# DeepSeek's V4-Flash is cheapest well-known AI model to run, study finds

> DeepSeek's V4-Flash costs far less to run than rival AI models, research firm says.

*Artificial Analysis found the Chinese model costs 3 cents per test, versus $1.86 for GPT-5.6 Sol and $3.15 for Claude Fable 5*

By Behzad Hosseini · WireRead
Canonical: https://wireread.com/news/deepseek-s-v4-flash-is-cheapest-well-known-ai-model-to-run-study-finds

DeepSeek's newly released V4-Flash model is by far the cheapest well-known AI model to run, according to research firm Artificial Analysis, which tested it against rivals from OpenAI, Anthropic and others.

Artificial Analysis said the San Francisco firm found V4-Flash averaged 3 cents per test, compared with 86 cents for Moonshot's Kimi K3, $1.86 for OpenAI's GPT-5.6 Sol and $3.15 for Anthropic's Claude Fable 5, making it more than 100 times cheaper to run than Fable 5.

DeepSeek released V4-Flash on Friday 31 July 2026, and Reuters reported the cost findings on 3 August, according to [the report via Yahoo Finance](https://finance.yahoo.com/technology/ai/articles/deepseeks-ai-model-far-cheapest-054143251.html).

The model's list price is $0.14 per million input tokens and $0.28 per million output tokens, Artificial Analysis said.

Artificial Analysis said it measures cost per test rather than list price alone, because a model that looks cheap per token can still cost more overall if it needs many more steps to reach a correct answer.

On performance, V4-Flash scored 50 out of 100 on the Artificial Analysis Intelligence Index, a measure across nine benchmarks covering coding, reasoning and workplace tasks, according to [The Next Web](https://thenextweb.com/news/deepseek-v4-flash-cheapest-ai-model-to-run). That places it level with Google's Gemini 3.6 Flash, one point behind Meta's Muse Spark 1.1 and Z.ai's GLM-5.2, and at least nine points behind Claude Opus 5, Fable 5 and GPT-5.6. Kimi K3 scored 57.

V4-Flash uses a mixture-of-experts architecture with about 284 billion total parameters and about 13 billion active per request, hybrid attention, and a 1 million token context window, Artificial Analysis said.

DeepSeek is reportedly preparing for a possible initial public offering. Its R1 model triggered a global tech sell-off in early 2025. Analysts have not yet said whether V4-Flash's pricing will affect competitors' strategies.

## Key takeaways

- V4-Flash averages 3 cents per benchmark test, versus $1.86 for GPT-5.6 Sol and $3.15 for Claude Fable 5
- The model scores 50 out of 100 on the Artificial Analysis Intelligence Index, level with Gemini 3.6 Flash
- DeepSeek is reportedly preparing for a possible IPO after its R1 model triggered a 2025 tech sell-off

## Sources

- [DeepSeek's new AI model is by far the cheapest of well-known models to run, research firm says](https://finance.yahoo.com/technology/ai/articles/deepseeks-ai-model-far-cheapest-054143251.html) — Reuters via Yahoo Finance, 2026-08-03
- [DeepSeek's V4-Flash is the cheapest well-known AI model to run, research firm finds](https://thenextweb.com/news/deepseek-v4-flash-cheapest-ai-model-to-run) — The Next Web, 2026-08-03