- Nemotron 3 Ultra (free) — $0 sample workload
- Nemotron 3.5 Lightning (free) — $0 sample workload
- Nemotron 3.5 Content Safety (free) — $0 sample workload
- Nemotron 3 Nano Omni (free) — $0 sample workload
- Nemotron 3 Super (free) — $0 sample workload
NVIDIA LLM API Models & Pricing
Browse NVIDIA LLM API models with normalized prompt pricing, output pricing, context windows, release dates, and popularity signals.
15Models tracked
15Priced models
2Popular models
2Latest releases
Provider shortlist
Use NVIDIA as a model-level shortlist, not a single default choice.
Start from the cost, context, and popularity picks below, then open the model pages or head-to-head comparisons before choosing an API.
Cost pick
Nemotron 3 Ultra (free)
$0 sample workload
Context pick
Nemotron 3 Ultra (free)
1M context window
Popular pick
Nemotron 3 Ultra (free)
#7 popularity signal
When to avoid
Verify model fit
Do not choose by provider name alone. Compare model-level input price, output price, context window, release timing, and current availability before production use.
- Nemotron 3 Ultra (free) — 1M
- Nemotron 3.5 Lightning (free) — 1M
- Nemotron 3 Super — 1M
- Nemotron 3 Ultra — 512.29K
- Nemotron 3 Ultra (batch) — 512.29K
NVIDIA comparisons
Search NVIDIA comparisons| Comparison | Sample Cost Winner | Larger Context | Newest Release |
|---|---|---|---|
| 🔥DeepSeek V4 Flash 0423 vs 🔥Nemotron 3 Ultra (free) | Nemotron 3 Ultra (free) | DeepSeek V4 Flash 0423 | |
| 🔥DeepSeek V4 Flash 0731 vs 🔥Nemotron 3 Ultra (free) | Nemotron 3 Ultra (free) | DeepSeek V4 Flash 0731 | |
| 🔥GPT-5.6 Luna vs 🔥Nemotron 3 Ultra (free) | Nemotron 3 Ultra (free) | GPT-5.6 Luna | |
| 🔥Hy3 vs 🔥Nemotron 3 Ultra (free) | Nemotron 3 Ultra (free) | Nemotron 3 Ultra (free) | |
| 🔥MiMo-V2.5 vs 🔥Nemotron 3 Ultra (free) | Nemotron 3 Ultra (free) | MiMo-V2.5 | |
| New🔥Ox Alpha vs 🔥Nemotron 3 Ultra (free) | Tie | Ox Alpha | |
| 🔥Nemotron 3 Ultra (free) vs 🔥GLM 5.2 | Nemotron 3 Ultra (free) | GLM 5.2 | |
| 🔥Nemotron 3 Ultra (free) vs 🔥Claude Opus 5 | Nemotron 3 Ultra (free) | Tie |
Cross-Provider Alternatives
Open alternatives hubUse this shortlist when NVIDIA is not a hard requirement and your first constraint is workload cost.
| Alternative | Provider | Sample Cost | Input / 1M | Output / 1M | Context |
|---|---|---|---|---|---|
| New🔥Ox Alpha | stealth | $0 | $0 | $0 | 1.05M |
| 🔥Laguna S 2.1 (free) | Poolside | $0 | $0 | $0 | 262.14K |
| NewDots3-Note Preview (free) | Dots Studio | $0 | $0 | $0 | 512K |
| NewLFM2.5-2.6B (free) | LiquidAI | $0 | $0 | $0 | 65.54K |
| Ling 3.0 Tiny (free) | inclusionAI | $0 | $0 | $0 | 262.14K |
| Inkling Small (free) | Thinking Machines | $0 | $0 | $0 | 262.14K |
NVIDIA model catalog
Browse all models| Model | Prompt | Output | Context | Popularity |
|---|---|---|---|---|
| 🔥Nemotron 3 Ultra (free) | $0 | $0 | 1M | #7 |
| New🔥Nemotron 3.5 Lightning (free) | $0 | $0 | 1M | #17 |
| NewNemotron 3.5 Lightning | $0.08 | $0.2 | 262.14K | |
| Nemotron 3.5 Content Safety (free) | $0 | $0 | 128K | |
| Nemotron 3 Ultra | $0.6 | $3.6 | 512.29K | |
| Nemotron 3 Ultra (batch) | $0.6 | $3.6 | 512.29K | |
| Nemotron 3 Nano Omni (free) | $0 | $0 | 256K | |
| Nemotron 3 Super | $0.085 | $0.4 | 1M | |
| Nemotron 3 Super (free) | $0 | $0 | 262.14K | |
| Nemotron 3 Nano 30B A3B | $0.05 | $0.2 | 262.14K | |
| Nemotron 3 Nano 30B A3B (free) | $0 | $0 | 256K | |
| Nemotron Nano 12B 2 VL (free) | $0 | $0 | 128K | |
| Llama 3.3 Nemotron Super 49B V1.5 | $0.4 | $0.4 | 131.07K | |
| Nemotron Nano 9B V2 | $0.04 | $0.16 | 131.07K | |
| Nemotron Nano 9B V2 (free) | $0 | $0 | 128K |