RunInfra pricing overview
TokenWatch tracks 8 text, 0 image, and 0 video model records for this provider. Reviewed metadata says prompts are not retained.
Cheapest input price: Nemotron 3.5 Lightning 30B at $0.050 per million input tokens and $0.150 per million output tokens. 8 of 8 text models publish a cache-read price; 8 carry a zero-data-retention tag.
RunInfra text-model pricing
Text offerings ranked by the Agentic workload mix (2.5% input, 97% cached input, 0.5% output). Change the calculator mix for a workload-specific estimate.
| Org | Provider | Model | Input $/M | Output $/M | Cache $/M | Blended $/M |
|---|---|---|---|---|---|---|
| nvidia | runinfra | Nemotron 3.5 Lightning 30B | $0.050 | $0.150 | $0.010 | $0.012 |
| z-ai | runinfra | GLM 5.3 Flash | $0.050 | $0.220 | $0.010 | $0.012 |
| ornith | runinfra | Ornith 1.5 35B | $0.100 | $0.400 | $0.010 | $0.014 |
| qwen | runinfra | Qwen3.8 27B | $0.100 | $0.400 | $0.010 | $0.014 |
| deepseek | runinfra | DeepSeek V4.1 Flash 1017 | $0.150 | $0.600 | $0.010 | $0.016 |
| deepseek | runinfra | DeepSeek V4.1 Flash | $0.140 | $0.580 | $0.030 | $0.035 |
| ornith | runinfra | Ornith 1.5 122B | $0.260 | $2.08 | $0.070 | $0.085 |
| z-ai | runinfra | GLM 5.3 | $1.30 | $4.20 | $0.130 | $0.180 |
Catalog snapshot 2026-10-29 from direct-provider APIs, OpenRouter endpoint data, and maintained fallbacks. See the sources and calculation rules; verify rates on the provider's official pricing page before committing spend.