Saltar al contenido
Alfa
  • Modelos
  • Clasificaciones
  • Ori
Hablar con ventas

Pie de página

OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Producto

  • Chat
  • Clasificaciones
  • Pruebas de rendimiento
  • Aplicaciones
  • Descubrir
  • Modelos
  • Ori
  • Colecciones
  • Proveedores
  • Herramientas
  • Precios
  • Business
  • Enterprise
  • Laboratorio

Empresa

  • Acerca de
  • Blog
  • Clientes
  • Empleo
    Empleo
  • Privacidad
  • Términos del servicio
  • Centro de confianza
  • Soporte
  • Compatible con OR
  • Datos
  • Marca

Desarrollador

  • Documentación
  • Referencia de la API
  • Plataforma para desarrolladores
  • Estado
  • Mapa del sitio para IA

Conectar

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube
Favicon de z-ai

Z.ai: GLM 4.6

z-ai/glm-4.6

Pesos del modelo
Comparar

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.

Modalidades
Precio de entrada / salida
0,43 US$ / 1,75 US$por 1M
Contexto
205K
Publicado
30 sept 2025
Fecha de corte del conocimiento
mar 2025
Comparar
ProveedoresPreciosRendimientoTiempo de actividadPruebas de rendimientoAplicacionesActividadPreguntas frecuentesExplorar

Proveedores

Distintas empresas alojan el mismo modelo. OpenRouter dirige su solicitud a una de ellas según el modo de enrutamiento que elija: Equilibrado (precio + velocidad), Nitro (el más rápido) o Floor (el más barato).

Precios

El precio medio que los clientes pagan realmente por este modelo, junto a los precios que publican los proveedores. El uso de caché y los descuentos hacen que el precio realmente pagado a menudo sea muy inferior al publicado.

Rendimiento

La velocidad de generación indica lo rápido que escribe el modelo (tokens por segundo: cuanto mayor, mejor). La latencia es el tiempo total de ida y vuelta (cuanto menor, mejor). TTFT es el tiempo hasta el primer token: cuánto tarda en aparecer algo en pantalla (cuanto menor, mejor).

Tiempo de actividad

El tiempo de actividad es el porcentaje de los últimos 3 días en que al menos un proveedor respondía a las solicitudes. La disponibilidad es el porcentaje de tiempo en que la inferencia se sirvió correctamente. OpenRouter supervisa continuamente y utiliza el siguiente mejor proveedor cuando uno devuelve un error.

Pruebas de rendimiento

Puntuaciones en evaluaciones estandarizadas y respuestas de este modelo a instrucciones compartidas de las pruebas de referencia. Los porcentajes más altos son mejores, y cada posición indica dónde se sitúa este modelo entre los modelos evaluados en esa fuente.

