GLM-5.3 - API Pricing, Context & Benchmarks

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
Provider	Provider model ID	Context	Max output	Input	Output	Cache read	Capabilities	Docs
Zhipu AI Coding Plan	`glm-5.3`	1M	131.072K	—	—	—	ReasoningToolsJSON	Docs ↗
Z.AI Coding Plan	`glm-5.3`	1M	131.072K	—	—	—	ReasoningToolsJSON	Docs ↗
Volcengine Ark Coding Plan	`glm-5.3`	1M	131.072K	—	—	—	ReasoningToolsJSON	Docs ↗
SCNet Token Plan	`GLM-5.3`	1M	131.072K	—	—	—	ReasoningToolsJSON	Docs ↗
NaN	`glm5.3`	1M	131.072K	—	—	—	ReasoningToolsJSON	Docs ↗
AgentRouter	`glm-5.3`	1M	131.072K	—	—	—	ReasoningToolsJSON	Docs ↗
Nvidia	`z-ai/glm-5.3`	1M	131.072K	—	—	—	ReasoningToolsJSON	Docs ↗
Alibaba Token Plan	`glm-5.3`	1M	131.072K	—	—	—	ReasoningToolsJSON	Docs ↗
Alibaba Token Plan (China)	`glm-5.3`	1M	131.072K	—	—	—	ReasoningToolsJSON	Docs ↗
OpenRouter	`z-ai/glm-5.3`	1.04858M	943.718K	$0.079	$1.4	$0.078	ReasoningToolsJSON	Docs ↗
Kenari	`glm-5-3`	1M	131.072K	$0.286	$3.429	$0.053	ReasoningToolsJSON	Docs ↗
CloudFerro Sherlock	`zai-org/GLM-5.3`	262.144K	131.072K	$0.34	$4.48	—	ReasoningToolsJSON	Docs ↗
CrofAI	`glm-5.3`	1M	131.072K	$0.4	$1.4	$0.06	ReasoningToolsJSON	Docs ↗
DevPass (LLM Gateway)	`glm-5.3`	1.04858M	131.072K	$0.45	$1.8	$0.135	ReasoningToolsJSON	Docs ↗
Cortecs	`glm-5.3`	1.04858M	1.04858M	$0.511	$2.045	$0.154	ReasoningToolsJSON	Docs ↗
Merge Gateway	`zai/glm-5.3`	1M	131.072K	$0.7	$2.2	$0.13	ReasoningToolsJSON	Docs ↗
Vultr	`glm-5.3`	1.04858M	131.072K	$0.75	$3	—	ReasoningToolsJSON	Docs ↗
IteraCompute	`z-ai/glm-5.3`	1.04858M	131.072K	$0.82	$2.88	$0.2	ReasoningTools	Docs ↗
Deep Infra	`zai-org/GLM-5.3`	1.04858M	131.072K	$0.9	$4	$0.2	ReasoningToolsJSON	Docs ↗
engy	`glm-5.3`	327.68K	32.768K	$0.98	$3.08	$0.18	ReasoningToolsJSON	Docs ↗
ai&	`zai-org/glm-5.3`	1.04858M	131.072K	$1	$4	$0.3	ReasoningToolsJSON	Docs ↗
Alibaba (China)	`glm-5.3`	1M	131.072K	$1.1	$3.851	$0.275	ReasoningToolsJSON	Docs ↗
Vancine	`glm-5.3`	1M	131.072K	$1.12	$3.52	$0.208	ReasoningToolsJSON	Docs ↗
CoralBricks	`glm-5.3-fast`	1.04858M	131.072K	$1.12	$4.4	—	ReasoningToolsJSON	Docs ↗
