GLM 5.2 とは何ですか？

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.

GLM 5.2 の料金はいくらですか？

GLM 5.2 の料金は $0.006/M 入力トークンと $6.80/M 出力トークン、Cache Read：$0.005/M tokens には別料金が適用されますです。

GLM 5.2 のコンテキスト長はどれくらいですか？

GLM 5.2 のコンテキストウィンドウは 1,048,576 トークンです。最大 1,048,576 トークンの補完に対応しています。

GLM 5.2 はツール呼び出しと構造化出力に対応していますか？

はい。GLM 5.2 は関数呼び出し用の tools を受け付けます。 response_format の JSON スキーマによる構造化出力にも対応しています。

GLM 5.2 を提供しているプロバイダーはどこですか？

GLM 5.2 は OpenRouter 上で 24 社のプロバイダー（Wafer, Relace, Morph, Cloudflare, DeepInfra, Ambient, StreamLake, CoreWeave と他 16 件）によって提供されています。リクエストは利用可能な最適のプロバイダーにルーティングされ、他のプロバイダーへの自動フェイルオーバーに対応し、プロバイダールーティングでプロバイダーを固定または除外できます。

GLM 5.2 はいつリリースされましたか？

GLM 5.2 は 2026年6月16日にリリースされました。

GLM 5.2 - API 料金とベンチマーク

Name: Z.ai: GLM 5.2
Author: Z.ai

ベンチマークスコアの概要： Z.ai: GLM 5.2 （Artificial Analysis、Design Arena、Vals AI）
出典	ベンチマーク	スコア
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 (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%
Design Arena	GLM 5.2 Agents Arena Agenticgamedev Elo	1155
Design Arena	GLM 5.2 Agents Arena Androidnative Elo	1177
Design Arena	GLM 5.2 Agents Arena Blender3d Elo	983
Design Arena	GLM 5.2 Agents Arena Full Stack Elo	1241
Design Arena	GLM 5.2 Agents Arena Godotgamedev Elo	1142
Design Arena	GLM 5.2 Agents Arena Htmlslides Elo	1071
Design Arena	GLM 5.2 Agents Arena Mobile Apps Elo	1160
Design Arena	GLM 5.2 Agents Arena Pdf Elo	1213
Design Arena	GLM 5.2 Agents Arena Python-Pptxslides Elo	1148
Design Arena	GLM 5.2 Agents Arena Webapps Elo	1207
Design Arena	GLM 5.2 Models Arena 3D Elo	1284
Design Arena	GLM 5.2 Models Arena Asciiart Elo	1188
Design Arena	GLM 5.2 Models Arena Code Categories Elo	1285
Design Arena	GLM 5.2 Models Arena Data Visualization Elo	1286
Design Arena	GLM 5.2 Models Arena Game Development Elo	1266
Design Arena	GLM 5.2 Models Arena SVG Elo	1207
Design Arena	GLM 5.2 Models Arena UI Component Elo	1290
Design Arena	GLM 5.2 Models Arena Website Elo	1283
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%


	$0.62	$2.42	$0.14	0.58s	105 tps	99.90%
50% off	$1.40$0.70	$4.40$2.20	$0.26$0.13	1.02s	80 tps	100.00%
	$0.006	$6.80	$0.005	0.47s	82 tps	99.57%
	$0.0065	$7.9057	$0.0065	1.34s	72 tps	100.00%
	$0.19	$8.00	$0.19	1.13s	87 tps	99.95%
	$1.40	$4.40	$0.26	0.49s	112 tps	99.59%
	$1.40	$4.40	$0.14	1.09s	81 tps	99.63%
56% off	$1.40$0.6131	$4.40$1.927	$0.26$0.1139	1.24s	45 tps	100.00%
54% off	$1.40$0.6496	$4.40$2.042	$0.26$0.1206	2.27s	48 tps	99.83%
33% off	$1.40$0.938	$4.40$2.948	$0.26$0.1742	1.04s	60 tps	100.00%
25% off	$0.75$0.5625	$2.40$1.80	$0.14$0.105	1.44s	45 tps	99.79%
	$1.12	$3.52	$0.224	1.32s	52 tps	94.92%
	$1.40	$4.40	$0.26	2.30s	46 tps	99.41%
Fast	$2.25	$7.88	$0.56	0.77s	72 tps	99.59%
Fast	$2.31	$7.26	$0.462	0.93s	88 tps	100.00%
	$1.40	$4.40	$0.26	2.38s	26 tps	100.00%
	$0.078	$1.40	$0.069	1.36s	20 tps	100.00%
	$0.19	$8.00	$0.18	0.64s	47 tps	99.44%
	$1.40	$4.40	$0.26	7.52s	19 tps	99.93%
	$0.60	$2.00	$0.15	0.80s	66 tps	94.66%
	$0.70	$2.20	$0.105	1.05s	80 tps	99.79%
	$0.966	$3.036	$0.1932	1.01s	72 tps	99.53%
	$1.40	$4.40	$0.26	1.55s	59 tps	100.00%
	$1.40	$4.40	$0.26	1.22s	46 tps	100.00%
	$1.40	$4.40	$0.14	2.11s	59 tps	98.80%
	$1.40	$4.40	$0.14	2.54s	47 tps	98.63%
	$1.40	$4.40	$0.19	2.98s	33 tps	99.54%
	$1.40	$4.40	$0.26	3.48s	45 tps	99.66%
Fast	$2.10	$6.60	$0.21	0.41s	168 tps	99.67%
Fast	$2.10	$6.60	$0.21	0.42s	146 tps	99.60%
	$1.40	$4.40	$0.14	1.76s	35 tps	65.91%
Standard ルーティングでは使用されません：これらのエンドポイントが使用されない理由
Flex25% off	$0.60$0.45	$1.92$1.44	$0.112$0.084	3.09s	34 tps	100.00%
	$1.54	$4.84	$0.154	0.62s	93 tps	100.00%

