Skip to content
Model Season every model has a season

GLM 5.3 Flash

z-ai/glm-5.3-flash-20260826
Z.ai (GLM)ChinaOpen weights

The 4th most-used model on the router over the last 7 days, with 10.0% of tokens. Weekly share peaked at 10.7% in the week of Aug 31, 2026, with 19T tokens processed since Aug 24, 2026.

Launch
Aug 26, 2026
Context
1.31M tokens
Modality
text, image and video → text
Reasoning
yes
License
Open weights
Input
$0.15 / 1M
Output
$0.50 / 1M
Share, last 7 days
10.0%
4th of 61 · Sep 4, 2026 to Sep 10, 2026
Peak weekly share
10.7%
week of Aug 31, 2026
Cumulative tokens
19T
since the week of Aug 24, 2026
Weeks in the top 10
2
of 2 weeks with volume

Weekly token share

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

0%5%10%15%Aug 24Aug 31peak 10.7% on Aug 31, 2026
See the numbers
WeekShare
Aug 31, 202610.734%
Aug 24, 20265.450%

Debuted in the week of Aug 24, 2026 and peaked at 10.7% 1 week later. The latest full week is the peak so far.

What this model is used for new

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

Plus 14 more tasks with a smaller share.

Ranks among the leaders in 26 of the 29 classified tasks. Its largest share is in code review, 18.0% of the task's tokens; in the heaviest task where it appears, workflow execution (24.6% of classified volume), it holds 11.3%.

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$0.075$0.251Mfp4yes
Relace$0.09$0.301Mfp4yes
Morph$0.10$0.351Mfp8yes
Wafer$0.10$0.351Mnot reportedyes
StreamLake$0.112$0.3741.02Mfp8no
GMICloud$0.112$0.3751Mfp8no
Novita$0.132$0.441Mfp8yes
Makora$0.14$0.471Mnot reportedyes
Crusoe$0.15$0.501Mfp4yes
CoreWeave$0.15$0.501Mfp8yes
Sail Research$0.15$0.501Mfp8yes
NextBit$0.15$0.501Mfp8yes
Fireworks$0.15$0.501Mnot reportedyes
Phala$0.15$0.501Mfp8yes
Friendli$0.15$0.501Mnot reportedno
SiliconFlow$0.15$0.501Mfp8yes
DigitalOcean$0.15$0.501Mnot reportedyes
Together$0.15$0.501Mnot reportedyes
Reka$0.15$0.50256kfp8yes
Parasail$0.15$0.501Mfp8yes
BaseTen$0.15$0.501Mfp8yes
Venice$0.15$0.501Mnot reportedyes
Cloudflare$0.15$0.501.31Mnot reportedno
Z.AI$0.15$0.501Mfp8yes
Modal$0.45$1.501Mfp8yes

25 endpoints across 25 providers, with input from $0.075 to $0.45 per 1M tokens. 21 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
41.9
11th of 82
Coding
71.5
19th of 111
Agents
51.2
6th of 86

GPQA Diamond 86.7%

$0.007 per task, 396 tasks. 26th of 131 evaluated. Median of evaluated models: 80.2%, $0.024 per task.

τ-bench verified, airline 73.3%

$0.0048 per task, 50 tasks. 42nd 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 Flashthis pageZ.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

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.