Free
$0
- Models
- Selected
- TPM
- Limited
- Concurrency
- 1
- Queue
- Best effort
- SLA
- No
Pricing
Start free. Build with serverless. Scale to reserved or dedicated capacity.
Serverless
Per token
- Models
- All
- TPM
- Standard
- Concurrency
- Higher
- Queue
- Priority
- SLA
- Standard
Reserved
Committed capacity
- Models
- Selected
- TPM
- Guaranteed
- Concurrency
- Guaranteed
- Queue
- Reserved
- SLA
- Contract
Dedicated
Custom
- Models
- Custom
- TPM
- Dedicated
- Concurrency
- Custom
- Queue
- Isolated
- SLA
- Contract
Qwen3.8-27B is online and free. Free capacity is subject to fair-use rate limits and has no SLA.
Model pricing
USD per 1M tokens. Input, cached input and output are priced separately.
| Model | Input | Cached Input | Output |
|---|---|---|---|
 Qwen3.8-27B | $0 | $0 | $0 |
| Qwen3.8-2.4T-A95B | $1.95 | $0.245 | $5.70 |
 GLM-5.3-Flash | $0.099 | $0.025 | $0.35 |
 Kimi K2.7 Code | $0.69 | $0.15 | $3.29 |
 DeepSeek V4 Pro | $0.89 | $0.030 | $2.69 |
| GLM-5.3 | $0.99 | $0.245 | $3.45 |
| Kimi K3 | $2.39 | $0.24 | $11.99 |
 MiniMax M3 | $0.299 | $0.045 | $1.19 |
| DeepSeek V4.1 Flash | $0.29 | $0.0058 | $1.16 |
| DeepSeek V4 Flash 0731Legacy alias · Same pricing as V4.1 Flash | $0.29 | $0.0058 | $1.16 |
Qwen3.8-27B input, cached input and output are free. See the Free Models page for availability and limits.
Try Free →