Skip to content
AI Atlas
ModelActiveOpen weightsIdentity probable

GLM 5.3 Flash

Z.ai (Zhipu AI)family · GLM5.3huggingface.co/zai-org/GLM-5.3-Flash

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...

Open in Graph
data quality72

Updated 5 h ago · first seen 11 Sept 2026

model_01M294AJ50P57GSKVAN937X1AH

Overview

Identity

Canonical model
Yesidentity confidence: mediumOne row per real model release. Artifacts (checkpoints, quantisations, conversions) and folded evaluation variants point here.
Official checkpoints
official_checkpoints = hf_repo identifiers carried by the model itself; artifacts are separate entities pointing here through canonical_id.
Artifacts
None recordedSeparate entities (checkpoint · quantization · conversion · packaging) pointing to this model through canonical_id.
Provider deployments
4
API aliases
fireworks/glm-5p3-flashglm-5-3-flashz-ai/glm-5.3-flashIdentifiers under which providers and evaluators refer to this model.
Folded evaluation variants
0Effort / thinking variants (…-high, …-non-reasoning) are result configurations of this model, not separate models. Their old URLs redirect here.

Openness

Open weights— weights downloadable under MIT; commercial use allowed; redistribution allowed; derivatives allowed; 4 dimensions unknown.

Weights downloadable under a permissive or Creative Commons licence allowing commercial use; code or data may be missing.

  • Weights

    Yes

  • Inference code

    —

  • Training code

    —

  • Training data

    —

  • Dataset

    —

  • Commercial use

    Yes

  • Redistribution

    Yes

  • Derivatives

    Yes

Licence: MIT License (permissive · SPDX MIT · stated as “mit”)

dimensions marked null are unknown, not false

Key facts

Release date

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 10 h agomedium

Openrouter id

Source:OpenRouter public model & pricing listingT2observed 15 h agomedium

Architecture

Architecture

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 14 h agomedium

Model type

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 14 h agomedium

Parameters

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 15 h agomedium

Weights dtype

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 14 h agomedium

File size

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 14 h agomedium

Library name

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 14 h agomedium

Pipeline tag

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 15 h agomedium

Hugging Face repo

Source:OpenRouter public model & pricing listingT2observed 15 h agomedium

Capabilities

Modalities

Modalities
imagetextvideo
Input
imagetextvideo
Output
text

Capabilities

  • Tool calling

    Yes

    OpenRouter public model & pricing listing · T2

  • Structured output

    Yes

    OpenRouter public model & pricing listing · T2

  • Reasoning

    Yes

    OpenRouter public model & pricing listing · T2

  • Vision

    Yes

    OpenRouter public model & pricing listing · T2

  • Audio

    Unavailable

  • Fine-tuning available

    Unavailable

Context window

Source:OpenRouter public model & pricing listingT2observed 12 h agomedium

Max output

Source:OpenRouter public model & pricing listingT2observed 15 h agomedium

Languages

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 14 h agomedium

Benchmarks20

Compare with another model →

Comparable same task and conditions · Partially comparable same task, conditions differ (effort, temperature, judge) · Not comparable different variant or metric

