Qwen3.8 2.4T A95B

Updated Sep 11, 2026

qwen1.0M context1.0M max outputreleased Aug 12, 2026Open weightsReasoningTool calling

Cheapest input

$2

Cheapest output

$6

Official

—

output per 1M tokens

Providers

12

offering this model

Spread

1.0×

max / min output

Offers

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

Provider	1M input	1M output	1M cache read	1M cache write	Context
AIHubMixopen	Cheapest$2	Cheapest$6	$0.5	—	262k
Deep Infraopen	$2	$6	$0.2	—	262k
Eden AIopen	$2	$6	$0.25	$2.5	1.0M
Fireworks AIopen	$2	$6	$0.25	—	262k
Charm Hyperopen	$2	$6	$0.25	—	1.0M
Kilo Gatewayopen	$2	$6	$0.25	$2.5	1.0M
OpenRouteropen	$2	$6	$0.25	—	1.0M
Requestyopen	$2	$6	$0.2	—	262k
Vercel AI Gatewayopen	$2	$6	$0.25	—	262k
Cortecsopen	$2.5	$6	$0.625	—	262k
Requestyeuopen	$2.5	$6	$0.63	—	1.0M
Hugging Faceopen	$2.5	$6.25	—	—	262k
Merge Gatewayopen	$2.5	$6.25	$0.5	—	262k

Other qwen models