Inference provider
InferenceNet: every model it hosts
14 endpoints tracked. Hosts may use different quantizations, context limits, and serving defaults, so compare price together with reliability and configuration. On this host family, the same model costs up to 28× more depending on which endpoint serves it.
Verified 2026-10-21 · source: OpenRouter public API
| Model | Input /1M | Output /1M | Cache read | Context | Uptime 1d | Throughput |
|---|---|---|---|---|---|---|
| DeepSeek: DeepSeek V4.1 Flashfp8 | $0.080 | $0.500 | $0.0080 | 1040K | 99.3% | — |
| DeepSeek: DeepSeek V4.1 Flashfp8 | $0.080 | $0.500 | $0.0080 | 1040K | 99.4% | — |
| Z.ai: GLM 5.3fp4 | $0.080 | $4.38 | $0.076 | 1049K | 99.3% | — |
| Z.ai: GLM 5.3fp4 | $0.080 | $4.38 | $0.076 | 1049K | 99.4% | — |
| DeepSeek: DeepSeek V4.1 Flashfp8 | $0.103 | $0.715 | $0.0080 | 1040K | 99.5% | — |
| DeepSeek: DeepSeek V4.1 Flashfp8 | $0.103 | $0.715 | $0.0080 | 1040K | 99.5% | — |
| Z.ai: GLM 5.3 Flashfp4 | $0.120 | $0.388 | $0.032 | 1049K | 93.8% | — |
| Z.ai: GLM 5.3 Flashfp4 | $0.120 | $0.388 | $0.032 | 1049K | 94.4% | — |
| MoonshotAI: Kimi K3fp4 | $0.239 | $11.94 | $0.210 | 1049K | 98.8% | — |
| MoonshotAI: Kimi K3fp4 | $0.239 | $11.94 | $0.210 | 1049K | 99.2% | — |
| StepFun: Step 5 Previewfp4 | $1.00 | $2.70 | $0.050 | 1049K | 100.0% | — |
| StepFun: Step 5 Previewfp4 | $1.00 | $2.70 | $0.050 | 1049K | 100.0% | — |
| MoonshotAI: Kimi K3fp4 | $2.04 | $13.20 | $0.350 | 1049K | 99.4% | — |
| MoonshotAI: Kimi K3fp4 | $2.24 | $14.52 | $0.350 | 1049K | 99.0% | — |
Prices are list prices at build time; providers run promotions. Uptime/throughput are OpenRouter's rolling measurements. Compare hosts on the providers index.