GLM 5 Turbo
by Z.ai · z-ai/glm-5-turbo · #221 cheapest of 325 paid models
Prices updated Jul 22, 2026, 1:43 AM UTC · refreshed hourly
GLM-5 Turbo is a new model from Z.ai designed for fast inference and strong performance in agent-driven environments such as OpenClaw scenarios. It is deeply optimized for real-world agent workflows...
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol
Pricing
Input
$1.20
per 1M tokens
Output
$4.00
per 1M tokens
Blended (3:1)
$1.90
3 input : 1 output
Cache read
$0.24
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for GLM 5 Turbo with prompt caching.
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $1.90 | $0.1264 | — |
| 50% | $1.54 | $0.0784 | −38% |
| 90% | $1.25 | $0.04 | −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 | $0.0018 | $1.80 |
| Document summary | 8,000 | 1,000 | $0.0136 | $13.60 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.044 | $44.00 |
| Long-context analysis | 150,000 | 5,000 | $0.2 | $200.00 |
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 | 1,298 |
| UI components | 1,306 |
| Data viz | 1,301 |
| SVG | 1,260 |
| 3D | 1,310 |
| Game dev | 1,315 |
| Code categories | 1,302 |
| ASCII art | 1,195 |
Specs
Context window
203K
tokens
Max output
131K
tokens
Input modalities
text
Tokenizer
Other