Inference provider
Morph: every model it hosts
6 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 4× 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 | $0.206 | $0.600 | $0.018 | 1049K | 100.0% | — |
| DeepSeek: DeepSeek V4.1 Flashfp8 | $0.206 | $0.600 | $0.018 | 1049K | 100.0% | — |
| Z.ai: GLM 5.3fp8 | $0.217 | $4.40 | $0.055 | 1049K | 98.5% | — |
| Z.ai: GLM 5.2fp8 | $0.217 | $4.40 | $0.055 | 1049K | 98.3% | — |
| Z.ai: GLM 5.3 Flashfp8 | $0.667 | $0.650 | $0.185 | 1049K | 95.8% | — |
| MoonshotAI: Kimi K3fp8 | $0.814 | $14.90 | $0.389 | 1049K | 98.7% | — |
Prices are list prices at build time; providers run promotions. Uptime/throughput are OpenRouter's rolling measurements. Compare hosts on the providers index.