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

qwen3-max-thinking API price — 3 gateways compared

Cheapest right now: Glama at $0.78/MTok in — 1.5× cheaper than the priciest gateway.

from $0.78 per million input tokens · 1.5× spread between gateways · updated continually

Gateway$ in /MTok$ out /MTok ContextInput price historyModel ID
OpenRouter fees$0.78$3.90262,144qwen/qwen3-max-thinkinguse
Glama$0.78$3.90262,144alibaba/qwen3-max-thinkinguse
DeepInfra$1.20$6.00256,000Qwen/Qwen3-Max-Thinkinguse

Fees beyond the token price

Changelog for qwen3-max-thinking

qwen3-max-thinking pricing FAQ

How much does qwen3-max-thinking cost per million tokens?

The cheapest tracked gateway charges $0.78 per million input tokens and $3.90 per million output tokens (Glama). Prices refresh continually.

Which gateway is cheapest for qwen3-max-thinking?

Glama for input tokens and Glama for output tokens, among the 3 gateways we track.

Do qwen3-max-thinking prices differ between gateways?

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

← All LLM prices · API