Resumen de puntuaciones en pruebas de rendimiento de Z.ai: GLM 4.6 (Artificial Analysis, Design Arena y Vals AI)
FuentePrueba de rendimientoPuntuación
Artificial AnalysisGLM-4.6 (Non-reasoning) GPQA Diamond63.2%
Artificial AnalysisGLM-4.6 (Non-reasoning) HLE5.5%
Artificial AnalysisGLM-4.6 (Non-reasoning) IFBench36.7%
Artificial AnalysisGLM-4.6 (Non-reasoning) τ²-Bench Telecom76.9%
Artificial AnalysisGLM-4.6 (Non-reasoning) AA-LCR26.3%
Artificial AnalysisGLM-4.6 (Non-reasoning) CritPt0.0%
Artificial AnalysisGLM-4.6 (Non-reasoning) LiveCodeBench56.1%
Artificial AnalysisGLM-4.6 (Non-reasoning) Terminal-Bench Hard28.8%
Artificial AnalysisGLM-4.6 (Non-reasoning) MMLU-Pro78.4%
Artificial AnalysisGLM-4.6 (Non-reasoning) AIME 202544.3%
Artificial AnalysisGLM-4.6 (Reasoning) Coding Index45,8
Artificial AnalysisGLM-4.6 (Reasoning) GPQA Diamond78.0%
Artificial AnalysisGLM-4.6 (Reasoning) HLE14.5%
Artificial AnalysisGLM-4.6 (Reasoning) IFBench43.4%
Artificial AnalysisGLM-4.6 (Reasoning) τ²-Bench Telecom70.5%
Artificial AnalysisGLM-4.6 (Reasoning) AA-LCR54.0%
Artificial AnalysisGLM-4.6 (Reasoning) τ-Bench Banking13.4%
Artificial AnalysisGLM-4.6 (Reasoning) GDPval-AA13.2%
Artificial AnalysisGLM-4.6 (Reasoning) CritPt1.1%
Artificial AnalysisGLM-4.6 (Reasoning) LiveCodeBench69.5%
Artificial AnalysisGLM-4.6 (Reasoning) Terminal-Bench Hard25.0%
Artificial AnalysisGLM-4.6 (Reasoning) Terminal-Bench 2.149.4%
Artificial AnalysisGLM-4.6 (Reasoning) MMLU-Pro82.9%
Artificial AnalysisGLM-4.6 (Reasoning) AIME 202586.0%
Design ArenaGLM 4.6 Agents Arena Androidnative Elo1080
Design ArenaGLM 4.6 Agents Arena Full Stack Elo1029
Design ArenaGLM 4.6 Agents Arena Godotgamedev Elo1180
Design ArenaGLM 4.6 Agents Arena Mobile Apps Elo1096
Design ArenaGLM 4.6 Models Arena 3D Elo1126
Design ArenaGLM 4.6 Models Arena Code Categories Elo1164
Design ArenaGLM 4.6 Models Arena Data Visualization Elo1161
Design ArenaGLM 4.6 Models Arena Game Development Elo1149
Design ArenaGLM 4.6 Models Arena SVG Elo1105
Design ArenaGLM 4.6 Models Arena UI Component Elo1142
Design ArenaGLM 4.6 Models Arena Website Elo1174
Vals AIGLM 4.6 AIME92.7%
Vals AIGLM 4.6 CorpFin v256.8%
Vals AIGLM 4.6 Finance Agent v1.136.5%
Vals AIGLM 4.6 GPQA Diamond74.5%
Vals AIGLM 4.6 IOI v14.3%
Vals AIGLM 4.6 LiveCodeBench81.0%
Vals AIGLM 4.6 LegalBench79.6%
Vals AIGLM 4.6 MedQA92.2%
Vals AIGLM 4.6 MGSM89.7%
Vals AIGLM 4.6 MMLU Pro82.2%
Vals AIGLM 4.6 TaxEval v266.2%
Vals AIGLM 4.6 Terminal-Bench 2.028.1%
Vals AIGLM 4.6 Vibe Code Bench v1.13.1%

Aplicaciones

Aplicaciones públicas que envían más tráfico a este modelo. Una buena señal de cómo son las cargas de trabajo reales en producción, y una pista sobre los casos de uso para los que este modelo es más adecuado.

Actividad

Volumen de tokens y tráfico de solicitudes a este modelo a lo largo del tiempo.

API

Código listo para usar para llamar a este modelo. La API de OpenRouter es compatible con OpenAI: la mayoría de los SDK funcionan con solo cambiar la URL base. Lo único que cambia entre modelos es el identificador del modelo que aparece a continuación.

Actualmente no está disponible mediante el enrutamiento dentro de la región de la UE. Documentación de enrutamiento dentro de la región

Explorar más modelos

Clasificaciones de modelos de IAClasificación
Latencia / rendimiento
0,43 US$1,75 US$0,08 US$1,97s15 tps
99,70 %
0,50 US$2,00 US$0,10 US$1,46s19 tps
99,92 %
0,55 US$2,20 US$0,11 US$4,70s26 tps
100,00 %
0,60 US$2,20 US$0,11 US$3,90s29 tps
100,00 %
No se utiliza en el enrutamiento Standard:Por qué no se usan estos endpoints
Flex
0,40 US$1,60 US$0,08 US$----
--
Rendimiento
29tok/s

