Z

Zhipu models on UnoRouter

29 models

Browse every Zhipu model available on UnoRouter: pricing, context, and capabilities.

ZZhipu
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...

ReasoningToolsVisionCache
1M$0.37input tokens$1.25output tokens
ZZhipu
glm-5.3-flash

GLM-5.3-Flash is the first natively multimodal model in the GLM-5 series with 320B total parameters and 18B active parameters. It incorporates several architectural improvements over GLM-5.2...

ReasoningToolsVisionCache
1M$0.13input tokens$0.43output tokens
ZZhipu
free
glm-5.3-flash:free

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...

ReasoningToolsVisionCache
1M
ZZhipu
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...

ReasoningToolsCache
1M$0.12input tokens$1.4091% off$0.38output tokens$4.4091% off
ZZhipu
or-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...

ReasoningToolsCache
1M$1.00input tokens$1.4029% off$3.14output tokens$4.4029% off
ZZhipu
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...

ReasoningToolsCache
1M$1.29input tokens$1.408% off$4.04output tokens$4.408% off
ZZhipu
glm-5.1

We are launching GLM-5, targeting complex systems engineering and long-horizon agentic tasks. Scaling is still one of the most important ways to improve the intelligence efficiency of Artificial...

ReasoningToolsCache
200K$0.67input tokens$1.4052% off$2.11output tokens$4.4052% off
ZZhipu
Deprecated
glm-4.7

GLM-4.7 is Zhipu AI's 2026 flagship model, featuring a 355B parameter Mixture-of-Experts (MoE) architecture. Its signature innovation is the "Interleaved Thinking" system, which enables the model to...

ReasoningToolsCache
204.8K$0.64input tokens$2.35output tokens
ZZhipu
Deprecated
glm-4.7-thinking

GLM-4.7 is Zhipu AI's 2026 flagship model, featuring a 355B parameter Mixture-of-Experts (MoE) architecture. Its signature innovation is the "Interleaved Thinking" system, which enables the model to...

ReasoningToolsCache
204.8K$0.64input tokens$2.35output tokens
ZZhipu
free
glm-4.7-flash:free

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...

ReasoningTools
128K
ZZhipu
Deprecated
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...

ReasoningToolsCache
204.8K$1.10input tokens$4.03output tokens
ZZhipu
free
glm-4.5-flash:free

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....

ReasoningToolsCache
131.1K

Currently busy

Every provider for these models has hit its rate limit. They come back automatically once the limits lift.

ZZhipu
Busyfree
glm-5.3-flash-search:free

GLM-5.3-Flash is the first natively multimodal model in the GLM-5 series with 320B total parameters and 18B active parameters. It incorporates several architectural improvements over GLM-5.2...

ReasoningToolsVisionCache
1M
ZZhipu
Busyfree
glm-5.3-flash-think-search:free

GLM-5.3-Flash is the first natively multimodal model in the GLM-5 series with 320B total parameters and 18B active parameters. It incorporates several architectural improvements over GLM-5.2...

ReasoningToolsVisionCache
1M
ZZhipu
Busyfree
glm-5.3-flash-thinking:free

GLM-5.3-Flash is the first natively multimodal model in the GLM-5 series with 320B total parameters and 18B active parameters. It incorporates several architectural improvements over GLM-5.2...

ReasoningToolsVisionCache
1M
ZZhipu
Busyfree
glm-5.3:free

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...

ReasoningToolsCache
1M
ZZhipu
Busyfree
glm-5.2:free

GLM-5.2 is the flagship model for the era of long tasks. It supports truly usable 1M context and has been tested to be capable of handling project-level engineering contexts. Long-term tasks are...

ReasoningToolsCache
1M
ZZhipu
Busyfree
glm-5.1:free

We are launching GLM-5, targeting complex systems engineering and long-horizon agentic tasks. Scaling is still one of the most important ways to improve the intelligence efficiency of Artificial...

ReasoningToolsCache
200K
ZZhipu
BusyDeprecated
glm-5

We are launching GLM-5, targeting complex systems engineering and long-horizon agentic tasks. Scaling is still one of the most important ways to improve the intelligence efficiency of Artificial...

ReasoningToolsCache
204.8K$1.00input tokens$3.20output tokens
ZZhipu
BusyfreeDeprecated
glm-5:free

We are launching GLM-5, targeting complex systems engineering and long-horizon agentic tasks. Scaling is still one of the most important ways to improve the intelligence efficiency of Artificial...

ReasoningToolsCache
204.8K
ZZhipu
Busyfree
glm-5-turbo:free

GLM-5-Turbo is the high-efficiency variant of Zhipu AI's fifth-generation foundation model, designed for rapid reasoning and large-scale autonomous agent orchestration. It integrates the...

ReasoningToolsCache
128K
ZZhipu
BusyfreeDeprecated
glm-4.7:free

GLM-4.7 is Zhipu AI's 2026 flagship model, featuring a 355B parameter Mixture-of-Experts (MoE) architecture. Its signature innovation is the "Interleaved Thinking" system, which enables the model to...

ReasoningToolsCache
204.8K
ZZhipu
Busyfree
glm-4.6v-flash:free

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...

ReasoningToolsVisionCache
128K
ZZhipu
BusyfreeDeprecated
glm-4.6:free

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...

ReasoningToolsCache
204.8K
ZZhipu
Busyfree
glm-4-flash:free

A high-speed, lightweight flagship model from Zhipu AI. As the most cost-effective member of the GLM-4 family, it is deeply optimized for high-concurrency and low-latency scenarios. It maintains a...

ToolsVision
128K
ZZhipu
Busyfree
glm-4.1v-thinking-flash:free
ReasoningToolsVision
65.5K
ZZhipu
Busyfree
glm-4:free

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...

ReasoningCache
24.6K
ZZhipu
Busyfree
coding-glm-5.3-flash-free:free
ReasoningToolsCache
1.0M
ZZhipu
Busyfree
glm-5.3-flash-uncensored-fp8:free

Popular comparisons