Was ZAI GLM-5.3 Flash the stealth model Ox Alpha?

Yes, the stealth model Ox Alpha was revealed to be ZAI's new model, GLM-5.3 Flash.

Where is the GLM 5.3 Flash documentation?

The GLM 5.3 Flash documentation on OpenRouter includes the Open-Weight vs Closed-Weight Models: What's the Difference? blog post. The quickstart covers API keys and your first request, and the API reference lists every parameter.

How much does GLM 5.3 Flash cost?

GLM 5.3 Flash costs $0.0399/M input tokens and $0.0784/M output tokens, with separate rates for Cache Read at $0.03/M tokens.

What is the context length of GLM 5.3 Flash?

GLM 5.3 Flash has a 1,048,576 token context window. It supports up to 131,072 completion tokens.

Does GLM 5.3 Flash support tool calling and structured outputs?

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

What inputs and outputs does GLM 5.3 Flash support?

GLM 5.3 Flash accepts text, images, and video as input and returns text.

Which providers serve GLM 5.3 Flash?

GLM 5.3 Flash is served by 37 providers on OpenRouter: Relace, Wafer, Open Inference, Darkbloom, Tenstorrent, GMICloud, NEAR AI, NovitaAI 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 Flash released?

GLM 5.3 Flash was released on August 26, 2026.

Z.ai: GLM 5.3 Flash

z-ai/glm-5.3-flash

Model weights

Compare

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.

Modalities

In / out price

$0.0399 / $0.0784per 1M

Context

1.0M

Released

Aug 26, 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


	$0.0399	$0.0784	$0.03	0.54s	99 tok/s	100.00%
	$0.06	$0.30	$0.03	0.66s	124 tok/s	99.86%
	$0.15	$0.50	$0.03	0.58s	150 tok/s	99.86%
	$0.15	$0.50	$0.03	0.51s	149 tok/s	99.69%
	$0.12	$0.50	$0.04	0.54s	151 tok/s	100.00%
	$0.1125	$0.375	$0.03	0.74s	133 tok/s	100.00%
	$0.15	$0.50	$0.03	0.35s	125 tok/s	100.00%
	$0.14	$0.24	$0.03	0.49s	95 tok/s	100.00%
	$0.15	$0.50	$0.03	0.31s	124 tok/s	100.00%
	$0.15	$0.50	$0.03	0.25s	123 tok/s	99.72%
	$0.108	$0.35	$0.035	0.30s	103 tok/s	100.00%
	$0.15	$0.50	$0.03	0.78s	113 tok/s	100.00%
	$0.108	$0.35	$0.035	0.32s	95 tok/s	100.00%
	$0.175	$0.47	$0.04	0.36s	120 tok/s	100.00%
	$0.12	$0.40	$0.024	0.88s	88 tok/s	99.97%
	$0.12	$0.30	$0.03	0.68s	87 tok/s	100.00%
	$0.15	$0.50	$0.03	1.02s	111 tok/s	100.00%
	$0.15	$0.50	$0.03	0.97s	98 tok/s	99.82%
	$0.042	$0.184	$0.041	0.52s	81 tok/s	100.00%
Fast	$0.1875	$0.625	$0.0375	0.58s	156 tok/s	99.82%
	$0.15	$0.50	$0.03	1.76s	96 tok/s	99.96%
	$0.15	$0.50	$0.03	0.68s	92 tok/s	100.00%
	$0.10	$0.50	$0.03	1.09s	63 tok/s	98.95%
	$0.065	$0.24	$0.064	0.56s	83 tok/s	100.00%
	$0.15	$0.50	$0.03	0.45s	105 tok/s	99.80%
	$0.12	$0.45	$0.03	0.84s	45 tok/s	100.00%
	$0.15	$0.50	$0.03	1.38s	94 tok/s	98.72%
	$0.10	$0.40	$0.03	0.92s	40 tok/s	99.33%
	$0.174	$0.183	$0.075	0.41s	40 tok/s	100.00%
50% off	$0.15$0.075	$0.50$0.25	$0.03$0.015	0.86s	33 tok/s	100.00%
	$0.075	$0.25	$0.015	0.88s	45 tok/s	99.80%
	$0.175	$0.625	$0.0225	1.03s	44 tok/s	100.00%
44% off	$0.15$0.084	$0.50$0.28	$0.03$0.0168	1.47s	33 tok/s	100.00%
	$0.08	$0.50	$0.012	0.67s	28 tok/s	99.97%
41% off	$0.15$0.0885	$0.50$0.295	$0.03$0.0177	1.49s	31 tok/s	99.89%
	$0.15	$0.50	$0.03	2.12s	36 tok/s	100.00%
	$0.15	$0.50	$0.03	2.13s	30 tok/s	97.85%
	$0.175	$0.625	$0.0225	3.00s	29 tok/s	100.00%
	$0.12	$0.38	$0.02	0.54s	169 tok/s	100.00%
	$0.15	$0.50	$0.03	0.79s	83 tok/s	98.33%
	$0.225	$0.75	$0.045	0.71s	106 tok/s	95.81%
	$0.065	$0.18	$0.012	6.19s	19 tok/s	94.72%

