Same open weights, served by 2 providers. Weights: nvidia/NVIDIA-Nemotron-3.5-Super-VL.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
DeepInfra | nvidia/NVIDIA-Nemotron-3.5-Super-VL | standardFP4Reduced context (262k of 1M) | $0.15 | $0.50 | $0.08 | $0.237 | Verified 34d ago ยท Changed 34d ago Price change pending review Not verified in 811h | |
Together AI | nvidia/NVIDIA-Nemotron-3.5-Super-VL | standardQuantization not disclosedReduced context (262k of 1M) | $0.15 | $0.50 | $0.02 | $0.237 | Verified 12h ago ยท Changed 36d ago |
Same weights don't always mean identical outputs: quantization, context limits and serving stacks can change quality, especially for tool calling. Prices are USD per 1M tokens; hyperscaler prices are for the reference region shown.
| DeepInfra fp4 | $25/mo |
| Together AI | $25/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.