OpenInference
- Inference provider
- 3 hosted endpoints
| Model | Endpoint | Context | Input /M | Output /M | Cached input /M | Cache write /M | Uptime 1d |
|---|---|---|---|---|---|---|---|
 DeepSeek V4.1 Flash | open-inference/fp4 | 1M | $0.07 | $0.80 | $0.006 | — | 100.00% |
| DeepSeek V4.1 Flash 1017 | open-inference/fp4 | 1M | $0.07 | $0.80 | $0.006 | — | 100.00% |
 GLM 5.3 Flash | open-inference/fp4 | 1M | $0.06 | $0.30 | $0.03 | — | 99.24% |