Qwen: Qwen3 VL 30B A3B ThinkingReasoning

qwen
$0.5output / 1M tokens

Best price — Output ($/1M tokens)

Markets

One row per access path (venue → underlying provider). Prices are each venue's published list price; performance is measured by Artificial Analysis. Your actual bill may vary by routing settings, fallbacks, region / ZDR, long-context tiers, and request features (JSON mode, tools, vision).

#ProviderClassInput $/MOutput $/MCache ($/M Read)vs consensusTTFTThroughputUptime 24hRequests 24h
1
fireworks
Direct host$0.5
$0.5
—-50.0% vs consensus
—
———
2
novita → qwen
Reseller$0.2
$1
—+0.0% vs consensus
—
———
3
siliconflow
Direct host$0.29
$1
—+0.0% vs consensus
—
———
4
openrouter → siliconflow
Reseller$0.29
$1
—+0.0% vs consensus
—
———
5
alibaba-cloud
Official$0.2
$2.4
—+140.0% vs consensus
2.2s
reasoning 2.3s
110.6 tps——
6
openrouter → qwen
Reseller$0.2
$2.4
—+140.0% vs consensus
—
———
7
deepinfra
Disabled by deepinfra · disabled · fp8
Direct host$0.29
$0.99
—-1.0% vs consensus
—
———
8
novita
Disabled by novita · stale
Direct host$0.2
$1
—+0.0% vs consensus
1.8s
91.6 tps——
9
openrouter → novita
Disabled by openrouter · disabled · fp16
Reseller$0.2
$1
—+0.0% vs consensus
—
———
Source ecosystem
Loading…