How much does GLM 5.2 cost?

GLM 5.2 costs $0.0066/M input tokens and $7.983/M output tokens, with separate rates for Cache Read at $0.0066/M tokens.

What is the context length of GLM 5.2?

GLM 5.2 has a 1,048,576 token context window. It supports up to 131,072 completion tokens.

Does GLM 5.2 support tool calling and structured outputs?

Yes. GLM 5.2 accepts tools for function calling. It also supports structured outputs via a JSON schema in response_format.

Which providers serve GLM 5.2?

GLM 5.2 is served by 24 providers on OpenRouter: Relace, Wafer, Baidu Qianfan (fp8), Cloudflare, StreamLake, DeepInfra, Ambient, CoreWeave and 16 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 5.2 released?

GLM 5.2 was released on June 16, 2026.

Z.ai: GLM 5.2

z-ai/glm-5.2

Model weights

Compare

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.

Modalities

In / out price

$0.0066 / $7.983per 1M

Context

1.0M

Released

Jun 16, 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


	$0.0066	$7.9833	$0.0066	0.77s	92 tok/s	99.71%
	$0.007	$6.80	$0.006	0.41s	104 tok/s	100.00%
87% off	$1.40$0.189	$4.40$0.594	$0.26$0.0351	1.23s	57 tok/s	100.00%
	$0.19	$8.00	$0.18	0.48s	99 tok/s	100.00%
	$0.19	$8.00	$0.19	0.92s	93 tok/s	100.00%
80% off	$1.40$0.28	$4.40$0.88	$0.26$0.052	1.49s	50 tok/s	100.00%
25% off	$0.75$0.5625	$2.40$1.80	$0.14$0.105	0.93s	49 tok/s	99.50%
	$0.60	$2.00	$0.15	0.86s	61 tok/s	86.15%
	$0.62	$2.42	$0.14	0.59s	127 tok/s	99.34%
54% off	$1.40$0.6496	$4.40$2.042	$0.26$0.1206	1.85s	83 tok/s	99.97%
50% off	$1.302$0.651	$4.092$2.046	$0.26$0.13	1.08s	72 tok/s	99.95%
	$0.694	$2.136	$0.234	0.63s	54 tok/s	99.81%
	$0.70	$2.20	$0.105	0.64s	86 tok/s	99.55%
33% off	$1.40$0.938	$4.40$2.948	$0.26$0.1742	1.28s	50 tok/s	99.06%
	$1.12	$3.52	$0.224	1.07s	54 tok/s	100.00%
	$1.40	$4.40	$0.14	1.00s	84 tok/s	99.49%
	$1.40	$4.40	$0.14	1.88s	85 tok/s	99.62%
	$1.40	$4.40	$0.26	0.64s	92 tok/s	100.00%
	$1.40	$4.40	$0.26	0.34s	137 tok/s	99.76%
	$1.40	$4.40	$0.14	2.85s	46 tok/s	98.92%
	$1.40	$4.40	$0.26	2.01s	86 tok/s	99.83%
	$1.40	$4.40	$0.26	1.80s	34 tok/s	99.15%
	$1.40	$4.40	$0.26	0.87s	78 tok/s	98.16%
	$1.40	$4.40	$0.26	0.46s	95 tok/s	99.26%
	$1.40	$4.40	$0.26	2.16s	40 tok/s	100.00%
	$1.54	$4.84	$0.154	0.71s	139 tok/s	99.40%
Fast	$2.10	$6.60	$0.21	0.37s	183 tok/s	99.09%
Fast	$2.10	$6.60	$0.21	0.38s	121 tok/s	99.05%
Fast	$2.25	$7.88	$0.56	0.88s	79 tok/s	100.00%
Fast	$2.31	$7.26	$0.462	1.50s	103 tok/s	94.42%
	$0.966	$3.036	$0.1932	1.12s	70 tok/s	97.10%
	$1.40	$4.40	$0.14	5.98s	18 tok/s	85.90%
Not used in Standard routing:Why these endpoints are not used
Flex25% off	$0.60$0.45	$1.92$1.44	$0.112$0.084	2.01s	49 tok/s	100.00%

