Inference provider
OpenInference: every model it hosts
3 endpoints tracked. Hosts may use different quantizations, context limits, and serving defaults, so compare price together with reliability and configuration.
Verified 2026-10-21 · source: OpenRouter public API
| Model | Input /1M | Output /1M | Cache read | Context | Uptime 1d | Throughput |
|---|---|---|---|---|---|---|
| DeepSeek: DeepSeek V4.1 Flashfp4 | $0.049 | $0.375 | $0.0010 | 1049K | 98.7% | — |
| DeepSeek: DeepSeek V4.1 Flashfp4 | $0.049 | $0.375 | $0.0012 | 1049K | 98.0% | — |
| Z.ai: GLM 5.3 Flashfp4 | $0.052 | $0.120 | $0.0038 | 1049K | 97.8% | — |
Prices are list prices at build time; providers run promotions. Uptime/throughput are OpenRouter's rolling measurements. Compare hosts on the providers index.