NVIDIA › Llama Nemotron Super 49B v1.5 › Pricing
Llama Nemotron Super 49B v1.5 pricing
Cheapest host: DeepInfra · checked Oct 26, 2026
$0.40 / $0.40per 1M tokens in / out
Price sheetper 1M tokens
| Input | $0.40 | DeepInfra |
| Output | $0.40 | |
| Context | 128K | tokens |
Where to buy1 provider · per 1M tokens
| Provider | Input | Output | Context |
|---|---|---|---|
| DeepInfra | $0.40 | $0.40 | — |
In NVIDIA's line-upper 1M in / out
| Nemotron 3.5 Content Safety | $0.20 / $0.20 | −50% |
| NVIDIA Nemotron Nano 12B v2 VL | $0.20 / $0.60 | −25% |
| Nemotron 3 Super 120B A12B | $0.13 / $1.15 | −5% |
| Llama Nemotron Super 49B v1.5 | $0.40 / $0.40 | this model |
| Nemotron 3 Ultra | $0.60 / $2.40 | 2.6× |
| Llama 3.1 Nemotron 70B Instruct | $1.20 / $1.20 | 3× |
| OpenCodeReasoning Nemotron 1.1 32B | $2.72 / $4.80 | 8.1× |
Cheaper for the same workvs Llama Nemotron Super 49B v1.5
| Claude Haiku 5.5 max | -50% | score ×5.9 | $0.21 |
| MiniMax M3.1 Flash thinking | -34% | score ×5.8 | $0.22 |
| GLM 5.3 Flash maxOpen | -41% | score ×5.7 | $0.28 |
| Qwen3.8 Flash thinkingOpen | -43% | score ×5.4 | $0.37 |
| GPT-6 Luna max | -50% | score ×5.2 | $0.068 |
Pricing questions
How much does Llama Nemotron Super 49B v1.5 cost?›
$0.40 per 1M input tokens and $0.40 per 1M output tokens.
Is Llama Nemotron Super 49B v1.5 free to use?›
There is no free API tier, but the weights are open: you can run it on your own hardware for the cost of compute.
What is a cheaper alternative to Llama Nemotron Super 49B v1.5?›
Claude Haiku 5.5 at max effort costs -50% per task with a score ×5.9 on Humanity's Last Exam.