Input $0.0066Output $7.9833
92 tok/s99.71% uptime
Input $0.007Output $6.80
104 tok/s100.00% uptime
Input $0.189Output $0.594
87% off
57 tok/s100.00% uptime
Input $0.19Output $8.00
99 tok/s100.00% uptime
Input $0.19Output $8.00
93 tok/s100.00% uptime
Input $0.28Output $0.88
80% off
50 tok/s100.00% uptime
Input $0.5625Output $1.80
25% off
49 tok/s99.50% uptime
Input $0.60Output $2.00
61 tok/s86.15% uptime
Input $0.62Output $2.42
127 tok/s99.34% uptime
Input $0.6496Output $2.042
54% off
83 tok/s99.97% uptime
Input $0.651Output $2.046
50% off
72 tok/s99.95% uptime
Input $0.694Output $2.136
54 tok/s99.81% uptime
Input $0.70Output $2.20
86 tok/s99.55% uptime
Input $0.938Output $2.948
33% off
50 tok/s99.06% uptime
Input $1.12Output $3.52
54 tok/s100.00% uptime
Input $1.40Output $4.40
84 tok/s99.49% uptime
Input $1.40Output $4.40
85 tok/s99.62% uptime
Input $1.40Output $4.40
92 tok/s100.00% uptime
Input $1.40Output $4.40
137 tok/s99.76% uptime
Input $1.40Output $4.40
46 tok/s98.92% uptime
Input $1.40Output $4.40
86 tok/s99.83% uptime
Input $1.40Output $4.40
34 tok/s99.15% uptime
Input $1.40Output $4.40
78 tok/s98.16% uptime
Input $1.40Output $4.40
95 tok/s99.26% uptime
Input $1.40Output $4.40
40 tok/s100.00% uptime
Input $1.54Output $4.84
139 tok/s99.40% uptime
Input $2.10Output $6.60
Fast
183 tok/s99.09% uptime
Input $2.10Output $6.60
Fast
121 tok/s99.05% uptime
Input $2.25Output $7.88
Fast
79 tok/s100.00% uptime
Input $2.31Output $7.26
Fast
103 tok/s94.42% uptime
Input $0.966Output $3.036
70 tok/s97.10% uptime
Input $1.40Output $4.40
18 tok/s85.90% uptime
Not used in Standard routing:Why these endpoints are not used
Input $0.45Output $1.44
Flex
1 more label
49 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

$0.2572/M tokens

Output

$4.013/M tokens

GLM 5.2 — Price history

Price history

No effective price data for this selection

		$0.00616	$6.800	83.3%	15.7%
		$0.00659	$7.983	80.4%	5.1%
		$0.07992	$0.615	72.6%	3.3%
		$0.16029	$1.553	84.1%	14.9%
		$0.18141	$8.000	85.8%	5.5%
		$0.18998	$8.000	73.0%	0.8%
		$0.21869	$2.200	80.9%	0.4%
		$0.22736	$2.048	80.3%	1.4%
		$0.22766	$2.114	81.9%	2.0%
		$0.28228	$2.419	70.4%	20.4%
		$0.29187	$3.036	87.2%	0.5%
		$0.29291	$1.954	80.9%	1.9%
		$0.29575	$1.805	59.0%	1.9%
		$0.34438	$4.400	83.8%	1.1%
		$0.35598	$2.000	54.2%	0.3%
		$0.38758	$3.519	81.7%	0.4%
		$0.41427	$4.399	86.5%	10.9%
		$0.42911	$4.399	85.2%	1.7%
		$0.46673	$4.839	77.4%	1.7%
		$0.49051	$2.947	58.6%	0.1%
		$0.52267	$4.400	77.0%	0.6%
		$0.52870	$4.399	69.1%	0.3%
	Fast	$0.53852	$7.260	95.9%	1.8%
		$0.55733	$4.399	73.9%	0.1%
		$0.59099	$4.399	71.0%	0.7%
		$0.59449	$4.399	70.7%	0.6%
		$0.76448	$4.399	50.4%	1.2%
		$0.84350	$4.400	48.8%	2.4%
	Fast	$0.98540	$6.600	59.0%	0.6%
	Fast	$1.01606	$6.600	57.3%	0.8%
	Fast	$1.23174	$7.879	60.2%	0.1%
		$0.82491	$4.399	45.6%	1.0%
Not used in Standard routing:Why these endpoints are not used
	Flex	$0.26939	$1.439	49.3%	0.0%

