ModelBench
Zhipu AI logo
Models/Zhipu AI

Zhipu AI: GLM-5.3-Flash

Native multimodal GLM model for efficient coding and long-horizon agent tasks

Source-linked glm-flash Open weights Released 2026-08-26
API record Report
InputT
OutputT
Input price$0.12/M
Output price$0.418/M
Context1M
Max output131.072K
Providers63
Inference availability

Providers

Provider-specific identifiers, limits, and listed prices per million tokens. Every row links back to the provider's own documentation.

Report a price
Providers offering GLM-5.3-Flash
ProviderProvider model IDContextMax outputInputOutputCache readCapabilitiesDocs
Zhipu AI Coding Plan glm-5.3-flash 1M 131.072K — — — ReasoningToolsJSON Docs ↗
Z.AI Coding Plan glm-5.3-flash 1M 131.072K — — — ReasoningToolsJSON Docs ↗
NaN glm5.3-flash 1M 131.072K — — — ReasoningToolsJSON Docs ↗
SCNet Token Plan GLM-5.3-Flash 1M 131.072K — — — ReasoningToolsJSON Docs ↗
Volcengine Ark Coding Plan glm-5.3-flash 1M 131.072K — — — ReasoningToolsJSON Docs ↗
Nvidia z-ai/glm-5.3-flash 1M 131.072K — — — ReasoningToolsJSON Docs ↗
AMD GLM-5.3-Flash 262.144K 131.072K — — — ReasoningToolsJSON Docs ↗
Pareto Inference z-ai/glm-5.3-flash 1M 131.072K $0.06 $0.2 $0.012 ReasoningToolsJSON Docs ↗
302.AI glm-5.3-flash 1M 131.072K $0.075 $0.25 $0.015 ReasoningToolsJSON Docs ↗
IteraCompute z-ai/glm-5.3-flash 1.04858M 131.072K $0.08 $0.28 $0.023 ReasoningTools Docs ↗
NEAR AI Cloud z-ai/glm-5.3-flash 1M 131.072K $0.08 $0.5 $0.012 ReasoningToolsJSON Docs ↗
Standard Compute z-ai/glm-5.3-flash 1M 50K $0.08 $0.5 $0.012 ReasoningToolsJSON Docs ↗
DevPass (LLM Gateway) glm-5.3-flash 1.04858M 131.072K $0.088 $0.25 $0.025 ReasoningToolsJSON Docs ↗
Cortecs glm-5.3-flash 1.04858M 1.04858M $0.1 $0.35 $0.018 ReasoningToolsJSON Docs ↗
Vultr glm-5.3-flash 1.04858M 131.072K $0.1 $0.35 — ReasoningToolsJSON Docs ↗
RunInfra zai-org/GLM-5.3-Flash 1.04858M 32.768K $0.11 $0.45 $0.03 ReasoningToolsJSON Docs ↗
AIHubMix glm-5.3-flash 1M 131.072K $0.113 $0.394 $0.028 ReasoningToolsJSON Docs ↗
Kenari glm-5-3-flash 1M 131.072K $0.114 $0.343 $0.023 ReasoningToolsJSON Docs ↗
Melious glm-5.3-flash 1M 131.072K $0.116 $0.464 $0.023 ReasoningToolsJSON Docs ↗
Volcengine Ark glm-5-3-flash-260828 1M 131.072K $0.119 $0.416 $0.034 ReasoningToolsJSON Docs ↗
Zhipu AI glm-5.3-flash 1M 131.072K $0.12 $0.418 $0.034 ReasoningToolsJSON Docs ↗
Vancine glm-5.3-flash 1M 131.072K $0.12 $0.4 $0.024 ReasoningToolsJSON Docs ↗
Boundless glm-5.3-flash 1.04858M 131.072K $0.12 $0.4 $0.024 ReasoningToolsJSON Docs ↗
GreenPT glm-5.3-flash 1M 131.072K $0.128 $0.511 $0.026 ReasoningToolsJSON Docs ↗
engy glm-5.3-flash 327.68K 32.768K $0.135 $0.45 $0.027 ReasoningToolsJSON Docs ↗
TokenGo z-ai/glm-5.3-flash 1M 131.072K $0.15 $0.5 $0.03 ReasoningToolsJSON Docs ↗
OrcaRouter z-ai/glm-5.3-flash 1M 128K $0.15 $0.5 $0.03 ReasoningToolsJSON Docs ↗
Synthetic hf:zai-org/GLM-5.3-Flash 524.288K 65.536K $0.15 $0.5 $0.04 ReasoningToolsJSON Docs ↗
Deep Infra zai-org/GLM-5.3-Flash 1.04858M 131.072K $0.15 $0.5 $0.03 ReasoningToolsJSON Docs ↗
