NVIDIA API pricing: every provider, per million tokens
The lowest blended price for a NVIDIA model is $0.0488 (₹4.60) per million tokens, for NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 on Darkbloom at INT4 (other providers mostly serve BF16), blended 3:1 input to output. The newest NVIDIA model with an API is NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16, released 12 Oct 2026. Its lowest blended price is $0.1325 (₹12) on Darkbloom at NVFP4. We list 19 offers from 12 providers for 4 NVIDIA models.
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16
10 providers · context up to 1,048,576| Precision | |||||
|---|---|---|---|---|---|
| DarkbloomCheapest | $0.1325₹12 | $0.06₹5.66 | $0.35₹33 | 262,144 | NVFP4 |
| Io Net | $0.1425₹13 | $0.09₹8.49 | $0.30₹28 | 262,144 | NVFP4 |
| Crusoe | $0.175₹17 | $0.10₹9.43 | $0.40₹38 | 1,048,576 | BF16 |
| CoreWeave | $0.23₹22 | $0.15₹14 | $0.47₹44 | 1,048,576 | NVFP4 |
| DeepInfra | $0.2375₹22 | $0.15₹14 | $0.50₹47 | 262,144 | FP4 |
| PrimeIntellect | $0.2375₹22 | $0.15₹14 | $0.50₹47 | 1,048,576 | NVFP4 |
| Together | $0.2375₹22 | $0.15₹14 | $0.50₹47 | 262,144 | Not listed |
| BaseTen | $0.275₹26 | $0.20₹19 | $0.50₹47 | 1,048,576 | FP4 |
| Venice | $0.275₹26 | $0.20₹19 | $0.50₹47 | 262,144 | FP4 |
| Nebius | $0.45₹42 | $0.30₹28 | $0.90₹85 | 1,048,576 | FP4 |
Run it yourself instead: will NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 fit your hardware?
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16
4 providers · context up to 262,144| Precision | |||||
|---|---|---|---|---|---|
| DarkbloomCheapest | $0.0488₹4.60 | $0.025₹2.36 | $0.12₹11 | 262,144 | INT4 |
| DeepInfra | $0.085₹8.01 | $0.06₹5.66 | $0.16₹15 | 262,144 | BF16 |
| Fireworks | $0.0875₹8.25 | $0.05₹4.71 | $0.20₹19 | 262,144 | Not listed |
| CoreWeave | $0.1025₹9.66 | $0.07₹6.60 | $0.20₹19 | 262,144 | BF16 |
Run it yourself instead: will NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 fit your hardware?
NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16
4 providers · context up to 262,144| Precision | |||||
|---|---|---|---|---|---|
| DeepInfraCheapest | $0.74₹70 | $0.40₹38 | $1.76₹166 | 262,144 | FP4 |
| KT | $0.925₹87 | $0.50₹47 | $2.20₹207 | 262,144 | Not listed |
| BaseTen | $1.05₹99 | $0.60₹57 | $2.40₹226 | 202,800 | FP4 |
| Venice | $1.25₹118 | $0.625₹59 | $3.125₹295 | 256,000 | FP8 |
Run it yourself instead: will NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 fit your hardware?
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
1 provider · context up to 262,144| Precision | |||||
|---|---|---|---|---|---|
| NebiusCheapest | $0.105₹9.90 | $0.06₹5.66 | $0.24₹23 | 262,144 | FP8 |
Run it yourself instead: will NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 fit your hardware?
NVIDIA API pricing questions
What is the cheapest NVIDIA model API?
The lowest blended price is $0.0488 (₹4.60) per million tokens, for NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 on Darkbloom at INT4 (other providers mostly serve BF16). That offer charges $0.025 for input and $0.12 for output per million tokens.
How many providers serve NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16?
10 providers on OpenRouter serve it. The ones with the lowest blended prices are Darkbloom, Io Net, Crusoe, CoreWeave, DeepInfra and 5 more. The lowest blended price is $0.1325 (₹12) per million tokens, on Darkbloom at NVFP4.
Is NVIDIA API pricing in INR?
Providers list prices in US dollars, so we show the rupee price beside each one at ₹94.29 per $1 (rate fetched 14 Nov 2026). For example, the lowest blended offer for NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 is Darkbloom at ₹5.66 for input and ₹33 for output per million tokens. Check the provider for taxes and the rate it charges.
How we compare prices
Offers come from OpenRouter's model listing, fetched 14 Nov 2026. Blended price weights input and output tokens 3 to 1. INR is shown beside USD at ₹94.29 per $1. Prices change, so check the provider before you build on a number.