GLM 4.5
by Z.ai · z-ai/glm-4.5 · #183 cheapest of 325 paid models
Prices updated Jul 22, 2026, 1:44 AM UTC · refreshed hourly
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...
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol
Pricing
Input
$0.60
per 1M tokens
Output
$2.20
per 1M tokens
Blended (3:1)
$1.00
3 input : 1 output
Cache read
$0.11
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for GLM 4.5 with prompt caching.
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $1.00 | $0.0634 | — |
| 50% | $0.816 | $0.0389 | −39% |
| 90% | $0.669 | $0.0193 | −70% |
*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates (available for OpenAI / Anthropic / Google — not flagged for this creator). Confirm on the vendor’s pricing page.
What a request costs
| Workload | Input tokens | Output tokens | Cost / request | Cost / 1K requests |
|---|---|---|---|---|
| Short chat message | 500 | 300 | $0.00096 | $0.96 |
| Document summary | 8,000 | 1,000 | $0.007 | $7.00 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.0224 | $22.40 |
| Long-context analysis | 150,000 | 5,000 | $0.101 | $101.00 |
Performance
Intelligence Index
—
AA composite quality
Coding Index
—
Math Index
—
Agentic Index
—
Output speed
—
median
Time to first token
—
median
Time to first answer
—
after reasoning tokens
Design Arena Elo
| Category | Elo |
|---|---|
| Website | 1,197 |
| UI components | 1,186 |
| Data viz | 1,196 |
| SVG | 1,143 |
| 3D | 1,229 |
| Game dev | 1,204 |
| Code categories | 1,199 |
Specs
Context window
131K
tokens
Max output
98K
tokens
Input modalities
text
Tokenizer
Other