Z.ai: GLM 5
z-ai/glm-5
47th smartest of 182ReasoningToolsJSON
Intelligence
39.5
47th of 182
Design Elo
1286
3D
Speed
—
tokens/sec
Latency
—
first token
Input price
$0.950
218th cheapest
Context
205K
131K max out
How it compares
Smarter than74%
of all ranked models
Cheaper than34%
of all ranked models
Overview
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...
Benchmarks
independent · Artificial Analysis & Design ArenaArtificial Analysis89th percentile
Intelligence Index
39.5
GPQA Diamond
82%
Humanity's Last Exam
27%
SciCode
46%
Tau²-Bench (agentic)
98%
Design Arena · Elo9,244 tournaments
3D
1286
Website
1273
Data Viz
1258
svg
1215
Providers & pricing (13)
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| StreamLakefp8 | $0.600 | $1.92 | 198K | 99.8% |
| GMICloudfp8 | $0.600 | $1.92 | 203K | 99.6% |
| DeepInfrafp4 | $0.600 | $2.08 | 203K | 100% |
| Baidufp8cache | $0.700 | $2.24 | 203K | 98.9% |
| DigitalOcean | $0.750 | $2.40 | 64K | 97.6% |
| SiliconFlowfp8 | $0.950 | $2.55 | 205K | 99.7% |
| AtlasCloudfp8 | $0.950 | $3.15 | 203K | 100% |
| Amazon Bedrock | $1.00 | $3.20 | 203K | 100% |
| Novitafp8 | $1.00 | $3.20 | 203K | 100% |
| Z.AIfp8 | $1.00 | $3.20 | 203K | 99.2% |
| Parasailfp8 | $1.00 | $3.20 | 203K | 98.2% |
| Venicefp8 | $1.00 | $3.20 | 198K | — |
| Phala | $1.20 | $3.50 | 203K | — |
Specifications
Context window205K
Max output131K
Knowledge cutoff—
Input modalitiestext
Output modalitiestext
Prompt cachingSupported
Cache read price$0.200/M
ModeratedNo
Open weightszai-org/GLM-5 ↗
GLM 5 FAQ
How much does GLM 5 cost?
GLM 5 costs $0.950 per million input tokens and $2.55 per million output tokens via OpenRouter, making it 218th cheapest of 332 paid models.
How smart is GLM 5?
GLM 5 scores 39.5 on the Artificial Analysis Intelligence Index, ranking 47th of 182 benchmarked models, with a GPQA Diamond score of 82%.
What is GLM 5's context window?
GLM 5 supports a 205K-token context window and can output up to 131K tokens. It accepts text input.