Benchmark results grouped by comparability group
Benchmark · groupBest scoreTrustConfigurationResultsvs leaderEvaluatedSource
Terminal-Benchagentic · accuracy · variant=v2.1 · evaluator=Artificial AnalysisIndependentevaluatorArtificial Analysisvariantv2.1reasoningonconditions differ across rows → partially comparable2non-primary groupobs. 12 Sept 2026artificialanalysis.aiT2
Terminal-Benchagentic · accuracy · variant=v4.0 · evaluator=Artificial AnalysisIndependentevaluatorArtificial Analysisvariantv4.0reasoningonconditions differ across rows → partially comparable2non-primary groupobs. 12 Sept 2026artificialanalysis.aiT2
LiveBench Agentic Codingcoding · average score · variant=Agentic CodingOfficial boardvariantAgentic Codingrelease2026-06-251−20.5 ptvs DeepSeek-V4.1-Flash25 Jun 2026livebench.aiT2
LiveBench Codingcoding · average score · variant=CodingOfficial boardvariantCodingrelease2026-06-251−7.42 ptvs Claude Fable 5.125 Jun 2026livebench.aiT2
SciCodecoding · accuracy · evaluator=Artificial AnalysisIndependentevaluatorArtificial Analysisreasoningonconditions differ across rows → partially comparable2−11.5 ptvs Claude Fable 5.1obs. 12 Sept 2026artificialanalysis.aiT2
Artificial Analysis Intelligence Indexcomposite · indexIndependentreasoningonversion4.3conditions differ across rows → partially comparable2−11.5vs Claude Fable 5.1obs. 12 Sept 2026artificialanalysis.aiT2
LiveBenchgeneral · global_averageOfficial boardrelease2026-06-251−11.8 ptvs Claude Fable 5.125 Jun 2026livebench.aiT2
LiveBench Data Analysisgeneral · average score · variant=Data AnalysisOfficial boardvariantData Analysisrelease2026-06-251−6.57 ptvs gpt-6-astra25 Jun 2026livebench.aiT2
LiveBench Languagegeneral · average score · variant=LanguageOfficial boardvariantLanguagerelease2026-06-251−13.4 ptvs Claude Fable 525 Jun 2026livebench.aiT2
LiveBench Instruction Followinginstruction-following · average score · variant=IFOfficial boardvariantIFrelease2026-06-251−28.6 ptvs Gemini 3.8 Flash25 Jun 2026livebench.aiT2
Humanity's Last Examknowledge · accuracy · evaluator=Artificial AnalysisIndependentevaluatorArtificial Analysisreasoningonconditions differ across rows → partially comparable2−19.3 ptvs Claude Fable 5.1obs. 12 Sept 2026artificialanalysis.aiT2
LiveBench Mathematicsmath · average score · variant=MathematicsOfficial boardvariantMathematicsrelease2026-06-251−15.8 ptvs Claude Fable 5.125 Jun 2026livebench.aiT2
GPQA Diamondreasoning · accuracy · variant=Diamond · evaluator=Artificial AnalysisIndependentevaluatorArtificial AnalysisvariantDiamondreasoningonconditions differ across rows → partially comparable1non-primary groupobs. 12 Sept 2026artificialanalysis.aiT2
GPQA Diamondreasoning · accuracy · variant=GPQA Diamond · evaluator=Artificial AnalysisIndependentevaluatorArtificial AnalysisvariantGPQA Diamond1−5.05 ptvs gpt-6-astraobs. 11 Sept 2026artificialanalysis.aiT2
LiveBench Reasoningreasoning · average score · variant=ReasoningOfficial boardvariantReasoningrelease2026-06-251−15.0 ptvs gpt-6-astra25 Jun 2026livebench.aiT2

Current rows only, grouped by benchmark → canonical metric → comparability group (task configuration). Effort variants folded into this model appear as rows of the same group. 20 current rows in total. “vs leader” compares with the current leader of the benchmark's primary group only; other groups are not directly comparable. Comparability rules →

Providers & Pricing6

All offers in the price terminal →
Provider deployments, cheapest output first
ProviderContextInput / 1MCached inOutput / 1MBatch in / outStatusObservedSource
OpenRoutercheapest outputz-ai/glm-5.3-flash1.05Mout 131.1K$0.015—active2 h agosince 12 Sept 2026openrouter.aiT2
OpenRouterz-ai/glm-5.3-flash:batch1.05Mout 943.7K$0.015—active2 h agosince 12 Sept 2026openrouter.aiT2
Z.ai APIz-ai/glm-5.3-flash:batch1.05Mout 943.7K$0.015—active6 h agosince 11 Sept 2026openrouter.aiT2
Fireworks AIfireworks/glm-5p3-flash—$0.03—active8 h agosince 11 Sept 2026app.fireworks.aiT1
Together AIglm-5-3-flash—$0.03$0.15 / $0.50active13 h agosince 11 Sept 2026together.aiT1
Z.ai APIz-ai/glm-5.3-flash1.05Mout 131.1K$0.03—active6 h agosince 11 Sept 2026openrouter.aiT2