Effective in $0.00616Effective out $6.800
Token share
15.7%
Effective in $0.00659Effective out $7.983
Token share
5.1%
Effective in $0.07992Effective out $0.615
Token share
3.3%
Effective in $0.16029Effective out $1.553
Token share
14.9%
Effective in $0.18141Effective out $8.000
Token share
5.5%
Effective in $0.18998Effective out $8.000
Token share
0.8%
Effective in $0.21869Effective out $2.200
Token share
0.4%
Effective in $0.22736Effective out $2.048
Token share
1.4%
Effective in $0.22766Effective out $2.114
Token share
2.0%
Effective in $0.28228Effective out $2.419
Token share
20.4%
Effective in $0.29187Effective out $3.036
Token share
0.5%
Effective in $0.29291Effective out $1.954
Token share
1.9%
Effective in $0.29575Effective out $1.805
Token share
1.9%
Effective in $0.34438Effective out $4.400
Token share
1.1%
Effective in $0.35598Effective out $2.000
Token share
0.3%
Effective in $0.38758Effective out $3.519
Token share
0.4%
Effective in $0.41427Effective out $4.399
Token share
10.9%
Effective in $0.42911Effective out $4.399
Token share
1.7%
Effective in $0.46673Effective out $4.839
Token share
1.7%
Effective in $0.49051Effective out $2.947
Token share
0.1%
Effective in $0.52267Effective out $4.400
Token share
0.6%
Effective in $0.52870Effective out $4.399
Token share
0.3%
Effective in $0.53852Effective out $7.260
FastToken share
1.8%
Effective in $0.55733Effective out $4.399
Token share
0.1%
Effective in $0.59099Effective out $4.399
Token share
0.7%
Effective in $0.59449Effective out $4.399
Token share
0.6%
Effective in $0.76448Effective out $4.399
Token share
1.2%
Effective in $0.84350Effective out $4.400
Token share
2.4%
Effective in $0.98540Effective out $6.600
FastToken share
0.6%
Effective in $1.01606Effective out $6.600
FastToken share
0.8%
Effective in $1.23174Effective out $7.879
FastToken share
0.1%
Effective in $0.82491Effective out $4.399
Token share
1.0%
Not used in Standard routing:Why these endpoints are not used
Effective in $0.26939Effective out $1.439
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

183tok/s

P50, best across providers

Latency

0.34s

P50, best provider

Reasoning effortLatency / throughput

AutoExacto benchmarks

GPQA DiamondTAU-BenchDigitalOcean90.5%75.2%Morph85.3%77.2%Wafer (US)89.6%71.6%DeepInfra91.0%68.4%Alibaba Cloud Int. (US)86.8%72.4%Alibaba Cloud Int.87.6%71.4%Wafer88.7%69.8%Alibaba Cloud Int. (Fast)84.0%69.1%