Boundless	`glm-5.3`	1.04858M	131.072K	$1.12	$3.52	$0.14	ReasoningToolsJSON	Docs ↗
AKI.IO	`glm5.3-754b`	524.288K	81.92K	$1.121	$3.925	$0.28	ReasoningToolsJSON	Docs ↗
AIHubMix	`glm-5.3`	1M	131.072K	$1.127	$3.944	$0.282	ReasoningToolsJSON	Docs ↗
Melious	`glm-5.3`	1M	131.072K	$1.159	$3.478	$0.232	ReasoningToolsJSON	Docs ↗
Zhipu AI	`glm-5.3`	1M	131.072K	$1.195	$4.183	$0.299	ReasoningToolsJSON	Docs ↗
Vivgrid	`glm-5.3`	1M	131.072K	$1.2	$4.2	$0.3	ReasoningToolsJSON	Docs ↗
CrossModel	`z-ai/glm-5.3`	1M	128K	$1.2	$4.4	$0.3	ReasoningToolsJSON	Docs ↗
Requesty	`glm-5.3`	1.04858M	1.04858M	$1.2	$4.2	$0.26	ReasoningTools	Docs ↗
Moark	`GLM-5.3`	1M	131.072K	$1.2	$4.18	—	ReasoningToolsJSON	Docs ↗
OrcaRouter	`z-ai/glm-5.3`	1M	131.072K	$1.26	$3.96	$0.234	ReasoningToolsJSON	Docs ↗
Friendli	`zai-org/GLM-5.3`	1.04858M	131.072K	$1.26	$3.96	$0.234	ReasoningToolsJSON	Docs ↗
GreenPT	`glm-5.3`	1M	131.072K	$1.278	$5.11	$0.319	ReasoningToolsJSON	Docs ↗
RunInfra	`zai-org/GLM-5.3`	1.04858M	32.768K	$1.3	$4.2	$0.13	ReasoningToolsJSON	Docs ↗
OpenCode Go	`glm-5.3`	1M	131.072K	$1.4	$4.4	$0.26	ReasoningToolsJSON	Docs ↗
TokenGo	`z-ai/glm-5.3`	1M	131.072K	$1.4	$4.4	$0.26	ReasoningToolsJSON	Docs ↗
Hugging Face	`zai-org/GLM-5.3`	1.04858M	131.072K	$1.4	$4.4	—	ReasoningToolsJSON	Docs ↗
Z.AI	`glm-5.3`	1M	131.072K	$1.4	$4.4	$0.26	ReasoningToolsJSON	Docs ↗
Ollama Cloud	`glm-5.3`	1.04858M	131.072K	$1.4	$4.4	$0.26	ReasoningTools	Docs ↗
Together AI	`zai-org/GLM-5.3`	1.04858M	262.144K	$1.4	$4.4	$0.26	ReasoningToolsJSON	Docs ↗
Ofox	`z-ai/glm-5.3`	1M	131.072K	$1.4	$4.4	$0.26	ReasoningToolsJSON	Docs ↗
ClinePass	`cline-pass/glm-5.3`	1M	131.072K	$1.4	$4.4	$0.26	ReasoningToolsJSON	Docs ↗
Eden AI	`zai/glm-5.3`	1.04858M	131.072K	$1.4	$4.4	$0.26	ReasoningToolsJSON	Docs ↗
Kilo Gateway	`z-ai/glm-5.3`	1.04858M	943.718K	$1.4	$4.4	$0.26	ReasoningToolsJSON	Docs ↗
OpenCode	`glm-5.3`	1M	131.072K	$1.4	$4.4	$0.26	ReasoningToolsJSON	Docs ↗
302.AI	`glm-5.3`	1M	131.072K	$1.4	$4.4	$0.26	ReasoningToolsJSON	Docs ↗
Inco	`glm-5.3`	1M	131.072K	$1.4	$4.4	$0.26	ReasoningToolsJSON	Docs ↗
Mistral	`zai-glm-5-3`	1.04858M	131.072K	$1.4	$4.4	$0.14	ReasoningToolsJSON	Docs ↗
