onomeoonomeoBeta

gpt-6-luna vs qwen3.8-2.4t-a95b

gpt-6-luna
2 advantages
qwen3.8-2.4t-a95b
1 advantage

How to choose

gpt-6-lunaLonger context: 1.1M tokensReads images
qwen3.8-2.4t-a95bOpen weights

gpt-6-luna

By OpenAI

qwen3.8-2.4t-a95b

By QwenNew in the last two weeks

Where they differ

gpt-6-lunaqwen3.8-2.4t-a95b
On this site
100%80 callsAvailability, last 3 days—
100%143 testsAvailability, this week's tests—
1.1sAverage response this week—
$0.75Reference price per million output tokens$9.00
#1Place in this week's rankingUnranked
$0.15Reference price per million input tokens$3.00
The model itself
1.1M tokensContext length256K tokens
YesReads imagesNo
May 2026Knowledge cutoffNot published
22 Sep 2026Released12 Aug 2026
NoOpen weightsYes
$0.015Reference price per million cache-read tokens$0.38

Where they match

  • Longest reply128K tokens
  • Calls toolsYes
  • Thinks before answeringYes
  • Conversations used for trainingUsed to train and improve the provider’s models

Availability over 3 days counts every call made through the site; this week's availability counts every call over the last 7 days, scheduled tests included, and response time comes from the site's own scheduled tests. Models marked as free are counted in calls; paid models are charged by usage, in US dollars.

Compare next

Figures come from real calls made through this site. Models are served by third-party providers and may slow down or be withdrawn; this page follows those changes.