P50, el mejor entre los proveedores

Latencia
1,46s

P50, mejor proveedor

Pruebas de rendimiento de AutoExacto
GPQA DiamondTAU-BenchNovitaAI84,3 %73,6 %Z.ai85,3 %72,5 %auto-routing79,2 %72,4 %DeepInfra78,7 %69,1 %Venice72,2 %69,3 %
Tiempo de actividad (3 d)El modelo estaba accesible. Solicitud enrutada a un proveedor.
100,00 %
Disponibilidad (3 d)El modelo devolvió una inferencia de cualquier proveedor. Los errores y las respuestas vacías cuentan en su contra.
98,50 %

Disponibilidad durante los últimos 3 días

Últimas 72 horas
Disponibilidad 98,50 %
Hace 3 díasHace 2 díasAyerAhora

Disponibilidad en las últimas 24 horas

OpenRouter Availability
98,68 %
Without Routing
97,04 %

Cuando se produce un error en un proveedor ascendente, podemos recuperarnos enrutando la solicitud a otro proveedor que funcione correctamente, si los filtros de su solicitud lo permiten. Puede acceder mediante programación a los datos de tiempo de actividad de cada proveedor a través de la API de endpoints. Obtenga más información sobre nuestras opciones de equilibrio de carga y enrutamiento de proveedores.

1.
Favicon de https://janitorai.com/
Janitor AI
Janitor AI is a chatbot platform where users create and chat with custom AI characters for interactive roleplay, storytelling, and immersive fiction.
12Btókenes
2.
Favicon de https://lorebary.com/
Sophia's LoreBary
Organize and enhance your roleplay creations.
3,85Btókenes
3.
Favicon de https://halluna.ai/
Halluna
nuevo
2,32Btókenes
4.
Favicon de https://nousresearch.com
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.
2,19Btókenes
5.
Favicon de https://sillytavern.app/
SillyTavern
SillyTavern is the LLM frontend for power users, a chat interface that connects to any model and gives deep control through character creation, roleplay, and prompt customization.
2,17Btókenes

Preguntas frecuentes

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.

GLM 4.6 cuesta 0,43 US$/M de tokens de entrada y 1,75 US$/M de tókenes de salida, con tarifas independientes para Cache Read a 0,08 US$/M tokens.

GLM 4.6 tiene una ventana de contexto de 204.800 tókenes. Admite hasta 16.384 tókenes de respuesta.

Sí. GLM 4.6 admite tools y tool_choice para llamadas a funciones. También admite salidas estructuradas mediante un esquema JSON en response_format.

GLM 4.6 está disponible a través de 4 proveedores en OpenRouter: DeepInfra, Venice, NovitaAI y Z.ai. Las solicitudes se enrutan al mejor proveedor disponible, con conmutación automática a los demás en caso de fallo, y puede fijar o excluir proveedores mediante el enrutamiento de proveedores.

GLM 4.6 se lanzó el 30 de septiembre de 2025. Su fecha límite de conocimientos es 31 de marzo de 2025.

Más modelos de 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).

TextoContexto 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.

TextoContexto 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.

TextoContexto de 1,0M0,37 US$ / 1,25 US$
GLM Flash Latest

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

TextoContexto 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.

TextoContexto 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.

TextoContexto de 1,0M0,05 US$ / 0,18 US$
GLM Latest

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

TextoContexto 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.

TextoContexto 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.

TextoContexto de 1,0M0,45 US$ / 2 US$
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.

TextoContexto de 1,0M0,006 US$ / 6,80 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.

TextoContexto 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“.

TextoContexto 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.

TextoContexto 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.

TextoContexto 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.

TextoContexto 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.

TextoContexto 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.

TextoContexto de 131K0,30 US$ / 0,90 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

TextoContexto 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

TextoContexto 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

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

GLM 4.6 cuesta 0,43 US/Mdetokensdeentraday1,75 US/M de tokens de entrada y 1,75 US/Mdetokensdeentraday1,75 US/M de tókenes de salida, con tarifas independientes para Cache Read a 0,08 US$/M tokens.