Input $0.0399Output $0.0784
99 tok/s100.00% uptime
Input $0.06Output $0.30
124 tok/s99.86% uptime
Input $0.15Output $0.50
150 tok/s99.86% uptime
Input $0.15Output $0.50
149 tok/s99.69% uptime
Input $0.12Output $0.50
151 tok/s100.00% uptime
Input $0.1125Output $0.375
133 tok/s100.00% uptime
Input $0.15Output $0.50
125 tok/s100.00% uptime
Input $0.14Output $0.24
95 tok/s100.00% uptime
Input $0.15Output $0.50
124 tok/s100.00% uptime
Input $0.15Output $0.50
123 tok/s99.72% uptime
Input $0.108Output $0.35
103 tok/s100.00% uptime
Input $0.15Output $0.50
113 tok/s100.00% uptime
Input $0.108Output $0.35
95 tok/s100.00% uptime
Input $0.175Output $0.47
120 tok/s100.00% uptime
Input $0.12Output $0.40
88 tok/s99.97% uptime
Input $0.12Output $0.30
87 tok/s100.00% uptime
Input $0.15Output $0.50
111 tok/s100.00% uptime
Input $0.15Output $0.50
98 tok/s99.82% uptime
Input $0.042Output $0.184
81 tok/s100.00% uptime
Input $0.1875Output $0.625
Fast
156 tok/s99.82% uptime
Input $0.15Output $0.50
96 tok/s99.96% uptime
Input $0.15Output $0.50
92 tok/s100.00% uptime
Input $0.10Output $0.50
63 tok/s98.95% uptime
Input $0.065Output $0.24
83 tok/s100.00% uptime
Input $0.15Output $0.50
105 tok/s99.80% uptime
Input $0.12Output $0.45
45 tok/s100.00% uptime
Input $0.15Output $0.50
94 tok/s98.72% uptime
Input $0.10Output $0.40
40 tok/s99.33% uptime
Input $0.174Output $0.183
40 tok/s100.00% uptime
Input $0.075Output $0.25
50% off
33 tok/s100.00% uptime
Input $0.075Output $0.25
45 tok/s99.80% uptime
Input $0.175Output $0.625
44 tok/s100.00% uptime
Input $0.084Output $0.28
44% off
33 tok/s100.00% uptime
Input $0.08Output $0.50
28 tok/s99.97% uptime
Input $0.0885Output $0.295
41% off
31 tok/s99.89% uptime
Input $0.15Output $0.50
36 tok/s100.00% uptime
Input $0.15Output $0.50
30 tok/s97.85% uptime
Input $0.175Output $0.625
29 tok/s100.00% uptime
Input $0.12Output $0.38
169 tok/s100.00% uptime
Input $0.15Output $0.50
83 tok/s98.33% uptime
Input $0.225Output $0.75
106 tok/s95.81% uptime
Input $0.065Output $0.18
19 tok/s94.72% 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

