GLM 5
glm-5GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading... Built by Z.ai.
Prices updated
Input price
$0.60
per 1M tokens · Standard
Output price
$1.92
per 1M tokens · Standard
Input limit
205K
tokens
Output limit
128K
tokens
Input formats
Output formats
GLM 5 price history
2 price records since 9/25/2026
GLM 5 cost calculator
$22/month
Standard pricing
Overview
What is GLM 5?
GLM 5 is a text & reasoning model from Z.ai. GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading... Its 205K context window and $0.60 input price make it a candidate for quality-focused production applications.
Benchmarks
GLM 5 benchmarks & speed
How GLM 5 scores on standardized evaluations, and where it lands among every model we track.
27.9
Intelligence Index
82tok/s
Output speed
1250
DesignArena Elo
Reasoning
GPQA Diamond
82.0%
Graduate-level scientific reasoning · top 50%
HLE
29.3%
Humanity's Last Exam · top 37%
Latency & design
- Time to first token
- 1.44s
- DesignArena win rate
- 55.5%
- Design battles judged
- 45,364
Independent scores from Artificial Analysis and DesignArena · updated 10/8/2026. Higher is better; ranks compare against every model we track with that score.
Rates
GLM 5 pricing
Pricing is based on token usage. Provider-specific caching, batch, regional, and tool charges may affect the final cost.
Input · Standard
$0.60
Per 1M tokens
Cached input · Standard
$0.12
Per 1M tokens
Capabilities
GLM 5 Tools
Tools available when using GLM 5 through supported provider APIs.
Function calling
Supported
Structured outputs
Supported
JSON mode
Supported
Reasoning
Supported
Built-in web search
Not supported
Log probabilities
Supported
Deterministic seed
Supported
Parallel tool calls
Not supported
Prompt caching
Supported
Where to run it
GLM 5 API providers
8 providers serve GLM 5. Prices are per 1M tokens; uptime is the last 24 hours.
| Provider | Input | Output | Cached | Context | Uptime |
|---|---|---|---|---|---|
| StreamLakefp8 | $0.60 | $1.92 | $0.12 | 198K | 99.66% |
| GMICloudfp8 | $0.60 | $1.92 | $0.12 | 203K | 99.31% |
| Baidufp8 | $0.70 | $2.24 | $0.14 | 203K | 98.97% |
| SiliconFlowfp8 | $0.95 | $2.55 | $0.20 | 205K | 99.74% |
| Amazon Bedrock | $1.00 | $3.20 | — | 203K | 98.77% |
| Venicefp8 | $1.00 | $3.20 | $0.20 | 198K | 99.63% |
| Novitafp8 | $1.00 | $3.20 | $0.20 | 203K | 100% |
| Z.AIfp8 | $1.00 | $3.20 | $0.20 | 203K | 99.92% |
- Input
- $0.60
- Output
- $1.92
- Cached
- $0.12
- Context
- 198K
- Uptime
- 99.66%
- Input
- $0.60
- Output
- $1.92
- Cached
- $0.12
- Context
- 203K
- Uptime
- 99.31%
- Input
- $0.70
- Output
- $2.24
- Cached
- $0.14
- Context
- 203K
- Uptime
- 98.97%
- Input
- $0.95
- Output
- $2.55
- Cached
- $0.20
- Context
- 205K
- Uptime
- 99.74%
- Input
- $1.00
- Output
- $3.20
- Cached
- —
- Context
- 203K
- Uptime
- 98.77%
- Input
- $1.00
- Output
- $3.20
- Cached
- $0.20
- Context
- 198K
- Uptime
- 99.63%
- Input
- $1.00
- Output
- $3.20
- Cached
- $0.20
- Context
- 203K
- Uptime
- 100%
- Input
- $1.00
- Output
- $3.20
- Cached
- $0.20
- Context
- 203K
- Uptime
- 99.92%
Strengths and limitations
Strengths
- Measured results (AA Intelligence 27.9 · DesignArena Elo 1250) position it for demanding production work.
- 205K context supports large documents, repositories and extended conversations.
- Supports text & reasoning workloads in one model.
Limitations
- Generated tokens cost 3× more than input tokens, which matters for verbose responses.
- Large context capacity does not guarantee consistent retrieval across the entire prompt.
- Arena Elo and MMLU-Pro are directional; test accuracy, latency and reliability on your own workload before committing.
Arena Elo, MMLU-Pro and pricing figures are illustrative; validate current vendor terms before purchase.
Same provider