GLM 4.6
by Z.ai · z-ai/glm-4.6 · #173 cheapest of 325 paid models
Prices updated Jul 22, 2026, 1:31 AM UTC · refreshed hourly
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...
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol
Pricing
Input
$0.50
per 1M tokens
Output
$2.00
per 1M tokens
Blended (3:1)
$0.875
3 input : 1 output
Cache read
$0.10
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for GLM 4.6 with prompt caching.
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $0.875 | $0.053 | — |
| 50% | $0.725 | $0.033 | −38% |
| 90% | $0.605 | $0.017 | −68% |
*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 | $0.00085 | $0.85 |
| Document summary | 8,000 | 1,000 | $0.006 | $6.00 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.019 | $19.00 |
| Long-context analysis | 150,000 | 5,000 | $0.085 | $85.00 |
Performance
Intelligence Index
28.7
AA composite quality
Coding Index
45.8
Math Index
—
Agentic Index
17.7
Output speed
—
median
Time to first token
—
median
Time to first answer
—
after reasoning tokens
Design Arena Elo
| Category | Elo |
|---|---|
| Website | 1,202 |
| Full-stack | 1,089 |
| Mobile apps | 1,178 |
| Android native | 1,076 |
| UI components | 1,201 |
| Data viz | 1,201 |
| SVG | 1,156 |
| 3D | 1,187 |
| Game dev | 1,208 |
| Godot game dev | 1,180 |
| Code categories | 1,199 |
Specs
Context window
205K
tokens
Max output
131K
tokens
Input modalities
text
Tokenizer
Other