Skip to content
Model Season every model has a seasonRadar

Qwen3 8B

qwen/qwen3-8b-04-28
QwenChinaOpen weights

No volume over the last 7 days. Weekly share peaked at 0.11% in the week of Jul 28, 2025, with 0T tokens processed since Jul 28, 2025.

Launch
Apr 28, 2025
Context
128k tokens
Modality
text → text
Reasoning
yes
License
Open weights
Input
$0.117 / 1M
Output
$0.455 / 1M
Share, last 7 days
—
no volume over the last 7 days
Peak weekly share
0.11%
week of Jul 28, 2025
Cumulative tokens
0T
since the week of Jul 28, 2025
Weeks in the top 10
0
of 1 week with volume

Weekly token share

Share of the router's weekly volume, since the first week with volume

0.0%0.1%0.1%0.1%Sep '25NovJan '26MarMayJulSeppeak 0.11% on Jul 28, 2025
See the numbers
WeekShare
Sep 14, 20260.000%
Sep 7, 20260.000%
Aug 31, 20260.000%
Aug 24, 20260.000%
Aug 17, 20260.000%
Aug 10, 20260.000%
Aug 3, 20260.000%
Jul 27, 20260.000%
Jul 20, 20260.000%
Jul 13, 20260.000%
Jul 6, 20260.000%
Jun 29, 20260.000%
Jun 22, 20260.000%
Jun 15, 20260.000%
Jun 8, 20260.000%
Jun 1, 20260.000%
May 25, 20260.000%
May 18, 20260.000%
May 11, 20260.000%
May 4, 20260.000%
Apr 27, 20260.000%
Apr 20, 20260.000%
Apr 13, 20260.000%
Apr 6, 20260.000%
Mar 30, 20260.000%
Mar 23, 20260.000%
Mar 16, 20260.000%
Mar 9, 20260.000%
Mar 2, 20260.000%
Feb 23, 20260.000%
Feb 16, 20260.000%
Feb 9, 20260.000%
Feb 2, 20260.000%
Jan 26, 20260.000%
Jan 19, 20260.000%
Jan 12, 20260.000%
Jan 5, 20260.000%
Dec 29, 20250.000%
Dec 22, 20250.000%
Dec 15, 20250.000%
Dec 8, 20250.000%
Dec 1, 20250.000%
Nov 24, 20250.000%
Nov 17, 20250.000%
Nov 10, 20250.000%
Nov 3, 20250.000%
Oct 27, 20250.000%
Oct 20, 20250.000%
Oct 13, 20250.000%
Oct 6, 20250.000%
Sep 29, 20250.000%
Sep 22, 20250.000%
Sep 15, 20250.000%
Sep 8, 20250.000%
Sep 1, 20250.000%
Aug 25, 20250.000%
Aug 18, 20250.000%
Aug 11, 20250.000%
Aug 4, 20250.000%
Jul 28, 20250.111%

Debuted in the week of Jul 28, 2025 and peaked at 0.11% in its first week. No volume was recorded in the latest full week.

What this model is used for new

Tasks where the model ranks among the leaders, and its share of each

This model is not among the leaders in any of the 29 tasks classified in the Sep 25, 2026 snapshot. That does not mean it goes unused: the source lists only the largest models in each task.

Snapshot of the rolling 7-day window through Sep 25, 2026. Share: the model's tokens in the task over the task's total tokens. Weight: the task's share of classified volume.

Where to run it

Endpoints in the source's catalog, from cheapest to most expensive on input

No endpoints listed for this model in the archived catalog.

Benchmarks

Artificial Analysis indexes and benchmarks run by the source, with cost per task

Intelligence
no index
not published
Coding
9.0
109th of 113
Agents
0.8
79th of 86

The source has not run its own benchmarks on this model.

Artificial Analysis indexes, exposed by the catalog; benchmarks run by the source and archived on Sep 26, 2026. The gray mark is the median of evaluated models.

Against the week's largest models

The five largest proprietary and five largest open-weights models over the last 7 days

ModelLab7-day shareBlended priceContextIntelligenceWeeks in top 10
Proprietary
GPT-5.6 LunaOpenAIOpenAI6.1%$0.451M37.38
jev-1.13TypesafeTypesafe1.6%———0
Gemini 3.8 FlashGoogleGoogle1.6%$1.501M40.91
Muse Spark 1.3 ContributorMetaMeta1.3%$0.1251M—0
GPT-6 LunaOpenAIOpenAI1.2%$0.201M37.30
Open weights
DeepSeek V4.1 FlashDeepSeekDeepSeek13.7%$0.5251M39.52
GLM 5.3 FlashZ.ai (GLM)Z.ai (GLM)13.7%$0.1551.31M41.84
Hy4 previewTencentTencent7.9%$1.251M—3
DeepSeek V4 Flash 0731DeepSeekDeepSeek6.1%$0.0961.31M34.37
Nemotron 3 UltraNVIDIANVIDIA3.7%$1.05256k22.911
Qwen3 8Bthis pageQwenQwen—$0.202128k—0

Share over the last 7 days (Sep 19, 2026 to Sep 25, 2026). Blended price in US dollars per million tokens, weighted 75% input and 25% output. A dash means the number is not published, not zero.

What this page doesn't say. Share here is a slice of one router's traffic, where the deciding factor is usually price per token. It is not market, revenue or user share, and it does not tell you which model fits your workload.