Skip to main content
Alibaba

Qwen API pricing

Every Qwen model we track, with the cheapest price per 1M tokens across 22 providers. Collected daily.

Cheapest input /1M
$0.030
Qwen3.7 Flash
Models
49
Providers
22
Last updated
October 9, 2026

Qwen API prices by model

Standard (real-time) rates per 1M tokens, newest first. “Cheapest” is the lowest input price across every provider we track; batch and cached-input rates are on each model page.

Qwen API pricing by model
ModelCheapest inputOutputCheapest on
Qwen3.8 2.4T A95B$2.00$6.00Together AI
Qwen3.8 27B$0.150$1.88Runcrate
Qwen 3.8 Max1.0M context$1.65$4.95Deep Infra
Qwen 3.8 Flash1.0M context$0.090$0.370EcoHash
Qwen3.8-Flash-Next$0.150$0.470Heabsy
Qwen3.7 Max$1.25$3.75Novita AI
Qwen3.7 Plus$0.320$1.28Velokey
Qwen3.7 Flash$0.030$0.130Prime Intellect
Qwen3.6 35B A3B$0.070$0.420Empirio Labs
Qwen 3.6 27B262K context$0.320$3.20Deep Infra
Qwen 3.6 Plus1.0M context$0.325$1.95OpenRouter
Qwen3.6 Max Preview$1.03$6.16OpenRouter
Qwen3.5 0.8B$0.040$0.080Prime Intellect
Qwen3.5 397B A17B$0.450$3.00Deep Infra
Qwen 3.5 9B256K context$0.090$0.130Empirio Labs
Qwen 3.5 35B262K context$0.080$0.750OpenRouter
Qwen 3.5 122B262K context$0.260$2.08OpenRouter
Qwen 3.5 27B262K context$0.260$2.60Deep Infra
Qwen3.5 4B$0.040$0.070Empirio Labs
Qwen 3.5 397B128K context$0.550$3.50DigitalOcean
Qwen3.5 2B$0.060$0.180Prime Intellect
Qwen3.5 Omni Flash$0.800$4.40Empirio Labs
Qwen3.5 Omni Plus$2.80$16.60Empirio Labs
Qwen3 Next 80B A3B$0.090$1.10Deep Infra
Qwen 3 32B41K context$0.080$0.280Deep Infra
Qwen 3 235B128K context$0.087$0.350GMI Cloud
Qwen 3 Coder 30B128K context$0.070$0.270Novita AI
Qwen3 Coder Next$0.120$0.800OpenRouter
Qwen 3 VL 235B262K context$0.200$0.880Deep Infra
Qwen 3 30B262K context$0.120$0.500Deep Infra
Qwen3 Coder 480B A35B Instruct$0.300$1.00Deep Infra
Qwen 3 Max262K context$0.780$3.90OpenRouter
Qwen 3 VL 30B131K context$0.150$0.600Deep Infra
Qwen3 VL 8B$0.117$0.455Prime Intellect
Qwen3 235B A22B 2507$0.090$0.550OpenRouter
Qwen 3 VL 32B128K context$0.104$0.416OpenRouter
Qwen 3 14B41K context$0.120$0.240Deep Infra
Qwen 3 8B41K context$0.117$0.455Prime Intellect
Qwen3 Omni 30B A3B$0.250$0.970Novita AI
Qwen 3 Coder Flash1.0M context$0.195$0.975OpenRouter
Qwen 3 Coder Plus1.0M context$0.650$3.25OpenRouter
Qwen3 Reranker 8B$0.200$0.0000Fireworks AI
Qwen 2.5 72B128K context$0.360$0.400Deep Infra
Qwen 2.5 VL 72B128K context$0.800$1.00OpenRouter
Qwen 2.5 7B128K context$0.100$0.200OpenRouter
Qwen 2.5 Coder 32B128K context$0.660$1.00OpenRouter
Qwen 2.5 14B128K context$0.800$0.800Together AI
Qwen2 Instruct 72B$0.900$0.900Together AI
Qwen Plus1.0M context$0.260$0.780OpenRouter

Qwen price history

Average input price per 1M tokens across the providers serving each model, last 90 days.

Frequently Asked Questions

What is the cheapest Qwen API?

Of the 49 Qwen models we track, Qwen3.7 Flash has the lowest input price right now: $0.030 per 1M input tokens on Prime Intellect. Prices are collected daily from 22 providers — see the table above for every model.

Where is Qwen3.8 2.4T A95B cheapest?

Qwen3.8 2.4T A95B is served by 3 providers we track. The lowest standard input price is $2.00 per 1M tokens on Together AI. Throughput, latency and context limits differ between hosts, so check the model page before committing.

Other model families