gpudiff the public record of change in GPU cloud pricing

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

Claude Sonnet 5 API price — 4 gateways compared

Cheapest right now: Glama at $2.00/MTok in — 1.5× cheaper than the priciest gateway.

Anthropic · from $2.00 per million input tokens · 1.5× spread between gateways · updated continually

Gateway	$ in /MTok	$ out /MTok	Context	Model ID
OpenRouter fees	$2.00	$10.00	1,000,000	anthropic/claude-sonnet-5	use
Requesty	$2.00	$10.00	1,000,000	vertex/claude-sonnet-5	use
Glama	$2.00	$10.00	1,000,000	anthropic/claude-sonnet-5	use
DeepInfra	$3.00	$15.00	1,000,000	anthropic/claude-sonnet-5	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

2026-09-02 deepinfra listed claude-sonnet-5-output at 15.0 usd_per_mtok
2026-09-02 deepinfra listed claude-sonnet-5-input at 3.0 usd_per_mtok
2026-09-01 deepinfra delisted claude-sonnet-5-output
2026-09-01 deepinfra delisted claude-sonnet-5-input
2026-08-27 requesty raised claude-sonnet-5-output 11.1%: 9.0 → 10.0 usd_per_mtok
2026-08-27 requesty raised claude-sonnet-5-input 11.1%: 1.8 → 2.0 usd_per_mtok

The cheapest tracked gateway charges $2.00 per million input tokens and $10.00 per million output tokens (Glama). Prices refresh continually.

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

Yes — the most expensive tracked gateway charges 1.5× the cheapest for input tokens. Identical model, identical tokens, different bill.