$0.04579/M tokens

Output

$0.3964/M tokens

GLM 5.3 Flash — Price history

Price history

No effective price data for this selection

	$0.0244	$0.4994	81.7%	1.9%
	$0.0311	$0.0778	88.3%	6.1%
	$0.0316	$0.2505	72.5%	0.6%
	$0.0327	$0.2997	91.1%	4.6%
	$0.0343	$0.3796	85.7%	3.2%
	$0.0347	$0.3994	88.8%	3.9%
	$0.0372	$0.4999	89.8%	1.7%
	$0.0374	$0.1791	52.1%	0.1%
	$0.0376	$0.4996	93.6%	0.4%
	$0.0384	$0.3493	95.3%	6.1%
	$0.0393	$0.3990	86.6%	0.5%
	$0.0404	$0.4485	88.5%	0.1%
	$0.0412	$0.1832	79.4%	2.6%
	$0.0413	$0.3492	91.3%	1.2%
	$0.0422	$0.4993	89.8%	4.0%
	$0.0423	$0.4996	89.7%	0.3%
	$0.0431	$0.4997	89.1%	2.7%
	$0.0440	$0.4996	88.4%	0.6%
	$0.0447	$0.4995	87.8%	12.5%
	$0.0455	$0.4996	87.0%	0.9%
	$0.0456	$0.4995	87.0%	9.2%
	$0.0459	$0.2943	60.1%	0.3%
	$0.0468	$0.2392	84.7%	1.8%
	$0.0471	$0.2991	80.9%	0.7%
	$0.0481	$0.3744	78.1%	3.4%
	$0.0482	$0.4995	89.7%	8.0%
	$0.0540	$0.2959	47.5%	3.4%
	$0.0543	$0.4995	79.7%	5.5%
	$0.0555	$0.4995	78.7%	0.8%
	$0.0564	$0.4995	77.9%	0.9%
	$0.0587	$0.2498	27.2%	0.1%
	$0.0638	$0.4689	82.4%	1.0%
	$0.0640	$0.4998	71.6%	5.9%
	$0.0642	$0.2393	72.8%	0.4%
	$0.0658	$0.4997	70.1%	2.1%
	$0.0683	$0.4994	68.1%	0.6%
	$0.0704	$0.1450	83.7%	0.4%
Fast	$0.0874	$0.6247	66.7%	0.1%
	$0.0893	$0.4995	50.6%	0.3%
	$0.1025	$0.7496	68.0%	1.1%
	$0.1143	$0.6243	39.7%	0.0%
	$0.1472	$0.6238	18.1%	0.0%

