Text model
nvidia/Nemotron-120B-A12B pricing
Baseten charges $0.30 per million input tokens and $0.75 per million output tokens for nvidia/Nemotron-120B-A12B. Below: every rate that applies, what common workloads cost, and cheaper options.
- Input
- $0.30/ 1M
- Output
- $0.75/ 1M
Retired 2026-10-16. npx @veqen/sdk scan finds every place your code uses it.
All rates
| Tier | Input | Output | Cache read | Cache write |
|---|---|---|---|---|
| Standard | $0.30 | $0.75 | — | — |
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 | $0.00075 | 100,000 | $75.00 |
| RAG answer, cached context | 2,000 fresh + 4,000 cached input, 500 output | $0.00217 | 100,000 | $217.50 |
| Agent step | 4,000 fresh + 8,000 cached input, 800 output | $0.0042 | 250,000 | $1,050.00 |
| 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/Nemotron-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/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B | $0.0005 | 33% |
| baseten/zai-org/GLM-5.3-Flash | $0.000425 | 43% |
| deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 | $0.00062 | 17% |
| novita/qwen/qwen3-235b-a22b-fp8 | $0.00062 | 17% |
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.