Hugging Face zai-org/GLM-5.3-Flash 1.04858M 131.072K $0.15 $0.5 — ReasoningToolsJSON Docs ↗
OpenRouter z-ai/glm-5.3-flash 1.04858M 943.717K $0.15 $0.5 $0.03 ReasoningToolsJSON Docs ↗
CrossModel z-ai/glm-5.3-flash 1M 128K $0.15 $0.5 $0.03 ReasoningToolsJSON Docs ↗
Z.AI glm-5.3-flash 1M 131.072K $0.15 $0.5 $0.03 ReasoningToolsJSON Docs ↗
Vivgrid glm-5.3-flash 1M 131.072K $0.15 $0.5 $0.04 ReasoningToolsJSON Docs ↗
Ollama Cloud glm-5.3-flash 1M 131.072K $0.15 $0.5 $0.03 ReasoningTools Docs ↗
Together AI zai-org/GLM-5.3-Flash 1.04858M 400K $0.15 $0.5 $0.03 ReasoningToolsJSON Docs ↗
Ofox z-ai/glm-5.3-flash 1M 131.072K $0.15 $0.5 $0.03 ReasoningToolsJSON Docs ↗
Eden AI zai/glm-5.3-flash 1.04858M 131.072K $0.15 $0.5 $0.03 ReasoningToolsJSON Docs ↗
Kilo Gateway z-ai/glm-5.3-flash 1.04858M 943.717K $0.15 $0.5 $0.03 ReasoningToolsJSON Docs ↗
Nebius Token Factory zai-org/GLM-5.3-Flash 1.024M 1.024M $0.15 $0.5 $0.03 ReasoningToolsJSON Docs ↗
OpenCode glm-5.3-flash 1M 131.072K $0.15 $0.5 $0.03 ReasoningToolsJSON Docs ↗
OpenCode Go glm-5.3-flash 1M 131.072K $0.15 $0.5 $0.03 ReasoningToolsJSON Docs ↗
Friendli zai-org/GLM-5.3-Flash 1.04858M 131.072K $0.15 $0.5 $0.03 ReasoningToolsJSON Docs ↗
SiliconFlow zai-org/GLM-5.3-Flash 1.049M 262K $0.15 $0.5 $0.03 ReasoningToolsJSON Docs ↗
Tempr Gateway zai/glm-5.3-flash 1M 131.072K $0.15 $0.5 $0.03 ReasoningToolsJSON Docs ↗
ai& zai-org/glm-5.3-flash 1.04855M 131.072K $0.15 $0.5 $0.03 ReasoningToolsJSON Docs ↗
Novita AI zai-org/glm-5.3-flash 1.04858M 131.072K $0.15 $0.5 $0.03 ReasoningToolsJSON Docs ↗
Prime Inference z-ai/glm-5.3-flash 1.04858M 943.718K $0.15 $0.5 — ReasoningToolsJSON Docs ↗
CommandCode z-ai/glm-5.3-flash 1M 131.072K $0.15 $0.5 $0.03 ReasoningToolsJSON Docs ↗
Perplexity Agent perplexity/glm-5.3-flash 1M 131.072K $0.15 $0.5 $0.03 ReasoningToolsJSON Docs ↗
Arcee zai-org/glm-5.3-flash 1M 131.072K $0.15 $0.5 $0.03 ReasoningToolsJSON Docs ↗
Modal nvidia/GLM-5.3-Flash-NVFP4 1M 131.072K $0.15 $0.5 $0.03 ReasoningToolsJSON Docs ↗
Mistral zai-glm-5-3-flash 1.04858M 131.072K $0.15 $0.5 $0.03 ReasoningToolsJSON Docs ↗
Bothub glm-5.3-flash 1M 131.072K $0.157 $0.522 — ReasoningToolsJSON Docs ↗
Charm Hyper glm-5.3-flash 1.04858M 131.072K $0.163 $0.544 $0.032 ReasoningToolsJSON Docs ↗
Requesty glm-5.3-flash 1M 262.144K $0.2 $0.6 $0.07 ReasoningToolsJSON Docs ↗
TensorX z-ai/glm-5.3-flash 1.04858M 64K $0.2 $0.5 $0.05 ReasoningToolsJSON Docs ↗
Opper glm-5.3-flash 1M 128K $0.2 $0.5 $0.07 ReasoningTools Docs ↗
Privatemode AI glm-5.3-flash 1M 131.072K $0.231 $0.751 $0.058 ReasoningToolsJSON Docs ↗
Berget.AI zai-org/GLM-5.3-Flash 1.04858M 16.384K $0.29 $0.58 — ReasoningToolsJSON Docs ↗
Inco glm-5.3-flash:fast 1M 131.072K $0.3 $1 $0.06 ReasoningToolsJSON Docs ↗
Tinfoil glm-5-3-flash 1.04858M 131.072K $0.4 $1.25 $0.1 ReasoningToolsJSON Docs ↗
Thinking Machines zai-org/GLM-5.3-Flash:peft:262144 262.144K 262.144K $0.84 $2.11 $0.168 ReasoningTools Docs ↗

Capability badges appear only where the provider catalog explicitly lists support. A blank cell means the source is silent, not that the feature is absent.

