Where is the GLM 5.3 documentation?

The GLM 5.3 documentation on OpenRouter includes the Self-Hosted LLM vs API: When Does Self-Hosting Pay Off blog post and the How to Benchmark LLMs blog post. The quickstart covers API keys and your first request, and the API reference lists every parameter.

How much does GLM 5.3 cost?

GLM 5.3 costs $0.0699/M input tokens and $1.40/M output tokens, with separate rates for Cache Read at $0.0689/M tokens.

What is the context length of GLM 5.3?

GLM 5.3 has a 1,048,576 token context window. It supports up to 1,048,576 completion tokens.

Does GLM 5.3 support tool calling and structured outputs?

Yes. GLM 5.3 accepts tools for function calling. It also supports structured outputs via a JSON schema in response_format.

Which providers serve GLM 5.3?

GLM 5.3 is served by 37 providers on OpenRouter: Wafer, Relace, inference.net, Reka AI, AkashML, DeepInfra, Baidu Qianfan, Decart and 29 more. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.

When was GLM 5.3 released?

GLM 5.3 was released on August 18, 2026.

Z.ai: GLM 5.3

z-ai/glm-5.3

Model weights

Compare

GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves on GLM-5.2 in coding and in the balance between performance and token efficiency.

Reasoning is always on and cannot be disabled. Reasoning efforts low, high, and max are supported; max is the default.

Modalities

In / out price

$0.0699 / $1.40per 1M

Context

1.0M

Released

Aug 18, 2026

Providers

Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick: Balanced (price + speed), Nitro (fastest), or Floor (cheapest).

Latency / throughput


	$0.56	$1.80	$0.10	0.57s	106 tok/s	100.00%
	$0.60	$2.00	$0.10	0.55s	114 tok/s	99.94%
	$0.0699	$1.40	$0.0689	0.40s	83 tok/s	100.00%
	$0.179	$1.40	$0.178	0.31s	82 tok/s	100.00%
	$0.75	$3.00	$0.19	0.47s	97 tok/s	100.00%
	$0.084	$3.60	$0.079	0.41s	82 tok/s	100.00%
	$1.00	$4.20	$0.14	0.85s	98 tok/s	99.97%
	$0.084	$3.60	$0.079	0.39s	81 tok/s	99.97%
	$0.0703	$4.3843	$0.0703	1.04s	84 tok/s	100.00%
	$1.40	$4.40	$0.26	0.26s	122 tok/s	99.44%
	$1.40	$4.40	$0.26	0.37s	119 tok/s	99.94%
	$0.91	$2.86	$0.169	0.51s	88 tok/s	100.00%
	$1.00	$4.00	$0.16	0.26s	98 tok/s	99.94%
	$0.19	$4.40	$0.19	1.14s	83 tok/s	99.92%
	$0.95	$3.50	$0.19	0.33s	99 tok/s	99.69%
	$0.70	$2.20	$0.13	1.42s	64 tok/s	100.00%
60% off	$1.40$0.5586	$4.40$1.756	$0.26$0.1037	1.33s	59 tok/s	99.04%
	$1.40	$4.40	$0.14	0.50s	91 tok/s	99.96%
	$0.75	$3.00	$0.12	1.21s	63 tok/s	99.89%
	$0.15	$3.00	$0.12	0.77s	52 tok/s	99.73%
	$1.40	$4.40	$0.26	0.56s	79 tok/s	99.84%
50% off	$1.40$0.70	$4.40$2.20	$0.26$0.13	2.34s	66 tok/s	100.00%
Fast	$2.10	$6.60	$0.21	0.38s	157 tok/s	100.00%
Fast	$2.10	$6.60	$0.39	0.51s	177 tok/s	99.04%
10% off	$1.40$1.26	$4.40$3.96	$0.26$0.234	0.39s	83 tok/s	100.00%
	$1.40	$4.40	$0.14	0.75s	85 tok/s	100.00%
	$1.145	$3.522	$0.386	0.76s	74 tok/s	100.00%
50% off	$1.40$0.70	$4.40$2.20	$0.26$0.13	1.59s	51 tok/s	99.82%
38% off	$0.90$0.5625	$4.00$2.50	$0.20$0.125	0.98s	52 tok/s	99.56%
Fast	$2.10	$6.60	$0.21	0.32s	124 tok/s	100.00%
	$1.40	$4.40	$0.26	1.35s	55 tok/s	100.00%
	$1.40	$4.40	$0.14	0.81s	61 tok/s	100.00%
20% off	$1.75$1.40	$5.50$4.40	$0.325$0.26	0.66s	127 tok/s	99.42%
	$1.05	$4.20	$0.168	0.93s	61 tok/s	99.71%
	$1.54	$4.84	$0.154	0.87s	95 tok/s	100.00%
	$1.19	$3.74	$0.238	1.70s	59 tok/s	99.43%
	$1.68	$5.28	$0.312	1.21s	84 tok/s	99.88%
	$1.40	$4.40	$0.26	0.55s	79 tok/s	100.00%
50% off	$2.80$1.40	$8.80$4.40	$0.14$0.07	1.17s	48 tok/s	100.00%
	$1.40	$4.40	$0.26	1.47s	55 tok/s	93.13%
	$1.40	$4.40	$0.26	0.50s	108 tok/s	95.90%
	$0.98	$3.08	$0.182	0.45s	115 tok/s	98.07%
55% off	$1.40$0.63	$4.40$1.98	$0.26$0.117	1.41s	62 tok/s	100.00%
	$1.40	$4.40	$0.28	0.90s	66 tok/s	100.00%
	$1.40	$4.40	$0.26	1.47s	45 tok/s	100.00%
Prime	$2.80	$8.80	$0.56	0.56s	100 tok/s	100.00%
	$1.40	$4.40	$0.26	0.39s	110 tok/s	100.00%
Fast	$2.10	$6.60	$0.26	0.65s	168 tok/s	94.73%
Not used in Standard routing:Why these endpoints are not used
Flex38% off	$0.72$0.45	$3.20$2.00	$0.16$0.10	1.63s	67 tok/s	100.00%

