Z.ai: GLM 5
z-ai/glm-5
GLM 5 is an open-weight model from Z.ai, ranking #55 of 234 on the TryAii Score. It's strongest on head-to-head chat (#30 on Chatbot Arena Elo). It's served by 18 independent hosts from $0.6/$1.92 per million input/output tokens — about half of what models at its level usually charge.
Prompt $/1M
$0.600
Completion $/1M
$1.920
Context
204,800 tok
Best provider
107 tok/s · BaseTen
Specs
- Model id
- z-ai/glm-5
- Display name
- Z.ai: GLM 5
- Modality
- text->text
- Tokenizer
- Other
- Instruct type
- —
- Context length
- 204,800
- Max completion
- 128,000
- Prompt $/1M
- $0.600
- Completion $/1M
- $1.920
- Free tier
- no
Capabilities
- Function callingno
- JSON modeno
- System promptno
- Visionno
- Moderatedno
Benchmark scores
Each axis is one benchmark, normalized to the best model in the field.
No benchmark data for this model.
Speed by provider
| Provider | tok/s |
|---|---|
| BaseTenfastest | 107 |
| Amazon Bedrockfastest | 98 |
| Together | 58 |
| Friendli | 52 |
| Baidu | 48 |
| Z.AI | 48 |
| AtlasCloud | 47 |
| Novita | 43 |
| Fireworks | 39 |
| Parasail | 39 |
| Nebius | 39 |
| SiliconFlow | 37 |
| DeepInfra | 35 |
| StreamLake | 34 |
| GMICloud | 32 |
| Venice | 30 |
| Chutes | 29 |
| Ambient | 25 |
| Phala | 14 |
| DigitalOcean | 7 |
| Artificial Analysis | 0 |