Skip to content
Model Season every model has a season

Gemma 4 31B

google/gemma-4-31b-it-20260402
GoogleUS/CanadaOpen weights

The 41st most-used model on the router over the last 7 days, with 0.29% of tokens. Weekly share peaked at 0.94% in the week of May 25, 2026, with 6.0T tokens processed since Apr 13, 2026.

Launch
Apr 2, 2026
Context
256k tokens
Modality
text, image and video → text
Reasoning
yes
License
Open weights
Input
$0.09 / 1M
Output
$0.34 / 1M
Share, last 7 days
0.29%
41st of 61 · Sep 4, 2026 to Sep 10, 2026
Peak weekly share
0.94%
week of May 25, 2026
Cumulative tokens
6.0T
since the week of Apr 13, 2026
Weeks in the top 10
0
of 21 weeks with volume

Weekly token share

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

0.0%0.2%0.4%0.6%0.8%1.0%1.2%May '26JunJulAugpeak 0.94% on May 25, 2026
See the numbers
WeekShare
Aug 31, 20260.302%
Aug 24, 20260.291%
Aug 17, 20260.415%
Aug 10, 20260.631%
Aug 3, 20260.600%
Jul 27, 20260.729%
Jul 20, 20260.638%
Jul 13, 20260.531%
Jul 6, 20260.610%
Jun 29, 20260.763%
Jun 22, 20260.457%
Jun 15, 20260.393%
Jun 8, 20260.512%
Jun 1, 20260.717%
May 25, 20260.945%
May 18, 20260.799%
May 11, 20260.942%
May 4, 20260.748%
Apr 27, 20260.718%
Apr 20, 20260.563%
Apr 13, 20260.268%

Debuted in the week of Apr 13, 2026 and peaked at 0.94% 6 weeks later. The latest full week came in at 0.30%, 32% of peak.

What this model is used for new

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

Ranks among the leaders in 2 of the 29 classified tasks. Its largest share is in roleplay and fiction, 2.7% of the task's tokens.

Snapshot of the rolling 7-day window through Sep 10, 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

ProviderInputOutputContextQuantizationZero retention
DeepInfra$0.09$0.34256kfp4yes
CoreWeave$0.10$0.34256kfp4yes
Venice$0.12$0.36250kbf16yes
Chutes$0.12$0.37128kfp4no
DeepInfra$0.13$0.38256kfp8yes
Crusoe$0.14$0.40256knot reportedyes
Friendli$0.14$0.40256knot reportedno
Novita$0.14$0.40256kbf16yes
Parasail$0.15$0.40256kfp8yes
DeepInfra$0.27$0.76128kfp8yes
SambaNova$0.38$1.15128knot reportedyes
Together$0.39$0.97256knot reportedyes
ModelRun$0.75$1.00256kfp4yes
SiliconFlow$0.75$1.00256kfp8yes

14 endpoints across 12 providers, with input from $0.09 to $0.75 per 1M tokens. 12 offer zero data retention.

Prices in US dollars per million tokens, from the latest archived endpoint catalog.

Benchmarks

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

Intelligence
15.4
57th of 82
Coding
43.4
65th of 111
Agents
6.7
60th of 86

GPQA Diamond 83.5%

$0.0038 per task, 3681 tasks. 49th of 131 evaluated. Median of evaluated models: 80.2%, $0.024 per task.

τ-bench verified, airline 76.1%

$0.016 per task, 996 tasks. 21st of 122 evaluated. Median of evaluated models: 70.7%, $0.056 per task.

Artificial Analysis indexes, exposed by the catalog; benchmarks run by the source and archived on Sep 11, 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 LunaOpenAIOpenAI11.5%$0.451M37.56
Gemini 3.8 FlashGoogleGoogle2.1%$1.501M41.20
Muse Spark 1.3 ContributorMetaMeta1.5%$0.1251M0
Claude Opus 5AnthropicAnthropic1.4%$10.001M50.71
GPT-5.6 SolOpenAIOpenAI1.4%$4.001M47.10
Open weights
Hy4 previewTencentTencent15.5%$1.251M1
DeepSeek V4 Flash 0731DeepSeekDeepSeek10.0%$0.0941.31M34.55
GLM 5.3 FlashZ.ai (GLM)Z.ai (GLM)10.0%$0.2371.31M41.92
MiMo-V2.5XiaomiXiaomi4.2%$0.1751M22.315
DeepSeek V4 Flash 0423DeepSeekDeepSeek3.9%$0.1111M24.819
Gemma 4 31Bthis pageGoogleGoogle0.29%$0.152256k15.40

Share over the last 7 days (Sep 4, 2026 to Sep 10, 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.