Skip to content
llmprice

Qwen3 Max

Updated Sep 11, 2026

qwen262k context66k max outputreleased Sep 23, 2025ReasoningTool calling
Cheapest input
$0.359
Cheapest output
$1.43
Official (Alibaba)
$6
output per 1M tokens
Providers
22
offering this model
Spread
5.9×
max / min output

Offers

Metered per-token prices. Cheapest input and output are highlighted; marks a context-tier surcharge.

Provider1M input1M output1M cache read1M cache writeContext
Ofox$0.36Cheapest$1.43$0.072262k
Ofox$0.36$1.43$0.072256k
Merge GatewayCheapest$0.359$1.434$0.0718262k
OrcaRouter$0.359$1.434262k
DevPass (LLM Gateway)$0.845$3.38$0.6$3.75262k
LLM Gateway$0.845$3.38262k
Alibaba (China)$0.861$3.441262k
Kilo Gateway$0.78$3.9$0.156$0.975262k
OpenRouter$0.78$3.9$0.156$0.975262k
EmpirioLabs AI$1.08$5.52$1.08256k
Abacus$1.2$6131k
Alibaba$1.2$6262k
Cloudflare AI Gateway$1.2$6262k
Deep Infra$1.2$6$0.24256k
Eden AI$1.2$6$0.24$1.5262k
Eden AIeu$1.2$6$0.24$1.5262k
LLM Gateway$1.2$6$0.24$1.5256k
LLMTR$1.2$6256k
Vercel AI Gateway$1.2$6$0.24262k
Vercel AI Gateway$1.2$6$0.24262k
NanoGPT$1.2002$6.001$0.6001256k
NovitaAI$2.11$8.45262k
iFlowfreefreefree256k
iFlowfreefreefree256k

Subscription plans (not per-token)

Billed per month, not per token — never counted as the cheapest offer.

Provider1M input1M outputContext
Alibaba Coding Planplanfreefree262k
Alibaba Coding Plan (China)planfreefree262k

Other qwen models