DeepSeek V4-Flash is cheapest well-known model to run on Artificial Analysis tests, firm says

3 (Reuters) - A version of DeepSeek's flagship AI model is by far the least expensive to run among well-known models on benchmark tests and more than 100 times cheaper to run than Anthropic's Claude Fable 5, research firm Artificial Analysis found, Reuters reported. DeepSeek officially released V4-Flash on Friday. The model charges $0.14 per million input tokens and $0.28 per million output tokens, according to Artificial Analysis. The firm estimated average cost at 3 cents per test, versus 86 cents for Moonshot AI's Kimi K3, $1.86 for OpenAI's GPT-5.6 Sol, and $3.15 for Claude Fable 5. Artificial Analysis said the comparison accounts for how much data a model must process and generate to finish a task, not headline pricing alone. V4-Flash scored 50 out of 100 on the firm's Intelligence Index across nine coding, reasoning, and workplace-style benchmarks, matching Google's Gemini 3.6 Flash and trailing Meta's Muse Spark 1.1 and Z.AI's GLM-5.2 by one point. Kimi K3 scored 57, while Anthropic's Claude Opus 5 and Fable 5 and OpenAI GPT-5.6 scored nine or more points higher. DeepSeek is preparing a more powerful V4-Pro without a stated release date. Sources have said the startup is preparing for a potential IPO.