USD per 1M tokens as published by each provider; native units (per-request fees, flex/priority tiers) are kept verbatim. Rows are append-only — every price change is kept in the history below. Cost of a workload →

Price history

Step lines per provider; amber markers are recorded changes. Click a marker or a row for the evidence behind that price.

Output price · USD / 1M tokens 4 providers

Output price history of GLM 5.3 Flash$0$0.20$0.40$0.60Sept 26Sept 26Sept 26Sept 26Sept 26Fireworks AI: first observed → $0.50 · 11 Sept 2026Z.ai API: first observed → $0.50 · 11 Sept 2026Z.ai API: $0.50 → $0.25 · 11 Sept 2026Together AI: first observed → $0.50 · 11 Sept 2026OpenRouter: first observed → $0.50 · 12 Sept 2026OpenRouter: $0.50 → $0.25 · 12 Sept 2026
  • Fireworks AI
  • Z.ai API
  • Together AI
  • OpenRouter
  • OpenRouter$0.50 → $0.2512 Sept 2026
  • OpenRouterfirst observed $0.5012 Sept 2026
  • Together AIfirst observed $0.5011 Sept 2026
  • Z.ai API$0.50 → $0.2511 Sept 2026
  • Z.ai APIfirst observed $0.5011 Sept 2026
  • Fireworks AIfirst observed $0.5011 Sept 2026

Input price · USD / 1M tokens 4 providers

Input price history of GLM 5.3 Flash$0$0.05$0.10$0.15$0.20Sept 26Sept 26Sept 26Sept 26Sept 26Fireworks AI: first observed → $0.15 · 11 Sept 2026Z.ai API: first observed → $0.15 · 11 Sept 2026Z.ai API: $0.15 → $0.075 · 11 Sept 2026Together AI: first observed → $0.15 · 11 Sept 2026OpenRouter: first observed → $0.15 · 12 Sept 2026OpenRouter: $0.15 → $0.075 · 12 Sept 2026
  • Fireworks AI
  • Z.ai API
  • Together AI
  • OpenRouter
  • OpenRouter$0.15 → $0.07512 Sept 2026
  • OpenRouterfirst observed $0.1512 Sept 2026
  • Together AIfirst observed $0.1511 Sept 2026
  • Z.ai API$0.15 → $0.07511 Sept 2026
  • Z.ai APIfirst observed $0.1511 Sept 2026
  • Fireworks AIfirst observed $0.1511 Sept 2026

Hardware fit37

Estimated

6 of 37 device × quantization combinations fit.

