gpudiff the public record of change in GPU cloud pricing
Follow the diffs: RSS · Free API · Sponsor this site

DeepSeek V4 Flash API price — 6 gateways compared

DeepSeek · from $0.08 per million input tokens · 1.7× spread between gateways · updated hourly

Gateway$ in /MTok$ out /MTok ContextInput price historyModel ID
Glama$0.08$0.171,000,000since 2026-08-20deepseek/deepseek-v4-flash
OpenRouter fees$0.09$0.181,048,576deepseek/deepseek-v4-flash
DeepInfra$0.09$0.181,048,576since 2026-08-20deepseek-ai/DeepSeek-V4-Flash
Requesty$0.10$0.201,048,576since 2026-08-20deepinfra/deepseek-ai/DeepSeek-V4-Flash
Novita$0.14$0.281,048,576since 2026-08-20deepseek/deepseek-v4-flash
Ramp Router fees$0.14$0.281,048,576since 2026-08-20deepseek-v4-flash

Fees beyond the token price

Changelog for DeepSeek V4 Flash

DeepSeek V4 Flash pricing FAQ

How much does DeepSeek V4 Flash cost per million tokens?

The cheapest tracked gateway charges $0.08 per million input tokens and $0.17 per million output tokens (Glama). Prices refresh hourly.

Which gateway is cheapest for DeepSeek V4 Flash?

Glama for input tokens and Glama for output tokens, among the 6 gateways we track.

Do DeepSeek V4 Flash prices differ between gateways?

Yes — the most expensive tracked gateway charges 1.7× the cheapest for input tokens. Identical model, identical tokens, different bill.

← All LLM prices · API