0731)
Grok 4.6vs DeepSeek V4 Flash (0731)Grok Build 0.1vs DeepSeek V4 Flash (0731)Grok 4.1 Fastvs DeepSeek V4 Flash (0731)
Muse Spark 1.3vs DeepSeek V4 Flash (0731)
DeepSeek V4 Pro (0813)vs DeepSeek V4 Flash (0731)DeepSeek V4 Flashvs DeepSeek V4 Flash (0731)
MiniMax M3vs DeepSeek V4 Flash (0731)
GLM 5.3vs DeepSeek V4 Flash (0731)GLM 5.3 Flashvs DeepSeek V4 Flash (0731)
Qwen3.8 Max (0902)vs DeepSeek V4 Flash (0731)Qwen3.7 Plusvs DeepSeek V4 Flash (0731)Qwen3 Coder Nextvs DeepSeek V4 Flash (0731)
Nemotron 3 Ultravs DeepSeek V4 Flash (0731)Frequently Asked Questions about DeepSeek V4 Flash (0731)▼
When was DeepSeek V4 Flash (0731) released?
▼
DeepSeek V4 Flash (0731) was released on July 31, 2026.
Who created DeepSeek V4 Flash (0731)?
▼
DeepSeek V4 Flash (0731) was created by DeepSeek.
How much does DeepSeek V4 Flash (0731) cost?
▼
DeepSeek V4 Flash (0731) costs $0.07/M input tokens and $0.18/M output tokens.
What is DeepSeek V4 Flash (0731) API pricing?
▼
The DeepSeek V4 Flash (0731) API is priced at $0.07 per million input tokens and $0.18 per million output tokens. You can access DeepSeek V4 Flash (0731) through idapt.app alongside 200+ other AI models in one workspace.
Is DeepSeek V4 Flash (0731) a reasoning model?
▼
Yes, DeepSeek V4 Flash (0731) 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 (0731) support image or vision input?
▼
No, DeepSeek V4 Flash (0731) does not currently support image or vision input. It is a text-only model.
Does DeepSeek V4 Flash (0731) support audio?
▼
No, DeepSeek V4 Flash (0731) does not support audio input.
What is the context window of DeepSeek V4 Flash (0731)?
▼
DeepSeek V4 Flash (0731) has a context window of 1M tokens, meaning it can process approximately 786,432 words of context at once.
Is DeepSeek V4 Flash (0731) open source?
▼
DeepSeek V4 Flash (0731) is a proprietary model developed by DeepSeek. The model weights and training data are not publicly available.
Where can I use DeepSeek V4 Flash (0731)?
▼
You can chat with DeepSeek V4 Flash (0731) 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 (0731) through DeepSeek's own API or platform.