Effective in $0.0244Effective out $0.4994
Token share
1.9%
Effective in $0.0311Effective out $0.0778
Token share
6.1%
Effective in $0.0316Effective out $0.2505
Token share
0.6%
Effective in $0.0327Effective out $0.2997
Token share
4.6%
Effective in $0.0343Effective out $0.3796
Token share
3.2%
Effective in $0.0347Effective out $0.3994
Token share
3.9%
Effective in $0.0372Effective out $0.4999
Token share
1.7%
Effective in $0.0374Effective out $0.1791
Token share
0.1%
Effective in $0.0376Effective out $0.4996
Token share
0.4%
Effective in $0.0384Effective out $0.3493
Token share
6.1%
Effective in $0.0393Effective out $0.3990
Token share
0.5%
Effective in $0.0404Effective out $0.4485
Token share
0.1%
Effective in $0.0412Effective out $0.1832
Token share
2.6%
Effective in $0.0413Effective out $0.3492
Token share
1.2%
Effective in $0.0422Effective out $0.4993
Token share
4.0%
Effective in $0.0423Effective out $0.4996
Token share
0.3%
Effective in $0.0431Effective out $0.4997
Token share
2.7%
Effective in $0.0440Effective out $0.4996
Token share
0.6%
Effective in $0.0447Effective out $0.4995
Token share
12.5%
Effective in $0.0455Effective out $0.4996
Token share
0.9%
Effective in $0.0456Effective out $0.4995
Token share
9.2%
Effective in $0.0459Effective out $0.2943
Token share
0.3%
Effective in $0.0468Effective out $0.2392
Token share
1.8%
Effective in $0.0471Effective out $0.2991
Token share
0.7%
Effective in $0.0481Effective out $0.3744
Token share
3.4%
Effective in $0.0482Effective out $0.4995
Token share
8.0%
Effective in $0.0540Effective out $0.2959
Token share
3.4%
Effective in $0.0543Effective out $0.4995
Token share
5.5%
Effective in $0.0555Effective out $0.4995
Token share
0.8%
Effective in $0.0564Effective out $0.4995
Token share
0.9%
Effective in $0.0587Effective out $0.2498
Token share
0.1%
Effective in $0.0638Effective out $0.4689
Token share
1.0%
Effective in $0.0640Effective out $0.4998
Token share
5.9%
Effective in $0.0642Effective out $0.2393
Token share
0.4%
Effective in $0.0658Effective out $0.4997
Token share
2.1%
Effective in $0.0683Effective out $0.4994
Token share
0.6%
Effective in $0.0704Effective out $0.1450
Token share
0.4%
Effective in $0.0874Effective out $0.6247
FastToken share
0.1%
Effective in $0.0893Effective out $0.4995
Token share
0.3%
Effective in $0.1025Effective out $0.7496
Token share
1.1%
Effective in $0.1143Effective out $0.6243
Token share
0.0%
Effective in $0.1472Effective out $0.6238
Token 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

169tok/s

P50, best across providers

Latency

0.25s

P50, best provider

Reasoning effortLatency / throughput

AutoExacto benchmarks

GPQA DiamondTAU-BenchDarkbloom92.5%--inference.net88.1%78.0%Z.ai88.2%77.4%DigitalOcean87.8%76.6%Baseten82.2%--inference.net (US)87.2%75.2%Baseten82.7%75.5%

+36 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)

100.00%

Availability (3d)

