Identity and capabilities
- Status
- active
- Local execution
- Available weights · transformers · mit
- Context window
- 200,000
- Maximum output
- 128,000
- Image input
- No
- Reasoning
- Yes
- Tool calling
- Yes
- Release date
- First seen
- 2026-08-29 19:40:01Z UTC
- Last verified
Current offers - prices in USD · per 1M tokens
| Amazon Bedrock | Hugging Face Inference Providers⊕ 2 routes ▾ | Novita AI | OpenRouter | Z.AI | |
|---|---|---|---|---|---|
| Standard | DeepInfra | ||||
| Cached input | $0.2 | $0.12 | $0.2 | ||
| Input | $1 | $0.6 | $1 | $0.6 | $1 |
| Output | $3.2 | $2.08 | $3.2 | $1.92 | $3.2 |
| Batch / Flex · Base context | |||||
| Input | $0.5 | ||||
| Output | $1.6 | ||||
| Priority | |||||
| Input | $1.75 | ||||
| Output | $5.6 |
Hugging Face Inference Providers · 2 routes
DeepInfra | Novita | |
|---|---|---|
| Input | $0.6 | $1 |
| Output | $2.08 | $3.2 |
Active promotions
40% off z-ai/glm-5
Recent price changes
No price changes in the last 7 days.