Inference provider
Venice: every model it hosts
13 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 17× 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 Flash 0423unknown | $0.097 | $0.193 | $0.020 | 1000K | 97.6% | — |
| Qwen: Qwen3.6 35B A3Bfp8 | $0.100 | $1.00 | — | 256K | 97.9% | — |
| DeepSeek: DeepSeek V4 Flash 0423unknown | $0.130 | $0.260 | $0.028 | 1000K | 97.5% | — |
| Z.ai: GLM 5.3 Flashunknown | $0.150 | $0.500 | $0.030 | 1049K | 96.7% | — |
| Xiaomi: MiMo-V2.6-Flashfp8 | $0.175 | $0.350 | $0.0038 | 1000K | 99.2% | — |
| NVIDIA: Nemotron 3.5 Super VLfp4 | $0.250 | $1.25 | $0.125 | 262K | 92.3% | — |
| DeepSeek: DeepSeek V4.1 Flashfp8 | $0.300 | $1.20 | $0.0075 | 1000K | 98.6% | — |
| MiniMax: MiniMax M3fp8 | $0.300 | $1.20 | $0.060 | 524K | 94.2% | — |
| NVIDIA: Nemotron 3 Ultrafp8 | $0.625 | $3.13 | $0.188 | 256K | 98.1% | — |
| Z.ai: GLM 5.3unknown | $1.40 | $4.40 | $0.260 | 1000K | 77.8% | — |
| Z.ai: GLM 5.2fp8 | $1.40 | $4.40 | $0.260 | 1000K | 99.9% | — |
| DeepSeek: DeepSeek V4 Pro 0423unknown | $1.65 | $4.95 | $0.165 | 1000K | 100.0% | — |
| DeepSeek: DeepSeek V4 Pro 0423unknown | $1.65 | $3.30 | $0.330 | 1000K | 92.0% | — |
Prices are list prices at build time; providers run promotions. Uptime/throughput are OpenRouter's rolling measurements. Compare hosts on the providers index.