Text model
nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B pricing
Baseten charges $0.20 per million input tokens and $0.50 per million output tokens for nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B, and $0.04 for cached input. Below: every rate that applies, what common workloads cost, and cheaper options.
- Input
- $0.20/ 1M
- Output
- $0.50/ 1M
- Cached input
- $0.04/ 1M
- Context
- 1Mtokens
All rates
| Tier | Input | Output | Cache read | Cache write |
|---|---|---|---|---|
| Standard | $0.20 | $0.50 | $0.04 | — |
USD per million tokens. Long-context tiers apply when the whole prompt, cached tokens included, passes the threshold.
Work it out
What common workloads cost
| Workload | Per call | Cost per call | Calls a month | Per month |
|---|---|---|---|---|
| Chat reply | 1,500 input and 400 output tokens | $0.0005 | 100,000 | $50.00 |
| RAG answer, cached context | 2,000 fresh + 4,000 cached input, 500 output | $0.00081 | 100,000 | $81.00 |
| Agent step | 4,000 fresh + 8,000 cached input, 800 output | $0.00152 | 250,000 | $380.00 |
| Batch summary | 3,000 input and 300 output tokens via the Batch API | — | 1,000,000 | — |
Planning a mix of models? Simulate a workload with nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B, alongside anything else you run.
Cheaper options
Current models that cost at least 15% less for a typical chat reply. Cheaper isn't always equivalent: test quality on your own prompts, then use veqen diff to see the impact at your volume.
| Model | Chat reply | Saving |
|---|---|---|
| baseten/openai/gpt-oss-120b | $0.00035 | 30% |
| baseten/deepseek-ai/DeepSeek-V4-Flash-0731 | $0.000299 | 40% |
| bedrock/anthropic.claude-haiku-5-5 | $0.00042 | 16% |
| cloudflare/@cf/openai/gpt-oss-20b | $0.00042 | 16% |
Price history
No price changes since Veqen started tracking this model.
Compare
Last verified with price book 2026-10-22. Sources: Baseten pricing and LiteLLM's MIT-licensed price file. Track every call to this model, per customer or project: install the SDK.