ベンチマークスコアの概要： Z.ai: GLM 5.2 （Artificial Analysis、Design Arena、Vals AI）
出典	ベンチマーク	スコア
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 (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%
Design Arena	GLM 5.2 Agents Arena Agenticgamedev Elo	1155
Design Arena	GLM 5.2 Agents Arena Androidnative Elo	1177
Design Arena	GLM 5.2 Agents Arena Blender3d Elo	983
Design Arena	GLM 5.2 Agents Arena Full Stack Elo	1241
Design Arena	GLM 5.2 Agents Arena Godotgamedev Elo	1142
Design Arena	GLM 5.2 Agents Arena Htmlslides Elo	1071
Design Arena	GLM 5.2 Agents Arena Mobile Apps Elo	1160
Design Arena	GLM 5.2 Agents Arena Pdf Elo	1213
Design Arena	GLM 5.2 Agents Arena Python-Pptxslides Elo	1148
Design Arena	GLM 5.2 Agents Arena Webapps Elo	1207
Design Arena	GLM 5.2 Models Arena 3D Elo	1284
Design Arena	GLM 5.2 Models Arena Asciiart Elo	1188
Design Arena	GLM 5.2 Models Arena Code Categories Elo	1285
Design Arena	GLM 5.2 Models Arena Data Visualization Elo	1286
Design Arena	GLM 5.2 Models Arena Game Development Elo	1266
Design Arena	GLM 5.2 Models Arena SVG Elo	1207
Design Arena	GLM 5.2 Models Arena UI Component Elo	1290
Design Arena	GLM 5.2 Models Arena Website Elo	1283
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%

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).

テキスト1.0M コンテキスト$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.

テキスト1M コンテキスト$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.

テキスト1.0M コンテキスト$0.37 / $1.25

GLM Flash Latest

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

テキスト1.0M コンテキスト

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.

テキスト1.0M コンテキスト$0.0285 / $0.0923

GLM 5.3 Flash (batch)

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.

テキスト1.0M コンテキスト$0.05 / $0.18

GLM Latest

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

テキスト1.0M コンテキスト

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.

テキスト1.0M コンテキスト$0.0699 / $1.40

GLM 5.3 (batch)

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.

テキスト1.0M コンテキスト$0.45 / $2

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.

テキスト205K コンテキスト$0.90 / $2.90

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“.

テキスト203K コンテキスト$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.

テキスト203K コンテキスト$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.

テキスト205K コンテキスト$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.

テキスト200K コンテキスト$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.

テキスト205K コンテキスト$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.

テキスト131K コンテキスト$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.

テキスト205K コンテキスト$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

テキスト66K コンテキスト$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

テキスト131K コンテキスト$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

テキスト131K コンテキスト$0.13 / $0.85

Z.ai: GLM 5.2

Z.ai: GLM 5.2

プロバイダー

料金

パフォーマンス

稼働率

ベンチマーク

アプリ

アクティビティ

API

EU 域内ルーティング経由で利用可能

さらにモデルを探す

プロバイダー

料金

パフォーマンス

稼働率

過去 3 日間の可用性

過去 24 時間の可用性

ベンチマーク

アプリ

アクティビティ

API

EU 域内ルーティング経由で利用可能

よくある質問

さらにモデルを探す

その他のモデル：提供元 Z.ai

過去 3 日間の可用性

過去 24 時間の可用性

よくある質問

その他のモデル：提供元 Z.ai