Run locally: your machine →
Estimated hardware fit
HardwareQuantizationDevice memoryEst. memoryFits
Apple M3 Ultra4bit—185.3 GB est.Yes
Mac Studio (Apple M5 Ultra)4bit—185.3 GB est.Yes
Apple M2 Ultra4bit—185.3 GB est.Yes
AMD Instinct MI300X4bit192 GB185.3 GB est.Yes
AMD Instinct MI325X4bit256 GB185.3 GB est.Yes
NVIDIA DGX B2004bit1,440 GB185.3 GB est.Yes
Apple M1 Ultra4bit—185.3 GB est.No
Apple M3 Max4bit—185.3 GB est.No
Apple M4 Max4bit—185.3 GB est.No
Mac Studio (Apple M5 Max)4bit—185.3 GB est.No
MacBook Pro (Apple M5 Max)4bit—185.3 GB est.No
Apple M2 Max4bit—185.3 GB est.No
Apple M1 Max4bit—185.3 GB est.No
Apple M4 Pro4bit—185.3 GB est.No
Mac mini (Apple M5 Pro)4bit—185.3 GB est.No
MacBook Pro (Apple M5 Pro)4bit—185.3 GB est.No
Apple M3 Pro4bit—185.3 GB est.No
Apple M1 Pro4bit—185.3 GB est.No
Apple M2 Pro4bit—185.3 GB est.No
Apple M44bit—185.3 GB est.No
iMac (Apple M4)4bit—185.3 GB est.No
Mac mini (Apple M6)4bit—185.3 GB est.No
MacBook Air (Apple M5)4bit—185.3 GB est.No
MacBook Pro (Apple M5)4bit—185.3 GB est.No
Apple M24bit—185.3 GB est.No
Apple M34bit—185.3 GB est.No
Apple M14bit—185.3 GB est.No
NVIDIA GeForce RTX 30904bit24 GB185.3 GB est.No
NVIDIA GeForce RTX 40904bit24 GB185.3 GB est.No
NVIDIA GeForce RTX 50904bit32 GB185.3 GB est.No
NVIDIA A100 80GB4bit80 GB185.3 GB est.No
NVIDIA H100 SXM4bit80 GB185.3 GB est.No
NVIDIA H100 NVL4bit94 GB185.3 GB est.No
NVIDIA DGX Spark4bit128 GB185.3 GB est.No
NVIDIA H2004bit141 GB185.3 GB est.No
NVIDIA H200 NVL4bit141 GB185.3 GB est.No
NVIDIA B2004bit180 GB185.3 GB est.No
Assumptions (7)
  • Estimated, not measured: weights = parameters × bytes/param × 1.15 runtime overhead (or the observed artifact file size when one is recorded).
  • bytes/param: 4bit = 0.5, 8bit = 1.0, fp16 = 2.0 (uniform quantization, no per-layer exceptions).
  • KV cache: 2 × layers × kv_heads × head_dim × 2 bytes × context × batch when the architecture is known; otherwise 0.5 GB per 8 192 tokens (× batch), independent of architecture (GQA/MLA models need less).
  • A model 'fits' when the estimate is at most the device memory minus 2 GB reserved for the OS and framework.
  • Mixture-of-experts models are estimated on total parameters (all experts must be resident); active parameters are ignored.
  • Device memory uses the largest configuration when several are listed (e.g. Apple silicon tiers).
  • Multi-GPU: device memories are summed; interconnect bandwidth, tensor-parallel replication and pipeline bubbles are not modelled.

Versions & Artifacts0

Version history

Context window2 changes

11 Sept 2026→11 Sept 2026→12 Sept 2026current

Licensefirst observation only

11 Sept 2026current

Max outputfirst observation only

11 Sept 2026current

Opennessfirst observation only

11 Sept 2026current

Parametersfirst observation only

11 Sept 2026current

Each hop is a claim: click a value for its source, tier and observation time. Nothing is overwritten — a new observation closes the previous claim.

Artifacts 0

No artifact (checkpoint, quantisation, conversion or packaging) points to this model yet.

Papers1

Timeline12

Full timeline →
  • Price changedModelGLM 5.3 FlashZ.ai (Zhipu AI)

    OpenRouter changed pricing for GLM 5.3 Flash: $0.15 in / $0.5 out per 1M tokens → $0.075 in / $0.25 out per 1M tokens

    $0.15 in / $0.50 out→$0.075 in / $0.25 outopenrouter
    openrouter.ai
  • Listed by providerModelGLM 5.3 FlashZ.ai (Zhipu AI)

    OpenRouter lists GLM 5.3 Flash at $0.075 in / $0.25 out per 1M tokens

    openrouter
    openrouter.ai
  • Listed by providerModelGLM 5.3 FlashZ.ai (Zhipu AI)

    OpenRouter lists GLM 5.3 Flash at $0.15 in / $0.5 out per 1M tokens

    openrouter
    openrouter.ai
  • Benchmark resultModelGLM 5.3 FlashZ.ai (Zhipu AI)