Listed rates

Price across providers

Input price per million tokens as published by each provider. Bars are drawn from listed rates only — no traffic weighting, since the catalog observes no requests.

Lowest input $0.06/M

Across 56 priced providers

Median input $0.15/M

Midpoint of listed rates

Highest input $0.84/M

14.0× the lowest listed rate

Output range $0.2 – $2.11

Per million output tokens

Pareto Inference $0.06/MLowest
302.AI $0.075/M
IteraCompute $0.08/M
NEAR AI Cloud $0.08/M
Standard Compute $0.08/M
DevPass (LLM Gateway) $0.088/M
Cortecs $0.1/M
Vultr $0.1/M
RunInfra $0.11/M
AIHubMix $0.113/M
Kenari $0.114/M
Melious $0.116/M
Volcengine Ark $0.119/M
Zhipu AI $0.12/M
Vancine $0.12/M
Boundless $0.12/M
GreenPT $0.128/M
engy $0.135/M
TokenGo $0.15/M
OrcaRouter $0.15/M
Synthetic $0.15/M
Deep Infra $0.15/M
Hugging Face $0.15/M
OpenRouter $0.15/M
CrossModel $0.15/M
Z.AI $0.15/M
Vivgrid $0.15/M
Ollama Cloud $0.15/M
Together AI $0.15/M
Ofox $0.15/M
Eden AI $0.15/M
Kilo Gateway $0.15/M
Nebius Token Factory $0.15/M
OpenCode $0.15/M
OpenCode Go $0.15/M
Friendli $0.15/M
SiliconFlow $0.15/M
Tempr Gateway $0.15/M
ai& $0.15/M
Novita AI $0.15/M
Prime Inference $0.15/M
CommandCode $0.15/M
Perplexity Agent $0.15/M
Arcee $0.15/M
Modal $0.15/M
Mistral $0.15/M
Bothub $0.157/M
Charm Hyper $0.163/M
Requesty $0.2/M
TensorX $0.2/M
Opper $0.2/M
Privatemode AI $0.231/M
Berget.AI $0.29/M
Inco $0.3/M
Tinfoil $0.4/M
Thinking Machines $0.84/M
Cost calculator

Estimate a workload

$0.00
Excludes taxes, non-token charges, and tiered discounts.

Context limits also differ by provider, from 262.144K to 1.049M tokens. Compare the provider table above before choosing on price alone.

Specification

Capabilities

Recorded from the source catalog and provider listings.

✓ Reasoning Yes
✓ Tool calling Yes
× Structured output No
✓ Attachments Yes
✓ Vision input Yes
✓ Open weights Yes
Creator
Zhipu AI
Model family
glm-flash
Knowledge cutoff
Not documented
License
Not documented
Release date
2026-08-26
Model ID
zhipuai/glm-5.3-flash

Weights: Hugging Face ↗

Published evaluations

Benchmarks

Every result stays attached to its source, version, metric and harness. Scores from different versions are never merged, and the profile below plots each benchmark against its own population rather than on a shared scale.

Benchmark registry
Benchmark profile
Humanity's Last…Humanity's Last Exam Agents' Last Ex…Agents' Last Exam GDPval-AAGDPval-AA 2 This model — Humanity's Last Exam: 55.3 accuracy (63.0th percentile) This model — Agents' Last Exam: 26.3 score (17.9th percentile) This model — GDPval-AA 2: 1773 Elo (75.0th percentile)

Each axis is this model's percentile among the 3 benchmarks it has published results for, measured against every other model with a score on that same benchmark. Percentiles are used because benchmarks do not share a scale — a 60 on one is not a 60 on another. Hover any point for the raw score.

Humanity's Last Exam accuracy Source ↗
Humanity's Last Exam #9 of 23
Agents' Last Exam score Source ↗
Agents' Last Exam #12 of 14
GDPval-AA — 2 Elo Source ↗
GDPval-AA #2 of 6
DeepSWE — 1.1 resolved · mini-swe-agent Source ↗
DeepSWE #3 of 3
AutomationBench — 1.0.6 pass@1 Source ↗
48.8 2 models scored — too few for a distribution
Terminal-Bench — 2.1 pass@1 · Claude Code 2.1.207 Source ↗
84.3 2 models scored — too few for a distribution

Each strip shows every published score for that benchmark, with this model marked. The lighter shape behind the ticks is the density of results, and the dashed line is the median.

Cost against capability

Price and performance

Listed input price plotted against Humanity's Last Exam, the benchmark with the widest published coverage that this model appears in.