Input $0.56Output $1.80
106 tok/s100.00% uptime
Input $0.60Output $2.00
114 tok/s99.94% uptime
Input $0.0699Output $1.40
83 tok/s100.00% uptime
Input $0.179Output $1.40
82 tok/s100.00% uptime
Input $0.75Output $3.00
97 tok/s100.00% uptime
Input $0.084Output $3.60
82 tok/s100.00% uptime
Input $1.00Output $4.20
98 tok/s99.97% uptime
Input $0.084Output $3.60
81 tok/s99.97% uptime
Input $0.0703Output $4.3843
84 tok/s100.00% uptime
Input $1.40Output $4.40
122 tok/s99.44% uptime
Input $1.40Output $4.40
119 tok/s99.94% uptime
Input $0.91Output $2.86
88 tok/s100.00% uptime
Input $1.00Output $4.00
98 tok/s99.94% uptime
Input $0.19Output $4.40
83 tok/s99.92% uptime
Input $0.95Output $3.50
99 tok/s99.69% uptime
Input $0.70Output $2.20
64 tok/s100.00% uptime
Input $0.5586Output $1.756
60% off
59 tok/s99.04% uptime
Input $1.40Output $4.40
91 tok/s99.96% uptime
Input $0.75Output $3.00
63 tok/s99.89% uptime
Input $0.15Output $3.00
52 tok/s99.73% uptime
Input $1.40Output $4.40
79 tok/s99.84% uptime
Input $0.70Output $2.20
50% off
66 tok/s100.00% uptime
Input $2.10Output $6.60
Fast
157 tok/s100.00% uptime
Input $2.10Output $6.60
Fast
177 tok/s99.04% uptime
Input $1.26Output $3.96
10% off
83 tok/s100.00% uptime
Input $1.40Output $4.40
85 tok/s100.00% uptime
Input $1.145Output $3.522
74 tok/s100.00% uptime
Input $0.70Output $2.20
50% off
51 tok/s99.82% uptime
Input $0.5625Output $2.50
38% off
52 tok/s99.56% uptime
Input $2.10Output $6.60
Fast
124 tok/s100.00% uptime
Input $1.40Output $4.40
55 tok/s100.00% uptime
Input $1.40Output $4.40
61 tok/s100.00% uptime
Input $1.40Output $4.40
20% off
127 tok/s99.42% uptime
Input $1.05Output $4.20
61 tok/s99.71% uptime
Input $1.54Output $4.84
95 tok/s100.00% uptime
Input $1.19Output $3.74
59 tok/s99.43% uptime
Input $1.68Output $5.28
84 tok/s99.88% uptime
Input $1.40Output $4.40
79 tok/s100.00% uptime
Input $1.40Output $4.40
50% off
48 tok/s100.00% uptime
Input $1.40Output $4.40
55 tok/s93.13% uptime
Input $1.40Output $4.40
108 tok/s95.90% uptime
Input $0.98Output $3.08
115 tok/s98.07% uptime
Input $0.63Output $1.98
55% off
62 tok/s100.00% uptime
Input $1.40Output $4.40
66 tok/s100.00% uptime
Input $1.40Output $4.40
45 tok/s100.00% uptime
Input $2.80Output $8.80
Prime
100 tok/s100.00% uptime
Input $1.40Output $4.40
110 tok/s100.00% uptime
Input $2.10Output $6.60
Fast
168 tok/s94.73% uptime
Not used in Standard routing:Why these endpoints are not used
Input $0.45Output $2.00
Flex
1 more label
67 tok/s100.00% uptime

