Z.ai: GLM 5.3 Flash

Available

z-ai/glm-5.3-flashUsage rank #3

GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while...

At a glance

Context window: 1.3Mtokens
Max output: 131Ktokens
Knowledge to: —
Released: 2026

Capabilities

CapabilitiesReasoningVisionToolsStructured output

InputTextImageVideo

OutputText

ReasoningSupportedmaxhighlow

Benchmarks

Intelligence index: 42
Coding index: 72
Agentic index: 51

Design Arena

Category	Elo	Win rate
models · 3d	1,354	59.5
models · uicomponent	1,339	55.8
models · svg	1,313	57.1
models · gamedev	1,312	47.7
models · codecategories	1,299	49.7
models · asciiart	1,287	55.9
models · website	1,285	48.5
models · dataviz	1,276	50.6

Standard evaluations

Benchmark	Score	Tasks
gpqa_diamond	0.86	594
tau_bench_verified_airline	0.75	100

Source: Artificial Analysis, Design Arena · as of Sep 16, 2026

Performance

Uptime on IranRouter

15%

Aug 18Sep 16

Reference uptime

99.9%

Aug 18Sep 16

Median latency

1,898 ms

Aug 18Sep 16

Throughput

32.7 tok/s

Aug 18Sep 16

IranRouter uptime comes from our own automated probes; the reference figures are daily measurements of this model's upstream routes. Each card shows a 30-day average, and a day without data stays empty.

Popularity

Current rank: #3
Rank change, 7 days: 0

Daily tokens · 90 days

1.6T

Jun 18Sep 15

Ranked by daily token volume across the global model market; the figure above the chart is the daily average.

Supported parameters

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p

Parameters this model accepts; anything else is ignored.

Quick start

from openai import OpenAI

client = OpenAI(
    api_key="ir-...",
    base_url="https://iranrouter.com/v1",
)

resp = client.chat.completions.create(
    model="z-ai/glm-5.3-flash",
    messages=[{"role": "user", "content": "سلام!"}],
)
print(resp.choices[0].message.content)

Only base_url and the key change; the rest of your code stays as it is.

Other models by this maker

Z.ai: GLM 5.31.3M Z.ai: GLM 5.21M