All ModelschatGLM 5 Turbo

GLM 5 Turbo

by Z-AIFast

Try on Kunya

Fast inference model optimized for agentic workflows and tool use

Detailed content for this model is coming soon.

Pricing

Input$1.248 per 1M tokens
Output$4.16 per 1M tokens
Context Window203K

Capabilities

Streaming Yes
Vision No
Reasoning No
Tool Use Yes
ProviderZ-AI
Try on Kunya

Similar Models

Llama 4 Scout

Meta

Efficient Llama 4 model

Read full article

Seed 2.0 Lite

ByteDance

Versatile multimodal model with low latency for agent and vision tasks

Read full article

DeepSeek Chat

DeepSeek

Legacy — maps to V4 Flash non-thinking mode. Deprecated 2026-07-24.

Read full article

Claude Haiku 4.5

Anthropic

Fastest model with near-frontier intelligence

Read full article