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Weighted average

Input

$0.1674/M tokens

Output

$2.841/M tokens

GLM 5.3 — Price history

Price history

No effective price data for this selection

		$0.0690	$1.40	93.4%	22.7%
		$0.0703	$4.38	89.5%	1.0%
		$0.0793	$3.60	94.2%	4.8%
		$0.0793	$3.60	94.0%	5.1%
		$0.1240	$1.84	95.2%	14.0%
		$0.1275	$3.00	75.0%	0.3%
		$0.1366	$1.75	92.8%	4.0%
		$0.1438	$2.00	91.2%	5.5%
		$0.1508	$3.00	95.1%	0.5%
		$0.1652	$2.20	93.8%	0.3%
		$0.1714	$2.20	92.7%	0.2%
		$0.1746	$2.52	90.9%	0.9%
		$0.1780	$1.40	93.6%	7.0%
		$0.1792	$1.84	65.4%	0.0%
		$0.1846	$4.20	94.8%	2.5%
		$0.1885	$2.21	89.8%	0.5%
		$0.1900	$4.40	82.7%	0.4%
		$0.2230	$3.08	94.9%	0.5%
		$0.2233	$2.86	92.7%	1.9%
		$0.2270	$4.40	93.1%	0.7%
		$0.2293	$4.40	92.9%	0.3%
		$0.2301	$3.00	92.8%	3.9%
		$0.2412	$3.50	93.3%	0.2%
		$0.2485	$2.10	92.5%	0.8%
		$0.2572	$1.98	73.0%	0.5%
	Fast	$0.2785	$6.60	96.4%	0.3%
		$0.2912	$4.40	83.4%	0.0%
		$0.2921	$4.40	97.2%	14.8%
		$0.3029	$3.74	93.2%	0.5%
		$0.3224	$4.40	94.5%	0.0%
		$0.3272	$4.40	85.1%	0.8%
	Fast	$0.3276	$6.60	93.8%	0.3%
		$0.3418	$4.40	92.8%	0.3%
		$0.3463	$4.84	86.1%	0.1%
		$0.3515	$4.40	92.0%	0.1%
		$0.3585	$4.40	91.4%	0.1%
		$0.3682	$4.40	90.5%	1.6%
		$0.3874	$4.00	72.9%	0.2%
		$0.4538	$4.40	83.0%	1.2%
		$0.4590	$5.28	89.3%	0.1%
		$0.4734	$4.20	65.4%	0.0%
	Fast	$0.5117	$6.60	86.3%	0.2%
		$0.5240	$4.40	78.2%	0.0%
		$0.5581	$4.40	73.9%	0.0%
		$0.5942	$3.98	64.9%	0.2%
	Fast	$0.6126	$6.60	87.0%	0.4%
		$0.6457	$4.40	66.2%	0.0%
	Prime	$0.8844	$8.80	85.5%	0.1%
Not used in Standard routing:Why these endpoints are not used
	Flex	$0.1646	$2.00	81.5%	0.0%