Nebius Token Factory	`zai-org/GLM-5.3`	1.024M	1.024M	$1.4	$4.4	$0.26	ReasoningToolsJSON	Docs ↗
SiliconFlow	`zai-org/GLM-5.3`	1.049M	262K	$1.4	$4.4	$0.26	ReasoningToolsJSON	Docs ↗
Tempr Gateway	`mistral/zai-glm-5-3`	1M	131.072K	$1.4	$4.4	$0.14	ReasoningToolsJSON	Docs ↗
Tempr Gateway	`zai/glm-5.3`	1M	131.072K	$1.4	$4.4	$0.26	ReasoningToolsJSON	Docs ↗
Synthetic	`hf:zai-org/GLM-5.3`	524.288K	65.536K	$1.4	$4.4	$0.26	ReasoningToolsJSON	Docs ↗
Novita AI	`zai-org/glm-5.3`	1.04858M	131.072K	$1.4	$4.4	$0.26	ReasoningToolsJSON	Docs ↗
Prime Inference	`z-ai/glm-5.3`	1.04858M	131.072K	$1.4	$4.4	$0.26	ReasoningTools	Docs ↗
Neon	`glm-5-3`	1.04858M	131.072K	$1.4	$4.4	$0.26	ReasoningToolsJSON	Docs ↗
CommandCode	`zai-org/GLM-5.3`	1M	131.072K	$1.4	$4.4	$0.26	ReasoningToolsJSON	Docs ↗
Standard Compute	`z-ai/glm-5.3`	1M	50K	$1.4	$4.4	$0.26	ReasoningToolsJSON	Docs ↗
Perplexity Agent	`perplexity/glm-5.3`	1M	131.072K	$1.4	$4.4	$0.26	ReasoningToolsJSON	Docs ↗
Arcee	`zai-org/glm-5.3`	1M	131.072K	$1.4	$4.4	$0.26	ReasoningToolsJSON	Docs ↗
Modal	`zai-org/GLM-5.3`	1M	131.072K	$1.4	$4.4	$0.26	ReasoningToolsJSON	Docs ↗
Bothub	`glm-5.3`	1M	131.072K	$1.424	$4.476	—	ReasoningToolsJSON	Docs ↗
Charm Hyper	`glm-5.3`	1M	128K	$1.524	$4.791	$0.283	ReasoningToolsJSON	Docs ↗
Berget.AI	`zai-org/GLM-5.3`	327.68K	32.768K	$1.75	$5.82	—	ReasoningToolsJSON	Docs ↗
TensorX	`z-ai/glm-5.3`	1.04858M	64K	$1.75	$4.5	$0.44	ReasoningToolsJSON	Docs ↗
Opper	`glm-5.3`	1M	131.072K	$1.75	$4.649	$0.44	ReasoningTools	Docs ↗
Privatemode AI	`glm-5.3`	1M	131.072K	$1.791	$6.633	$0.173	ReasoningToolsJSON	Docs ↗
Tinfoil	`glm-5-3`	1.04858M	131.072K	$1.8	$5.75	$0.45	ReasoningToolsJSON	Docs ↗
NEAR AI Cloud	`z-ai/glm-5.3`	1M	131.072K	$1.8	$5.75	$0.45	ReasoningToolsJSON	Docs ↗
Scaleway	`glm-5.3`	256K	16.384K	$2.01	$6.15	—	ReasoningToolsJSON	Docs ↗
DevPass (LLM Gateway)	`glm-5.3-fast`	1M	131.072K	$2.8	$8.8	$0.56	ReasoningToolsJSON	Docs ↗
Thinking Machines	`zai-org/GLM-5.3:peft:262144`	262.144K	262.144K	$3.78	$12.15	$0.756	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 $0.079/M