99.81%

Availability over the last 3 days

Last 72 hours

Availability 99.81%

3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability

99.71%

Without Routing

97.98%

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 Flash (Artificial Analysis, Design Arena and Vals AI)
Source	Benchmark	Score
Artificial Analysis	GLM-5.3-Flash Intelligence Index	27.8
Artificial Analysis	GLM-5.3-Flash Coding Index	71.5
Artificial Analysis	GLM-5.3-Flash Agentic Index	50.9
Artificial Analysis	GLM-5.3-Flash GPQA Diamond	91.2%
Artificial Analysis	GLM-5.3-Flash HLE	39.9%
Artificial Analysis	GLM-5.3-Flash AA-LCR	80.0%
Artificial Analysis	GLM-5.3-Flash τ-Bench Banking	47.2%
Artificial Analysis	GLM-5.3-Flash GDPval-AA	57.4%
Artificial Analysis	GLM-5.3-Flash CritPt	15.4%
Artificial Analysis	GLM-5.3-Flash SciCode	51.6%
Artificial Analysis	GLM-5.3-Flash Terminal-Bench 4.0	32.8%
Artificial Analysis	GLM-5.3-Flash Terminal-Bench 2.1	84.3%
Artificial Analysis	GLM-5.3-Flash AA-Omniscience Accuracy	28.2%
Artificial Analysis	GLM-5.3-Flash AA-Omniscience Non-Hallucination Rate	61.7%
Design Arena	GLM-5.3-Flash Models Arena 3D Elo	1293
Design Arena	GLM-5.3-Flash Models Arena Asciiart Elo	1261
Design Arena	GLM-5.3-Flash Models Arena Code Categories Elo	1267
Design Arena	GLM-5.3-Flash Models Arena Data Visualization Elo	1257
Design Arena	GLM-5.3-Flash Models Arena Game Development Elo	1266
Design Arena	GLM-5.3-Flash Models Arena SVG Elo	1271
Design Arena	GLM-5.3-Flash Models Arena UI Component Elo	1296
Design Arena	GLM-5.3-Flash Models Arena Website Elo	1257
Vals AI	GLM 5.3 Flash Access to Justice Benchmark	71.1%
Vals AI	GLM 5.3 Flash Code Migration v1.1	51.6%
Vals AI	GLM 5.3 Flash CyberBench v1.1	67.9%
Vals AI	GLM 5.3 Flash CyberOffense	18.3%
Vals AI	GLM 5.3 Flash EMB v1.1	66.3%
Vals AI	GLM 5.3 Flash Finance Agent v2.1	60.6%
Vals AI	GLM 5.3 Flash Vals Finance Index	55.8%
Vals AI	GLM 5.3 Flash GPQA Diamond	86.4%
Vals AI	GLM 5.3 Flash HLAB-Vals-1.1	10.4%
Vals AI	GLM 5.3 Flash IOI	52.5%
Vals AI	GLM 5.3 Flash LiveCodeBench	80.5%
Vals AI	GLM 5.3 Flash LegalBench	83.9%
Vals AI	GLM 5.3 Flash Vals Legal Index	71.1%
Vals AI	GLM 5.3 Flash Legal Research Bench	45.2%
Vals AI	GLM 5.3 Flash MedScribe	88.9%
Vals AI	GLM 5.3 Flash MMLU Pro	86.1%
Vals AI	GLM 5.3 Flash MMMU Pro	86.0%
Vals AI	GLM 5.3 Flash ProgramBench	0.0%
Vals AI	GLM 5.3 Flash ProofBench v1.1	21.0%
Vals AI	GLM 5.3 Flash SAGE	89.3%
Vals AI	GLM 5.3 Flash SkillsBench	40.2%
Vals AI	GLM 5.3 Flash SRE Bench	0.8%
Vals AI	GLM 5.3 Flash SWE-bench	92.0%
Vals AI	GLM 5.3 Flash Tax Agent Bench	31.6%
Vals AI	GLM 5.3 Flash TaxEval v2	75.6%
Vals AI	GLM 5.3 Flash Terminal-Bench 4.0	37.4%
Vals AI	GLM 5.3 Flash Terminal-Bench-Science	2.9%
Vals AI	GLM 5.3 Flash Vals Index	50.9%
Vals AI	GLM 5.3 Flash Vibe Code Bench 1-100	16.0%
Vals AI	GLM 5.3 Flash Vibe Code Bench v1.1	30.8%

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.

6.83Ttokens

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.

3.5Ttokens

Portkey AI

Control panel for AI apps

3.37Ttokens

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

1.51Ttokens

Lemonade

The AI tool for Roblox games.

1.12Ttokens

Rest of OpenRouter

413B

Top 5 Apps

161B

Z.ai: GLM Flash versions

Available through EU in-region routing

Z.ai: GLM 5.3 Flash 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

Prices in Europe

Inceptron: $0.175/M tokens input, $0.47/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 (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

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.

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$0.322 / $0.989

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

GLM 4.5 Air

GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications. Like GLM-4.5, it adopts the Mixture-of-Experts (MoE) architecture but with a more compact parameter size. GLM-4.5-Air also supports hybrid inference modes, offering a "thinking mode" for advanced reasoning and tool use, and a "non-thinking mode" for real-time interaction. Users can control the reasoning behaviour with the reasoning enabled boolean. Learn more in our docs

Text131K context$0.13 / $0.85

Z.ai: GLM 5.3 Flash

Providers