Effective in $0.0690Effective out $1.40
Token share
22.7%
Effective in $0.0703Effective out $4.38
Token share
1.0%
Effective in $0.0793Effective out $3.60
Token share
4.8%
Effective in $0.0793Effective out $3.60
Token share
5.1%
Effective in $0.1240Effective out $1.84
Token share
14.0%
Effective in $0.1275Effective out $3.00
Token share
0.3%
Effective in $0.1366Effective out $1.75
Token share
4.0%
Effective in $0.1438Effective out $2.00
Token share
5.5%
Effective in $0.1508Effective out $3.00
Token share
0.5%
Effective in $0.1652Effective out $2.20
Token share
0.3%
Effective in $0.1714Effective out $2.20
Token share
0.2%
Effective in $0.1746Effective out $2.52
Token share
0.9%
Effective in $0.1780Effective out $1.40
Token share
7.0%
Effective in $0.1792Effective out $1.84
Token share
0.0%
Effective in $0.1846Effective out $4.20
Token share
2.5%
Effective in $0.1885Effective out $2.21
Token share
0.5%
Effective in $0.1900Effective out $4.40
Token share
0.4%
Effective in $0.2230Effective out $3.08
Token share
0.5%
Effective in $0.2233Effective out $2.86
Token share
1.9%
Effective in $0.2270Effective out $4.40
Token share
0.7%
Effective in $0.2293Effective out $4.40
Token share
0.3%
Effective in $0.2301Effective out $3.00
Token share
3.9%
Effective in $0.2412Effective out $3.50
Token share
0.2%
Effective in $0.2485Effective out $2.10
Token share
0.8%
Effective in $0.2572Effective out $1.98
Token share
0.5%
Effective in $0.2785Effective out $6.60
FastToken share
0.3%
Effective in $0.2912Effective out $4.40
Token share
0.0%
Effective in $0.2921Effective out $4.40
Token share
14.8%
Effective in $0.3029Effective out $3.74
Token share
0.5%
Effective in $0.3224Effective out $4.40
Token share
0.0%
Effective in $0.3272Effective out $4.40
Token share
0.8%
Effective in $0.3276Effective out $6.60
FastToken share
0.3%
Effective in $0.3418Effective out $4.40
Token share
0.3%
Effective in $0.3463Effective out $4.84
Token share
0.1%
Effective in $0.3515Effective out $4.40
Token share
0.1%
Effective in $0.3585Effective out $4.40
Token share
0.1%
Effective in $0.3682Effective out $4.40
Token share
1.6%
Effective in $0.3874Effective out $4.00
Token share
0.2%
Effective in $0.4538Effective out $4.40
Token share
1.2%
Effective in $0.4590Effective out $5.28
Token share
0.1%
Effective in $0.4734Effective out $4.20
Token share
0.0%
Effective in $0.5117Effective out $6.60
FastToken share
0.2%
Effective in $0.5240Effective out $4.40
Token share
0.0%
Effective in $0.5581Effective out $4.40
Token share
0.0%
Effective in $0.5942Effective out $3.98
Token share
0.2%
Effective in $0.6126Effective out $6.60
FastToken share
0.4%
Effective in $0.6457Effective out $4.40
Token share
0.0%
Effective in $0.8844Effective out $8.80
PrimeToken share
0.1%
Not used in Standard routing:Why these endpoints are not used
Effective in $0.1646Effective out $2.00
FlexToken share
0.0%

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).

Throughput

177tok/s

P50, best across providers

Latency

0.26s

P50, best provider

Reasoning effortLatency / throughput

AutoExacto benchmarks

GPQA DiamondTAU-BenchBaseten (fp8) (US)84.7%83.7%Wafer88.4%78.7%Wafer (US)87.6%79.1%Doubleword88.6%78.0%Z.ai88.4%77.4%DeepInfra87.0%78.1%Baseten (fp4) (US)84.0%76.6%Baseten (fp4)84.0%76.2%Baseten (fp8)84.6%70.4%

+39 more providers

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Uptime (3d)

99.99%

Availability (3d)

99.92%

Availability over the last 3 days

Last 72 hours

Availability 99.92%

3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability

99.95%

Without Routing

99.25%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.

Benchmarks

Scores on standardized evaluations and this model’s own outputs on shared benchmark prompts. Higher percentages are better — and each rank shows where this model lands among the models evaluated on that source.

