DeepSeek V4 Flash
Fastby DeepSeek
Fast, lightweight V4 variant.
At a glance
- Provider
- DeepSeek
- Best for
- Fast
- Reads images
- No
- Price
- from $5 / 1M tokens
- Subscription
- None — pay as you go
Benchmarks
Higher is better.
- GPQA Diamond· graduate-level reasoning
- 89.4%
- AA Coding Index· real-world coding (composite)
- 56.2%
Source: artificialanalysis.ai, as of 13 Aug 2026. Figures are publisher-reported where not independently verified.
Use DeepSeek V4 Flash without a subscription
On the GPQA Diamond graduate-level reasoning benchmark, DeepSeek V4 Flash scores 89.4%. anyAInow gives you DeepSeek V4 Flash alongside every other top AI model from a single balance — from $5 / 1m tokens, with no monthly fee and tokens that never expire. Start a chat on DeepSeek V4 Flash, switch to another model mid-conversation, or run two models side by side to compare their answers. Top up from $5 and only pay for what you use.
Other models
DeepSeek V4.1 Flash
Newest fast, lightweight variant.
DeepSeek V4 Pro
High performance at low cost.
DeepSeek R1
The renowned open reasoning model, strong at logic and step-by-step problems.
GPT-5.4 mini
Fast, capable and great value for routine work.
GPT-5.6 Luna
The fast, low-cost tier of OpenAI's newest GPT-5.6 family.
GPT-6 Luna
The fast, low-cost tier of OpenAI's GPT-6 family.