    GLM 5.3 Flash scores 84.27% on Terminal-Bench

    artificial_analysis
    artificialanalysis.ai
  • Benchmark resultModelGLM 5.3 FlashZ.ai (Zhipu AI)

    GLM 5.3 Flash scores 32.83% on Terminal-Bench

    artificial_analysis
    artificialanalysis.ai
  • Benchmark resultModelGLM 5.3 FlashZ.ai (Zhipu AI)

    GLM 5.3 Flash scores 51.62% on SciCode

    artificial_analysis
    artificialanalysis.ai
  • Benchmark resultModelGLM 5.3 FlashZ.ai (Zhipu AI)

    GLM 5.3 Flash scores 39.85% on Humanity's Last Exam

    artificial_analysis
    artificialanalysis.ai
  • Benchmark resultModelGLM 5.3 FlashZ.ai (Zhipu AI)

    GLM 5.3 Flash scores 91.21% on GPQA Diamond

    artificial_analysis
    artificialanalysis.ai
  • Benchmark resultModelGLM 5.3 FlashZ.ai (Zhipu AI)

    GLM 5.3 Flash scores 41.91 on Artificial Analysis Intelligence Index

    artificial_analysis
    artificialanalysis.ai
  • Context window changedModelGLM 5.3 FlashZ.ai (Zhipu AI)

    GLM 5.3 Flash: context length changed from 1000000 to 1310720

    Context window1M tokens→1.31M tokensopenrouter
    openrouter.ai
  • Release date changedModelGLM 5.3 FlashZ.ai (Zhipu AI)

    GLM 5.3 Flash: release date changed from 2026-08-25 to 2026-08-26

    Release date25 Aug 2026→26 Aug 2026openrouter
    openrouter.ai
  • Release date changedModelGLM 5.3 FlashZ.ai (Zhipu AI)

    GLM 5.3 Flash: release date changed from 2026-08-26 to 2026-08-25

    Release date26 Aug 2026→25 Aug 2026huggingface
    huggingface.co

Change history

Temporal, append-only claims: a new observation closes the previous claim instead of overwriting it. Rewind the record with the as-of picker.
2 claims · 1 propertiesShow all properties

Aa median output tokens per secondmetric.aa_median_output_tokens_per_second2

Claim history for Aa median output tokens per second
ValueValid from → toStatusSourceConfidenceExtractor
97.9 → currentcurrentArtificial AnalysisT2mediumdeterministic
94.9 → supersededArtificial AnalysisT2mediumdeterministic

Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →

Provenance

Attributed facts

46

Source tiers

T246

Freshest observation

5 h ago

Conflicts

None

Source documents 8

Source documents
SourceDocumentTypeTierLast observedSnapshots
Fireworks AI — pricingdocs.fireworks.ai/serverless/pricing.md pricingT1· Official2 h ago2
Together AI — pricingtogether.ai/pricing pricingT1· Official4 h ago1
Hugging Face Hub (public pages, model cards, papers)huggingface.co/zai-org/GLM-5.3-Flash model_pageT2· Quality secondary1 min ago5
Hugging Face Hub (public pages, model cards, papers)huggingface.co/models?author=zai-org&p=0&sort=downloads listingT2· Quality secondary45 min ago8
OpenRouter public model & pricing listingopenrouter.ai/api/v1/models catalogueT2· Quality secondary2 h ago11
Artificial Analysisartificialanalysis.ai/leaderboards/models leaderboardT2· Quality secondary5 h ago2
Hugging Face Hub (public pages, model cards, papers)huggingface.co/zai-org/GLM-5.3-Flash/raw/main/README.md model_cardT2· Quality secondary8 h ago1
LiveBenchlivebench.ai/table_2026_06_25.csv leaderboardT2· Quality secondary13 h ago1

Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.

Data quality (72/100) measures how well AI Atlas knows this entity — completeness, primary-source ratio, freshness, conflicts — never how good the model is. Methodology →