Benchmark score summary for Z.ai: GLM 5.3 (Artificial Analysis, Design Arena and Vals AI)
Source	Benchmark	Score
Artificial Analysis	GLM-5.3 (Max) Intelligence Index	31.7
Artificial Analysis	GLM-5.3 (Max) Coding Index	74.8
Artificial Analysis	GLM-5.3 (Max) Agentic Index	53.1
Artificial Analysis	GLM-5.3 (Max) GPQA Diamond	91.7%
Artificial Analysis	GLM-5.3 (Max) HLE	42.3%
Artificial Analysis	GLM-5.3 (Max) AA-LCR	79.7%
Artificial Analysis	GLM-5.3 (Max) τ-Bench Banking	50.3%
Artificial Analysis	GLM-5.3 (Max) GDPval-AA	57.7%
Artificial Analysis	GLM-5.3 (Max) CritPt	19.1%
Artificial Analysis	GLM-5.3 (Max) SciCode	59.0%
Artificial Analysis	GLM-5.3 (Max) Terminal-Bench 4.0	41.9%
Artificial Analysis	GLM-5.3 (Max) Terminal-Bench 2.1	83.9%
Artificial Analysis	GLM-5.3 (Max) AA-Omniscience Accuracy	32.3%
Artificial Analysis	GLM-5.3 (Max) AA-Omniscience Non-Hallucination Rate	61.1%
Artificial Analysis	GLM-5.3 (Low) Intelligence Index	23.1
Artificial Analysis	GLM-5.3 (Low) HLE	36.6%
Artificial Analysis	GLM-5.3 (Low) AA-LCR	72.7%
Artificial Analysis	GLM-5.3 (Low) GDPval-AA	41.6%
Artificial Analysis	GLM-5.3 (Low) CritPt	14.6%
Artificial Analysis	GLM-5.3 (Low) SciCode	42.0%
Artificial Analysis	GLM-5.3 (Low) Terminal-Bench 4.0	34.8%
Artificial Analysis	GLM-5.3 (Low) AA-Omniscience Accuracy	31.9%
Artificial Analysis	GLM-5.3 (Low) AA-Omniscience Non-Hallucination Rate	36.8%
Design Arena	GLM-5.3 Models Arena 3D Elo	1294
Design Arena	GLM-5.3 Models Arena Asciiart Elo	1198
Design Arena	GLM-5.3 Models Arena Code Categories Elo	1283
Design Arena	GLM-5.3 Models Arena Data Visualization Elo	1251
Design Arena	GLM-5.3 Models Arena Game Development Elo	1288
Design Arena	GLM-5.3 Models Arena SVG Elo	1246
Design Arena	GLM-5.3 Models Arena UI Component Elo	1285
Design Arena	GLM-5.3 Models Arena Website Elo	1279
Design Arena	GLM-5.3 Agents Arena Htmlslides Elo	1189
Design Arena	GLM-5.3 Agents Arena Mobile Apps Elo	1184
Design Arena	GLM-5.3 Agents Arena Python-Pptxslides Elo	1216
Design Arena	GLM-5.3 Agents Arena Webapps Elo	1270
Vals AI	GLM 5.3 Access to Justice Benchmark	73.7%
Vals AI	GLM 5.3 Code Migration v1.1	55.1%
Vals AI	GLM 5.3 CyberBench v1.1	72.1%
Vals AI	GLM 5.3 EMB v1.1	69.1%
Vals AI	GLM 5.3 Finance Agent v2.1	65.0%
Vals AI	GLM 5.3 Vals Finance Index	61.4%
Vals AI	GLM 5.3 Financial Coaching Bench	74.1%
Vals AI	GLM 5.3 GPQA Diamond	88.1%
Vals AI	GLM 5.3 HLAB-Vals-1.1	14.6%
Vals AI	GLM 5.3 Immigration	66.7%
Vals AI	GLM 5.3 IOI	68.4%
Vals AI	GLM 5.3 LiveCodeBench	80.5%
Vals AI	GLM 5.3 LegalBench	84.8%
Vals AI	GLM 5.3 Vals Legal Index	74.6%
Vals AI	GLM 5.3 Legal Research Bench	49.0%
Vals AI	GLM 5.3 MedCode	42.9%
Vals AI	GLM 5.3 MedScribe	88.8%
Vals AI	GLM 5.3 MMLU Pro	86.8%
Vals AI	GLM 5.3 MysteryMechanism	23.0%
Vals AI	GLM 5.3 ProgramBench	1.5%
Vals AI	GLM 5.3 ProofBench v1.1	49.0%
Vals AI	GLM 5.3 Public Benefits Bench v1.1	68.5%
Vals AI	GLM 5.3 Vals RSI Index	22.9%
Vals AI	GLM 5.3 SkillsBench	47.5%
Vals AI	GLM 5.3 SRE Bench	9.2%
Vals AI	GLM 5.3 SWE-bench	95.4%
Vals AI	GLM 5.3 Tax Agent Bench	43.3%
Vals AI	GLM 5.3 TaxEval v2	72.4%
Vals AI	GLM 5.3 Terminal-Bench 4.0	38.9%
Vals AI	GLM 5.3 Terminal-Bench-Science	5.7%
Vals AI	GLM 5.3 Vals Index	59.8%
Vals AI	GLM 5.3 Vibe Code Bench 1-100 v1.1	29.8%
Vals AI	GLM 5.3 Vibe Code Bench v1.1	78.1%