Across 66 priced providers

Median input $1.4/M

Midpoint of listed rates

Highest input $3.78/M

47.8× the lowest listed rate

Output range $1.4 – $12.15

Per million output tokens

OpenRouter $0.079/MLowest

Kenari $0.286/M

CloudFerro Sherlock $0.34/M

CrofAI $0.4/M

DevPass (LLM Gateway) $0.45/M

Cortecs $0.511/M

Merge Gateway $0.7/M

Vultr $0.75/M

IteraCompute $0.82/M

Deep Infra $0.9/M

engy $0.98/M

ai& $1/M

Alibaba (China) $1.1/M

Vancine $1.12/M

CoralBricks $1.12/M

Boundless $1.12/M

AKI.IO $1.121/M

AIHubMix $1.127/M

Melious $1.159/M

Zhipu AI $1.195/M

Vivgrid $1.2/M

CrossModel $1.2/M

Requesty $1.2/M

Moark $1.2/M

OrcaRouter $1.26/M

Friendli $1.26/M

GreenPT $1.278/M

RunInfra $1.3/M

OpenCode Go $1.4/M

TokenGo $1.4/M

Hugging Face $1.4/M

Z.AI $1.4/M

Ollama Cloud $1.4/M

Together AI $1.4/M

Ofox $1.4/M

ClinePass $1.4/M

Eden AI $1.4/M

Kilo Gateway $1.4/M

OpenCode $1.4/M

302.AI $1.4/M

Inco $1.4/M

Mistral $1.4/M

Nebius Token Factory $1.4/M

SiliconFlow $1.4/M

Tempr Gateway $1.4/M

Synthetic $1.4/M

Novita AI $1.4/M

Prime Inference $1.4/M

Neon $1.4/M

CommandCode $1.4/M

Standard Compute $1.4/M

Perplexity Agent $1.4/M

Arcee $1.4/M

Modal $1.4/M

Bothub $1.424/M

Charm Hyper $1.524/M

Berget.AI $1.75/M

TensorX $1.75/M

Opper $1.75/M

Privatemode AI $1.791/M

Tinfoil $1.8/M

NEAR AI Cloud $1.8/M

Scaleway $2.01/M

DevPass (LLM Gateway) $2.8/M

Thinking Machines $3.78/M

Cost calculator

Estimate a workload

Provider Input tokens 1,000,000 Output tokens 250,000 Cached input 0%

$0.00

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

Context limits also differ by provider, from 256K 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 No

× Vision input No

✓ Open weights Yes

Creator: Zhipu AI
Model family: glm
Knowledge cutoff: Not documented
License: Not documented
Release date: 2026-08-14
Model ID: zhipuai/glm-5.3

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

Humanity's Last Exam accuracy Source ↗

Humanity's Last Exam #3 of 23

62.5

GDPval-AA — 2 Elo Source ↗

GDPval-AA #3 of 6

1769.0

DeepSWE — 1.1 resolved · mini-swe-agent Source ↗

DeepSWE #2 of 3

66.9

Toolathlon-Verified pass@1 Source ↗

Toolathlon-Verified #2 of 3

73.0

AutomationBench — 1.0.6 pass@1 Source ↗

48.2 2 models scored — too few for a distribution

FrontierSWE dominance score · 2026-08-14 Source ↗

78.1 2 models scored — too few for a distribution

NL2Repo score Source ↗

58.0 2 models scored — too few for a distribution

Terminal-Bench — 2.1 pass@1 · Claude Code 2.1.207 Source ↗

88.2 2 models scored — too few for a distribution

Agents' Last Exam score · Claude Code 2.1.207 Source ↗

28.5 1 model scored — too few for a distribution

CyberGym pass@1 · Claude Code 2.1.207 Source ↗

84.5 1 model scored — too few for a distribution

ExploitBench average coverage · Claude Code 2.1.207 Source ↗

54.4 1 model scored — too few for a distribution

ExploitGym tasks solved · Claude Code 2.1.207 Source ↗

130.0 1 model scored — too few for a distribution

PostTrainBench weighted average · Claude Code 2.1.207 Source ↗

39.8 1 model scored — too few for a distribution

ProgramBench almost solved Source ↗

19.0 1 model scored — too few for a distribution

SWE-Marathon — 1.1 score · Claude Code 2.1.207 Source ↗

42.5 1 model scored — too few for a distribution

Terminal-Bench — 3.0 avg@3 · Claude Code 2.1.207 Source ↗

28.3 1 model 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.

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

Oct 20, 2026Price Completion4.4 → 4.18306

Oct 20, 2026Price Prompt1.4 → 1.19516

Sep 01, 2026Price Completion4.2 → 4.4

Sep 01, 2026Price Prompt1.2 → 1.4

Aug 17, 2026Price Completion4.4 → 4.2

Aug 17, 2026Price Prompt1.4 → 1.2

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

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

curl

curl "https://modelbench.lol/api/v1/models/zhipuai/glm-5.3"

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?

Flagship GLM model for long-horizon coding, agents, and complex project delivery. It is published by Zhipu AI and catalogued here from Models.dev.

How much does GLM-5.3 cost?

Listed input pricing starts at $0.079 per million tokens from OpenRouter, rising to $3.78 across 66 listed providers.

What is the context length of GLM-5.3?

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

Does GLM-5.3 support tool calling and structured output?

Provider catalogs list support for tool calling, and reasoning.

Which providers serve GLM-5.3?

73 providers list this model: Zhipu AI Coding Plan, Z.AI Coding Plan, Volcengine Ark Coding Plan, SCNet Token Plan, NaN, AgentRouter and 67 more.

Are the weights for GLM-5.3 open?

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

When was GLM-5.3 released?

The catalog records a release date of 2026-08-14, last verified Oct 24, 2026.

Zhipu AI: GLM-5.3