+22 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

99.88%

Without Routing

97.05%

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 5.2 (Artificial Analysis, Design Arena and Vals AI)
Source	Benchmark	Score
Artificial Analysis	GLM-5.2 (Non-reasoning) Coding Index	46.5
Artificial Analysis	GLM-5.2 (Non-reasoning) GPQA Diamond	68.6%
Artificial Analysis	GLM-5.2 (Non-reasoning) HLE	9.8%
Artificial Analysis	GLM-5.2 (Non-reasoning) AA-LCR	42.3%
Artificial Analysis	GLM-5.2 (Non-reasoning) τ-Bench Banking	16.7%
Artificial Analysis	GLM-5.2 (Non-reasoning) GDPval-AA	37.6%
Artificial Analysis	GLM-5.2 (Non-reasoning) CritPt	3.1%
Artificial Analysis	GLM-5.2 (Non-reasoning) Terminal-Bench 2.1	51.7%
Artificial Analysis	GLM-5.2 (Max) Coding Index	68.8
Artificial Analysis	GLM-5.2 (Max) Agentic Index	38.4
Artificial Analysis	GLM-5.2 (Max) GPQA Diamond	89.5%
Artificial Analysis	GLM-5.2 (Max) HLE	41.1%
Artificial Analysis	GLM-5.2 (Max) IFBench	73.3%
Artificial Analysis	GLM-5.2 (Max) τ²-Bench Telecom	99.1%
Artificial Analysis	GLM-5.2 (Max) AA-LCR	78.3%
Artificial Analysis	GLM-5.2 (Max) τ-Bench Banking	34.6%
Artificial Analysis	GLM-5.2 (Max) GDPval-AA	44.1%
Artificial Analysis	GLM-5.2 (Max) CritPt	20.9%
Artificial Analysis	GLM-5.2 (Max) SciCode	51.2%
Artificial Analysis	GLM-5.2 (Max) Terminal-Bench Hard	50.8%
Artificial Analysis	GLM-5.2 (Max) Terminal-Bench 4.0	1.0%
Artificial Analysis	GLM-5.2 (Max) Terminal-Bench 2.1	77.9%
Artificial Analysis	GLM-5.2 (Max) AA-Omniscience Accuracy	21.1%
Artificial Analysis	GLM-5.2 (Max) AA-Omniscience Non-Hallucination Rate	74.1%
Design Arena	GLM 5.2 Agents Arena Agenticgamedev Elo	1158
Design Arena	GLM 5.2 Agents Arena Androidnative Elo	1169
Design Arena	GLM 5.2 Agents Arena Blender3d Elo	983
Design Arena	GLM 5.2 Agents Arena Full Stack Elo	1219
Design Arena	GLM 5.2 Agents Arena Godotgamedev Elo	1142
Design Arena	GLM 5.2 Agents Arena Htmlslides Elo	1068
Design Arena	GLM 5.2 Agents Arena Mobile Apps Elo	1155
Design Arena	GLM 5.2 Agents Arena Pdf Elo	1243
Design Arena	GLM 5.2 Agents Arena Python-Pptxslides Elo	1157
Design Arena	GLM 5.2 Agents Arena Spreadsheet Elo	1081
Design Arena	GLM 5.2 Agents Arena Webapps Elo	1200
Design Arena	GLM 5.2 Models Arena 3D Elo	1265
Design Arena	GLM 5.2 Models Arena Asciiart Elo	1186
Design Arena	GLM 5.2 Models Arena Code Categories Elo	1276
Design Arena	GLM 5.2 Models Arena Data Visualization Elo	1283
Design Arena	GLM 5.2 Models Arena Game Development Elo	1256
Design Arena	GLM 5.2 Models Arena SVG Elo	1197
Design Arena	GLM 5.2 Models Arena UI Component Elo	1287
Design Arena	GLM 5.2 Models Arena Website Elo	1277
Vals AI	GLM 5.2 Code Migration	37.9%
Vals AI	GLM 5.2 CorpFin v2	66.1%
Vals AI	GLM 5.2 EMB	61.5%
Vals AI	GLM 5.2 Finance Agent (v2)	49.7%
Vals AI	GLM 5.2 GPQA Diamond	85.6%
Vals AI	GLM 5.2 Harvey's Legal Agent Benchmark v1	7.1%
Vals AI	GLM 5.2 LiveCodeBench	69.5%
Vals AI	GLM 5.2 LegalBench	84.1%
Vals AI	GLM 5.2 Legal Research Bench	31.3%
Vals AI	GLM 5.2 MedCode	40.8%
Vals AI	GLM 5.2 MedScribe	83.5%
Vals AI	GLM 5.2 MMLU Pro	86.7%
Vals AI	GLM 5.2 ProgramBench	0.5%
Vals AI	GLM 5.2 ProofBench v1	35.0%
Vals AI	GLM 5.2 SkillsBench	45.1%
Vals AI	GLM 5.2 SRE Bench	0.0%
Vals AI	GLM 5.2 SWE-bench	82.8%
Vals AI	GLM 5.2 TaxEval v2	73.3%
Vals AI	GLM 5.2 Terminal-Bench 2.1	67.8%
Vals AI	GLM 5.2 Vals Index	53.1%
Vals AI	GLM 5.2 Vibe Code Bench v1.1	64.0%

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.

HighLevel

new

1.4Ttokens

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.

213Btokens

Janitor AI

Janitor AI is a chatbot platform where users create and chat with custom AI characters for interactive roleplay, storytelling, and immersive fiction.

57.6Btokens

OpenClaw

OpenClaw is an open-source AI agent that connects to your messaging apps and takes real actions on your behalf, from running commands and browsing the web to managing files and sending emails.

55.3Btokens

ISEKAI ZERO

AI adventures. Travel with your favorite characters

43.5Btokens

Rest of OpenRouter

71.2B

Top 5 Apps

59.8B

Available through EU in-region routing

Z.ai: GLM 5.2 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: $1.40/M tokens input, $4.40/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

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$0.45 / $2

GLM 5.2

Text1.0M context$0.0066 / $7.983

GLM 5.2 (batch)

Text1.0M context$0.347 / $1.068

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

Z.ai: GLM 5.2

Providers