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

Claude Code

Claude Code is Anthropic's agentic coding tool that reads your entire codebase, plans and executes changes across files, runs tests, and iterates on failures, all from natural language prompts.

2.02Ttokens

Hermes Agent

Hermes Agent is an open-source, self-improving AI agent by Nous Research that runs persistently with memory across sessions, and builds reusable skills from experience. It comes with 40+ built-in tools, including web search, browser automation, and vision, plus scheduled automations and subagents.

902Btokens

There are many coding agents, but this one is yours.

694Btokens

Strix

Open-source AI hackers that find and validate vulnerabilities in your code, APIs, and infrastructure, and open fix PRs.

663Btokens

omp

new

481Btokens

Rest of OpenRouter

222B

Top 5 Apps

51.9B

Z.ai: GLM versions

Available through EU in-region routing

Z.ai: GLM 5.3 is available through EU in-region routing. Requests sent to eu.openrouter.ai are decrypted in the EU and routed only to shared provider endpoints in Europe (the EU/EEA, the UK, and Switzerland).

Providers in Europe

Inceptron, Mistral

Prices in Europe

Inceptron: $1/M tokens input, $4.20/M tokens output
Mistral: $1.54/M tokens input, $4.84/M tokens output

Base URL

https://eu.openrouter.ai/api/v1

Plan

Requires Business or Enterprise. Self-serve on Business: no contract, no monthly minimum. OpenRouter Business for EU in-region routing

Fails closed: if no shared provider endpoint in Europe is available, the request errors instead of leaving the region. Requests served by your own BYOK key go to your deployment’s region, which you control. In-region routing docs

More models from Z.ai

GLM 5.3 FlashX Legal

GLM-5.3-FlashX-Legal (GLM-Legal) is Z.ai's legal-domain variant of GLM-5.3-FlashX, a native multimodal model that accepts text, image, and video input and produces text. It adds legal-domain mid-training and post-training with reinforcement learning in task environments modeled on real legal workflows, targeting document understanding, legal reasoning, and multi-step task execution such as legal research, contract review, cross-document consistency checks, and drafting or revising legal documents.

It keeps the GLM-5.3-FlashX 1M-token context window, mandatory thinking mode, function calling, structured output, and streaming, and is designed to run in agent setups connected to legal data and document-editing tools (MCP services).

Text1.0M context$0.37 / $1.25

GLM 5.3 Prime

GLM-5.3-Prime is the high-speed variant of Z.ai's GLM-5.3, inheriting its full capabilities while delivering 1.5–2× the output throughput through inference acceleration. It supports text input and output with a 1M-token context window and up to 128K output tokens, and targets coding and agentic workloads, including long-horizon multi-turn agent orchestration, real-time conversation, and streaming code generation.

Reasoning is always on and cannot be disabled. Reasoning efforts low, high, and max are supported; max is the default.

Text1M context$2.80 / $8.80

GLM 5.3 FlashX

GLM-5.3-FlashX is the high-speed variant of Z.ai's GLM-5.3-Flash, a native multimodal model delivering inference speeds of up to 200 tokens/s. Built on the same hybrid sparse and linear attention architecture (320B total parameters, 18B active), it is suited for efficient coding, visual understanding, and long-horizon agent tasks with a 1M-token context window.

Text1.0M context$0.37 / $1.25

GLM Flash Latest

This model always redirects to the latest model in the GLM Flash family.

Text1.0M context

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 reducing compute overhead.

Text1.0M context$0.0399 / $0.0784

GLM 5.3 Flash (batch)

Text1.0M context$0.05 / $0.18

GLM Latest

This model always redirects to the latest GLM model from Z.ai.

