modelbenchmark.io

Qwen 3 Max Thinking

Alibaba · qwen3-max-thinking

Compare

Qwen reasoning model for deliberate problem solving, math, and coding

Specification

most-agreed values

Context
262K
Max output
66K
Released
2026-01-23
Knowledge cutoff
2025-01
Retires
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.78
Output
$3.90
Cache read
$0.24

Long-context price tiers

the rate above each context threshold

AbovePrice$/M
128KInput$1.95
128KOutput$9.75

Available from 4 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
kilo$0.78$3.90262K66K
openrouter$0.78$3.90262K66K
deepinfra$1.20$6.00$0.24256K
vercel$1.20$6.00$0.24256K66K

Price history

append-only observations · a listing writes a row only when its price moves

DateHostField$/M
2026-09-02openrouterInput$0.78
2026-09-06openrouterInput$0.78
2026-09-02openrouterOutput$3.90
2026-09-06openrouterOutput$3.90

More from Alibaba

most-hosted first