Qu’est-ce que 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.

Combien coûte GLM 5.2 ?

GLM 5.2 coûte 0,006 $US/M de jetons d’entrée et 6,80 $US/M de jetons de sortie, avec des tarifs distincts pour Cache Read à 0,005 $US/M tokens.

Quelle est la longueur de contexte de GLM 5.2 ?

GLM 5.2 dispose d’une fenêtre de contexte de 1 048 576 jetons. Il prend en charge jusqu’à 1 048 576 jetons de complétion.

GLM 5.2 prend-il en charge les appels d’outils et les sorties structurées ?

Oui. GLM 5.2 accepte tools pour l’appel de fonctions. Il prend également en charge les sorties structurées via un schéma JSON dans response_format.

Quels fournisseurs proposent GLM 5.2 ?

GLM 5.2 est proposé par 24 fournisseurs sur OpenRouter : Wafer, Relace, Morph, Cloudflare, DeepInfra, Ambient, StreamLake, CoreWeave et 16 de plus. Les requêtes sont acheminées vers le meilleur fournisseur disponible, avec un basculement automatique vers les autres, et vous pouvez fixer ou exclure des fournisseurs avec le routage des fournisseurs.

Quand GLM 5.2 a-t-il été publié ?

GLM 5.2 est sorti le 16 juin 2026.

GLM 5.2 - Tarifs de l’API et évaluations comparatives

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

Résumé des scores aux tests de performance pour Z.ai: GLM 5.2 (Artificial Analysis, Design Arena et Vals AI)
Source	Test de performance	Score
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%


	0,006 $US	6,80 $US	0,005 $US	0,35s	127 tps	99,59 %
	0,0065 $US	7,9057 $US	0,0065 $US	1,24s	104 tps	100,00 %
	0,087 $US	1,40 $US	0,069 $US	1,05s	26 tps	100,00 %
	0,19 $US	8,00 $US	0,18 $US	0,46s	114 tps	99,46 %
	0,19 $US	8,00 $US	0,19 $US	0,84s	63 tps	99,95 %
25% off	0,75 $US0,5625 $US	2,40 $US1,80 $US	0,14 $US0,105 $US	1,53s	52 tps	99,74 %
	0,60 $US	2,00 $US	0,15 $US	0,61s	97 tps	94,64 %
56% off	1,40 $US0,6131 $US	4,40 $US1,927 $US	0,26 $US0,1139 $US	1,15s	45 tps	100,00 %
	0,62 $US	2,42 $US	0,14 $US	0,49s	185 tps	99,91 %
54% off	1,40 $US0,6496 $US	4,40 $US2,042 $US	0,26 $US0,1206 $US	1,98s	57 tps	99,84 %
	0,70 $US	2,20 $US	0,105 $US	0,79s	80 tps	99,80 %
50% off	1,40 $US0,70 $US	4,40 $US2,20 $US	0,26 $US0,13 $US	0,94s	94 tps	100,00 %
33% off	1,40 $US0,938 $US	4,40 $US2,948 $US	0,26 $US0,1742 $US	1,00s	56 tps	100,00 %
	0,966 $US	3,036 $US	0,1932 $US	0,96s	67 tps	99,50 %
	1,12 $US	3,52 $US	0,224 $US	1,03s	53 tps	94,92 %
	1,40 $US	4,40 $US	0,14 $US	4,19s	68 tps	65,48 %
	1,40 $US	4,40 $US	0,14 $US	1,33s	71 tps	99,65 %
	1,40 $US	4,40 $US	0,14 $US	2,60s	55 tps	98,84 %
	1,40 $US	4,40 $US	0,19 $US	0,31s	117 tps	99,56 %
	1,40 $US	4,40 $US	0,26 $US	0,41s	192 tps	99,61 %
	1,40 $US	4,40 $US	0,26 $US	1,03s	46 tps	100,00 %
	1,40 $US	4,40 $US	0,14 $US	1,26s	46 tps	98,63 %
	1,40 $US	4,40 $US	0,26 $US	1,93s	70 tps	99,41 %
	1,40 $US	4,40 $US	0,26 $US	1,85s	26 tps	100,00 %
	1,40 $US	4,40 $US	0,26 $US	0,51s	188 tps	99,93 %
	1,40 $US	4,40 $US	0,26 $US	0,37s	148 tps	99,68 %
	1,40 $US	4,40 $US	0,26 $US	1,00s	61 tps	100,00 %
Fast	2,10 $US	6,60 $US	0,21 $US	0,36s	173 tps	99,64 %
Fast	2,10 $US	6,60 $US	0,21 $US	0,37s	138 tps	99,62 %
Fast	2,25 $US	7,88 $US	0,56 $US	0,87s	86 tps	99,60 %
Fast	2,31 $US	7,26 $US	0,462 $US	0,85s	93 tps	100,00 %
Non utilisé pour le routage Standard :Pourquoi ces points de terminaison ne sont pas utilisés
Flex25% off	0,60 $US0,45 $US	1,92 $US1,44 $US	0,112 $US0,084 $US	3,30s	39 tps	100,00 %
	1,54 $US	4,84 $US	0,154 $US	--	--	100,00 %

Résumé des scores aux tests de performance pour Z.ai: GLM 5.2 (Artificial Analysis, Design Arena et Vals AI)
Source	Test de performance	Score
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).

TexteContexte de 1,0M0,37 $US / 1,25 $US

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.

TexteContexte de 1M2,80 $US / 8,80 $US

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.

TexteContexte de 1,0M0,37 $US / 1,25 $US

GLM Flash Latest

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

TexteContexte de 1,0M

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.

TexteContexte de 1,0M0,0285 $US / 0,0923 $US

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.

TexteContexte de 1,0M0,05 $US / 0,18 $US

GLM Latest

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

TexteContexte de 1,0M

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.

TexteContexte de 1,0M0,0699 $US / 1,40 $US

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.

TexteContexte de 1,0M0,45 $US / 2 $US

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.

TexteContexte de 205K0,90 $US / 2,90 $US

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“.

TexteContexte de 203K1,20 $US / 4 $US

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.

TexteContexte de 203K1,20 $US / 4 $US

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.

TexteContexte de 205K0,60 $US / 1,92 $US

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.

TexteContexte de 200K0,0605 $US / 0,40 $US

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.

TexteContexte de 205K0,40 $US / 1,75 $US

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.

TexteContexte de 131K0,30 $US / 0,90 $US

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.

TexteContexte de 205K0,43 $US / 1,75 $US

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

TexteContexte de 66K0,60 $US / 1,80 $US

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

TexteContexte de 131K0,60 $US / 2,20 $US

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

TexteContexte de 131K0,13 $US / 0,85 $US

Z.ai: GLM 5.2

Z.ai: GLM 5.2

Fournisseurs

Tarification

Performances

Disponibilité

Évaluations comparatives

Applications

Activité

API

Disponible via le routage au sein de la région UE

Explorer d’autres modèles

Fournisseurs

Tarification

Performances

Disponibilité

Disponibilité au cours des 3 derniers jours

Disponibilité au cours des dernières 24 heures

Évaluations comparatives

Applications

Activité

API

Disponible via le routage au sein de la région UE

Questions fréquentes

Explorer d’autres modèles

Autres modèles de Z.ai

Disponibilité au cours des 3 derniers jours

Disponibilité au cours des dernières 24 heures

Questions fréquentes

Autres modèles de Z.ai