Text1.0M context

GLM 5.3

Reasoning is always on and cannot be disabled. Reasoning efforts low, high, and max are supported; max is the default.

Text1.0M context$0.0699 / $1.40

GLM 5.3 (batch)

Reasoning is always on and cannot be disabled. Reasoning efforts low, high, and max are supported; max is the default.

Text1.0M context$0.45 / $2

GLM 5.2

GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering, and complex multi-step automation.

Reasoning efforts high and xhigh are supported; xhigh maps to max reasoning. It is particularly strong at coding and tool use across long-running tasks, able to maintain engineering context and follow standards consistently through a full development workflow, from requirements to multi-platform deployment, in a single task.

Text1.0M context$0.0066 / $7.983

GLM 5.1

GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models built around minute-level interactions, GLM-5.1 can work independently and continuously on a single task for more than 8 hours, autonomously planning, executing, and improving itself throughout the process, ultimately delivering complete, engineering-grade results.

Text205K context$0.8988 / $2.825

GLM 5V Turbo

GLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks. It natively handles image, video, and text inputs, excels at long-horizon planning, complex coding, and task execution, and works seamlessly with agents to complete the full loop of “perceive → plan → execute“.

Text203K context$1.20 / $4

GLM 5 Turbo

GLM-5 Turbo is a new model from Z.ai designed for fast inference and strong performance in agent-driven environments such as OpenClaw scenarios. It is deeply optimized for real-world agent workflows involving long execution chains, with improved complex instruction decomposition, tool use, scheduled and persistent execution, and overall stability across extended tasks.

Text203K context$1.20 / $4

GLM 5

GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading closed-source models. With advanced agentic planning, deep backend reasoning, and iterative self-correction, GLM-5 moves beyond code generation to full-system construction and autonomous execution.

Text205K context$0.60 / $1.92

GLM 4.7 Flash

As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency. It is further optimized for agentic coding use cases, strengthening coding capabilities, long-horizon task planning, and tool collaboration, and has achieved leading performance among open-source models of the same size on several current public benchmark leaderboards.

Text200K context$0.0605 / $0.40

GLM 4.7

GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates significant improvements in executing complex agent tasks while delivering more natural conversational experiences and superior front-end aesthetics.

Text205K context$0.40 / $1.75

GLM 4.6V

GLM-4.6V is a large multimodal model designed for high-fidelity visual understanding and long-context reasoning across images, documents, and mixed media. It supports up to 128K tokens, processes complex page layouts and charts directly as visual inputs, and integrates native multimodal function calling to connect perception with downstream tool execution. The model also enables interleaved image-text generation and UI reconstruction workflows, including screenshot-to-HTML synthesis and iterative visual editing.

Text131K context$0.30 / $0.90

GLM 4.6

Compared with GLM-4.5, this generation brings several key improvements:

Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex agentic tasks. Superior coding performance: The model achieves higher scores on code benchmarks and demonstrates better real-world performance in applications such as Claude Code、Cline、Roo Code and Kilo Code, including improvements in generating visually polished front-end pages. Advanced reasoning: GLM-4.6 shows a clear improvement in reasoning performance and supports tool use during inference, leading to stronger overall capability. More capable agents: GLM-4.6 exhibits stronger performance in tool using and search-based agents, and integrates more effectively within agent frameworks. Refined writing: Better aligns with human preferences in style and readability, and performs more naturally in role-playing scenarios.

Text205K context$0.43 / $1.75

GLM 4.5V

GLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) architecture with 106B parameters and 12B activated parameters, it achieves state-of-the-art results in video understanding, image Q&A, OCR, and document parsing, with strong gains in front-end web coding, grounding, and spatial reasoning. It offers a hybrid inference mode: a "thinking mode" for deep reasoning and a "non-thinking mode" for fast responses. Reasoning behavior can be toggled via the reasoning enabled boolean. Learn more in our docs

Text66K context$0.60 / $1.80

GLM 4.5

GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 128k tokens. GLM-4.5 delivers significantly enhanced capabilities in reasoning, code generation, and agent alignment. It supports a hybrid inference mode with two options, a "thinking mode" designed for complex reasoning and tool use, and a "non-thinking mode" optimized for instant responses. Users can control the reasoning behaviour with the reasoning enabled boolean. Learn more in our docs

Text131K context$0.60 / $2.20

Z.ai: GLM 5.3

Providers