Llama Nemotron Super 49B v1.5
Llama Nemotron Super 49B v1.5Alternatives?
CheaperMiniMax M3.1 Flashthinking×11.1-34%$0.22Complete model response must be appended
BetterGPT-6 Lunalow×4.7-50%$0.005Function calling only with none · Chat Completions+3
OpenQwen3.8 27Bxhigh×7.9+139%$1.01max_tokens range · QwenCloud+4
CheaperClaude Haiku 5.5max×10.3-50%$0.21Remove sampling parameters+5
CheaperGLM 5.3 FlashmaxOpen×9.2-41%$0.28Memory (4-bit): 30 GB → 193 GB+5MiniMax M3.1 Flashthinking×11.1-34%$0.22Complete model response must be appendedClaude Haiku 5.5max×10.3-50%$0.21Remove sampling parameters+5GLM 5.3 FlashmaxOpen×9.2-41%$0.28Memory (4-bit): 30 GB → 193 GB+5GPT-6 Lunamax×8.9-50%$0.068Function calling only with none · Chat Completions+3Qwen3.8 FlashthinkingOpen×8.8-43%$0.37Memory (4-bit): 30 GB → 108 GB+6GPT-6 Lunalow×4.7-50%$0.005Function calling only with none · Chat Completions+3
Granite 4.2 3BthinkingOpen+54%-87%$0.006GPT-5.6 Lunalow×4.6+13%$0.01GPT OSS 20BhighOpen×2.5-91%$0.011
Mistral Small 4thinkingOpen×2.3-34%$0.015Memory (4-bit): 30 GB → 72 GBQwen3.8 27BxhighOpen×7.9+139%$1.01max_tokens range · QwenCloud+4Nemotron 3.5 Super VLOpen×7.1-56%$0.19Memory (4-bit): 30 GB → 75 GBNemotron 3.5 Bolt 74B-A9BOpen×5.7——Memory (4-bit): 30 GB → 45 GBQwen 3.5 27BthinkingOpen×5.5+106%$0.30 / $2.40
Gemma 4 31BthinkingOpen×5.5-60%$0.10 / $0.34Nemotron 3.5 Super VLOpen×7.1—$0.19Memory (4-bit): 30 GB → 75 GBNemotron 3 UltrathinkingOpen×6.6—$0.58Memory (4-bit): 30 GB → 336 GBNemotron 3.5 Bolt 74B-A9BOpen×5.7——Memory (4-bit): 30 GB → 45 GBNemotron 3 Super 120B A12BOpen×4.8—$1.64Memory (4-bit): 30 GB → 74 GBNemotron Cascade 2 30B A3BOpen×2.8——Nemotron 3.5 LightningthinkingOpen×2.5—$0.079Llama 3.1 Nemotron Nano 4B v1.1Opensame——NVIDIA Nemotron 3 Nano 4BOpensame——All NVIDIA models →Run it yourself
estimateBenchmarks
in Chat & KnowledgeFAQ
How much does Llama Nemotron Super 49B v1.5 cost?›
$0.40 per 1M input tokens and $0.40 per 1M output tokens (cheapest host: DeepInfra).
Is Llama Nemotron Super 49B v1.5 free to use?›
There is no free API; the cheapest paid price is $0.40 per 1M input tokens. The weights are open, so you can run it yourself.
How good is Llama Nemotron Super 49B v1.5, and what is it best at?›
#297 of 334 in Chat & Knowledge, #170 of 239 in Coding, #171 of 242 in Agents & Tool Use, #128 of 195 in Writing & Language.
Is Llama Nemotron Super 49B v1.5 better than Ling 1T?›
On Humanity's Last Exam, Llama Nemotron Super 49B v1.5 scores 7.3 vs 7.3 — about the same.
How can I use Llama Nemotron Super 49B v1.5?›
Through the API of DeepInfra.
What is the context window of Llama Nemotron Super 49B v1.5?›
128K tokens.
When was Llama Nemotron Super 49B v1.5 released? Is there a newer version?›
Released 2025-07-25. It has been superseded by Nemotron 3 Super.
Is Llama Nemotron Super 49B v1.5 open source?›
Yes, the weights are open (nvidia-open-model-license licence).
Can I run Llama Nemotron Super 49B v1.5 locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can Llama Nemotron Super 49B v1.5 read images?›
No, it accepts text only.
What is Llama Nemotron Super 49B v1.5?›
Llama Nemotron Super 49B v1.5 is an open-weights language model from NVIDIA, released Jul 2025.
What are the best alternatives to Llama Nemotron Super 49B v1.5?›
MiniMax M3.1 Flash (cheaper), GPT-6 Luna (better), Qwen3.8 27B (open weights).