Model Details
Released
Jul 28, 2025
Context Length
128,000
Max Output
32,000
Modalities
Text
→
Text
Capabilities
Tool use
Structured outputs
Code execution
Where is GLM 4.5 Flash a perfect fit?
GLM-4.5-Flash is a general-purpose text model. It supports configurable thinking, function calling, long-context processing, and cost-free hosted inference. It is suitable for below use-cases:
- General-purpose chat and Q&A
- Coding assistance and code generation
- Function-calling applications
- Lightweight AI agents
- Multi-step reasoning
- Text summarization and extraction
- Long-form writing
- Prototyping AI applications with minimal API cost
- High-volume workloads where a free hosted tier is available
GLM-4.5-Flash should not be confused with the open-weight GLM-4.5 model (355B total parameters, 32B active) or GLM-4.5-Air (106B total, 12B active). Those are separate downloadable models. GLM-4.5-Flash is best classified as a free hosted, lightweight text-model offering, rather than a confirmed standalone open-weight checkpoint. Its appeal is low-cost experimentation and general-purpose reasoning with tool calling.
- General-purpose chat and Q&A
- Coding assistance and code generation
- Function-calling applications
- Lightweight AI agents
- Multi-step reasoning
- Text summarization and extraction
- Long-form writing
- Prototyping AI applications with minimal API cost
- High-volume workloads where a free hosted tier is available
GLM-4.5-Flash should not be confused with the open-weight GLM-4.5 model (355B total parameters, 32B active) or GLM-4.5-Air (106B total, 12B active). Those are separate downloadable models. GLM-4.5-Flash is best classified as a free hosted, lightweight text-model offering, rather than a confirmed standalone open-weight checkpoint. Its appeal is low-cost experimentation and general-purpose reasoning with tool calling.
Quick Model Estimate
Your GLM 4.5 Flash Cost Estimate
💰 Total Cost
—
for 1000 input + 1000 output tokens
📥 Input (1000 × Free)
—
📤 Output (1000 × Free)
—
Cost Breakdown
📥 Input
📤 Output
Prices are watched for changes and checked against the provider's own page.
Pricing
Other Models in the GLM 4.5 Family
FAQs about GLM 4.5 Flash
How much does GLM 4.5 Flash cost per 1M tokens?
GLM 4.5 Flash costs nothing for input tokens, and nothing for output tokens.
What does a typical workload cost with GLM 4.5 Flash?
1,000 requests of 2,000 input and 500 output tokens each — 2,000,000 input and 500,000 output tokens in total — costs nothing with GLM 4.5 Flash at its lowest rates. Use the calculator on this page for your own volumes.
Where can I use GLM 4.5 Flash?
GLM 4.5 Flash is available through Z.ai, free of charge for input tokens.
What is GLM 4.5 Flash's context window?
GLM 4.5 Flash has a context window of 128,000 tokens, and returns up to 32,000 tokens in a single response.
What input types does GLM 4.5 Flash support?
GLM 4.5 Flash accepts text input, and returns text.