gpudiff the public record of change in GPU cloud pricing

Follow the diffs: RSS · Free API · Sponsor this site

deepseek-v4.1-flash API price — 4 gateways compared

from $0.30 per million input tokens · same price on every gateway · updated continually

Gateway	$ in /MTok	$ out /MTok	Context	Input price history	Model ID
OpenRouter fees	$0.30	$1.20	1,048,576	since 2026-09-10	deepseek/deepseek-v4.1-flash	use
Requesty	$0.30	$1.20	1,000,000	since 2026-09-10	deepseek/deepseek-v4.1-flash	use
Novita	$0.30	$1.20	1,048,576	since 2026-09-10	deepseek/deepseek-v4.1-flash	use
DeepInfra	$0.30	$1.20	1,048,576	since 2026-09-10	deepseek-ai/DeepSeek-V4.1-Flash	use

Fees beyond the token price

OpenRouter: No markup on token prices (provider pass-through), but credit purchases cost 5.5% via card ($0.80 minimum) or 5% via crypto; BYOK usage above the monthly allowance is charged 5%. source

2026-09-10 requesty listed deepseek-v4.1-flash-output at 1.2 usd_per_mtok
2026-09-10 requesty listed deepseek-v4.1-flash-input at 0.3 usd_per_mtok
2026-09-10 openrouter listed deepseek-deepseek-v4.1-flash-output at 1.2 usd_per_mtok
2026-09-10 openrouter listed deepseek-deepseek-v4.1-flash-input at 0.3 usd_per_mtok
2026-09-10 novita listed deepseek-v4.1-flash-output at 1.2 usd_per_mtok
2026-09-10 novita listed deepseek-v4.1-flash-input at 0.3 usd_per_mtok
2026-09-10 deepinfra listed deepseek-v4.1-flash-output at 1.2 usd_per_mtok
2026-09-10 deepinfra listed deepseek-v4.1-flash-input at 0.3 usd_per_mtok

The cheapest tracked gateway charges $0.30 per million input tokens and $1.20 per million output tokens (DeepInfra). Prices refresh continually.

DeepInfra for input tokens and DeepInfra for output tokens, among the 4 gateways we track.

No — every tracked gateway currently charges the same per-token price, so the difference between them is fees and routing, not token cost.