0 34 69 $0.1 $1 $10 Qwen3.7 Max — $2.5/M, score 41.4 Qwen3.8 Max Preview — $0.338/M, score 43.6 Claude Fable 5 — $10/M, score 64.5 Claude Opus 4.7 — $5/M, score 54.7 Claude Opus 4.8 — $5/M, score 57.9 Claude Opus 5 — $5/M, score 64.7 Claude Sonnet 4.6 — $3/M, score 46.8 Gemini 3.1 Pro Preview — $2/M, score 44.4 Gemini 3.5 Flash — $1.5/M, score 40.2 Muse Spark 1.1 — $1.25/M, score 62.1 Nemotron 3 Ultra 550B A55B — $0.1/M, score 37.4 Nemotron 3.5 Lightning 30B A3B — $0.025/M, score 11.72 GPT-5.4 — $2.5/M, score 52.1 GPT-5.4 mini — $0.75/M, score 28.2 GPT-5.4 nano — $0.2/M, score 24.3 GPT-5.4 Pro — $30/M, score 58.7 GPT-5.5 — $5/M, score 52.2 GPT-5.5 Pro — $30/M, score 57.2 GPT-6 Astra — $10/M, score 57.2 Step 3.7 Flash — $0.202/M, score 47.2 GLM-5.2 — $1.195/M, score 54.7 GLM-5.3 — $1.195/M, score 62.5 GLM-5.3-Flash — $0.12/M, score 55.3 GLM-5.3-Flash Input price per million tokens (log scale) Accuracy

The stepped line is the efficient frontier: at each price, the best score available for that money or less. A model sitting on it is not being beaten by anything cheaper. Price is log-scaled because listed rates span four orders of magnitude. Only models with both a listed price and a score on this benchmark can appear.

Catalog activity

Change log

Field-level changes detected between successful source imports.

Full change log
Price Completion0.5 → 0.41831
Price Prompt0.15 → 0.11952
Price Completion0.25 → 0.5
Price Prompt0.075 → 0.15
Provenance

Sources & verification

Every figure on this page traces back to one of these records.

Methodology
Last verified
Oct 24, 2026
Status
Source-linked
Confidence
Medium
Catalog source
Models.dev
Models.devcatalog ↗Zhipu AI Coding Plan documentationprovider documentation ↗Z.AI Coding Plan documentationprovider documentation ↗NaN documentationprovider documentation ↗SCNet Token Plan documentationprovider documentation ↗Volcengine Ark Coding Plan documentationprovider documentation ↗Nvidia documentationprovider documentation ↗AMD documentationprovider documentation ↗Pareto Inference documentationprovider documentation ↗302.AI documentationprovider documentation ↗IteraCompute documentationprovider documentation ↗NEAR AI Cloud documentationprovider documentation ↗
Public API

Use this record

Fetch the complete source-linked model record. No key, no account, no rate-limited tier.

API documentation
Endpoint
GET https://modelbench.lol/api/v1/models/zhipuai/glm-5.3-flash
curl
curl "https://modelbench.lol/api/v1/models/zhipuai/glm-5.3-flash"
Common questions

Frequently asked questions

Answered directly from the stored record — nothing here is generated beyond the catalog's own fields.

What is GLM-5.3-Flash?

Native multimodal GLM model for efficient coding and long-horizon agent tasks. It is published by Zhipu AI and catalogued here from Models.dev.

How much does GLM-5.3-Flash cost?

Listed input pricing starts at $0.06 per million tokens from Pareto Inference, rising to $0.84 across 56 listed providers.

What is the context length of GLM-5.3-Flash?

GLM-5.3-Flash accepts up to 1M tokens of context and returns up to 131.072K output tokens.

Does GLM-5.3-Flash support tool calling and structured output?

Provider catalogs list support for tool calling, reasoning, and image input.

Which providers serve GLM-5.3-Flash?

63 providers list this model: Zhipu AI Coding Plan, Z.AI Coding Plan, NaN, SCNet Token Plan, Volcengine Ark Coding Plan, Nvidia and 57 more.

Are the weights for GLM-5.3-Flash open?

Yes. The weights are published and downloadable from Hugging Face.

When was GLM-5.3-Flash released?

The catalog records a release date of 2026-08-26, last verified Oct 24, 2026.

More models from Zhipu AI

View all →
GLM-4.7

Mature GLM model for dependable coding, reasoning, and structured agent tasks

204.8K ctx $0.448/M in GLM-4.5V

GLM vision model for visual reasoning, documents, and multimodal agents

64K ctx $0.299/M in GLM-4.5

Hybrid-reasoning GLM release that made the 4.5 line broadly useful

131.072K ctx $0.6/M in GLM-4.7-FlashX

Efficient GLM model for fast reasoning, coding, and agent workflows

200K ctx $0.075/M in