Get an email when this model's blended price drops. No account needed.
One email per drop. Unsubscribe anytime.
Daily blended price ($/1M) — recorded each day, builds into a trend over time.
Typical 3:1 output-to-input mix, per 1M tokens
Price as of 2026-05-11 · Source: novita_reference_catalog
General-purpose text generation, chat, summarization and content workloads where broad capability and low cost matter most.
Novita AI serverless route for DeepSeek V4 Flash with 1M-token context and low-latency reasoning metadata.
deepseek/deepseek-v4-flash is a Text model from Novita AI (US). HotON.ai tracks it at $0.14 per 1M input tokens and $0.28 per 1M output tokens, with a 1049K-token context window. Its composite efficiency score is 96/100 at an estimated $0.000 per successful task.
deepseek/deepseek-v4-flash is tracked at $0.14 per 1M input tokens and $0.28 per 1M output tokens. A typical 3:1 output-to-input workload blends to roughly $0.25 per 1M tokens. Figures are illustrative demo data.
General-purpose text generation, chat, summarization and content workloads where broad capability and low cost matter most.
deepseek/deepseek-v4-flash supports up to a 1049K-token context window — large enough for long documents and extended conversations in a single request.
Within the HotON.ai tracked set, deepseek/deepseek-v4-flash is cheaper than 74% of models on input price and ranks #5 of 535 by overall efficiency.
Yes — ling-2.6-flash is a lower-cost option at $0.24 per 1M output tokens, while still covering similar Text use cases. Compare them side by side on HotON.ai.
Ready to paste into articles, papers or AI prompts — prices and date refresh with the live data.
HotON.ai — deepseek/deepseek-v4-flash (Novita AI): $0.14/1M input, $0.28/1M output, as of 2026-05-11. https://hoton.ai/en/models/novita-deepseek-deepseek-v4-flashPricing is real (via the TestKey catalog, updated daily). Quality (Arena Elo) is real where the model is ranked on LMArena. Efficiency is a modeled composite of real price and context.