Inference APIs
Compare/Chat

Nemotron 3.5 Super VL vs GPT-OSS 120B on Groq

Nemotron 3.5 Super VL is an open-weight chat model you can call on this endpoint; GPT-OSS 120B on Groq is offered from Groq. Below: what each costs for three realistic workloads, the limits that apply, and when to choose which.

Groq figures are public list prices and documented limits, checked 2026-09-16 against the provider page. Inference APIs prices are read live from the price list.

Short answer
  • Cost: It depends on the shape of the workload: Nemotron 3.5 Super VL is cheaper for generation-heavy, GPT-OSS 120B on Groq for chat assistant and long prompts or rag.
  • Limits: Groq: Free tier: 30 requests/min, 1,000 requests/day, 8,000 tokens/min, 200,000 tokens/day. Developer-tier upgrades were paused when we checked (Sep 2026). Here: no per-minute or per-day caps.

Side by side

Nemotron 3.5 Super VLGPT-OSS 120B on Groq
Served byInference APIsGroq
Model authorNVIDIANVIDIA
Model idnvidia/NVIDIA-Nemotron-3.5-Super-VLopenai/gpt-oss-120b
Input price$0.20 / 1M tokens$0.15 / 1M tokens
Output price$0.65 / 1M tokens$0.75 / 1M tokens
Context window262K tokens131K tokens
CapabilitiesVision, Chat, Reasoning, Tool calling, JSON modeChat, Reasoning, Tool calling, JSON mode
WeightsOpenOpen
StatusAvailableAvailable
LimitsNo per-minute or per-day request or token caps; usage draws on a prepaid balanceFree tier: 30 requests/min, 1,000 requests/day, 8,000 tokens/min, 200,000 tokens/day. Developer-tier upgrades were paused when we checked (Sep 2026).
Time to first token0.17 snot measured by us
Output speed35.2 tokens / snot measured by us

What three workloads cost

List prices applied to the same work. The cheaper side of each row is in bold.

WorkloadNemotron 3.5 Super VLGPT-OSS 120B on GroqDifference
Chat assistant — 10,000 turns of 800 tokens in, 300 out$3.55$3.453%
Long prompts or RAG — 10,000 requests of 8,000 in, 500 out$19.25$15.7518%
Generation-heavy — 10,000 requests of 500 in, 2,000 out$14.00$15.7511%

It depends on the shape of the workload: Nemotron 3.5 Super VL is cheaper for generation-heavy, GPT-OSS 120B on Groq for chat assistant and long prompts or rag. Reasoning models bill their thinking as output tokens, so real output counts run higher than the visible answer; treat the generation-heavy row as a floor for them.

When to choose which

Choose Nemotron 3.5 Super VL if
  • You need more than 131K tokens of context (it takes 262K)
  • Vision at a Flash-tier price: $0.20 / $0.65 per million tokens against $0.26 / $1.15 for Qwen3-VL 235B
  • Screenshot and document questions in an agent that also calls tools
  • You used Llama 4 Scout or Maverick on Groq for images and want a cheap replacement
  • You have outgrown the free tier and cannot upgrade
Choose GPT-OSS 120B on Groq if
  • Your volume fits the free tier, or you already have a Developer-tier account
  • Raw output speed is the priority; Groq's hardware is built for it

Price, context and speed are measurable; answer quality on your task is not something a table can settle. Both take the same request, so the honest test is to run your own prompts through each.

Measured speed

Medians of three streamed runs on 2026-09-17, public endpoint, a prompt that asks for about 120 words. Time to first token is the first token of any kind, reasoning included; output speed counts every generated token from that point. Reasoning models then think before the visible answer starts: Nemotron 3.5 Super VL began answering after — s at default settings, which you can shorten with the reasoning controls on each model page. Expect ±30% with time of day. We did not measure Groq and do not quote other people's numbers; read "not measured" as unknown, not slow. Method and raw numbers: speed measurements.

Switching from Groq

Both speak the OpenAI wire format. The edit is the base URL, the key and the model id; then re-run your own prompts, because it is a different model.

Python · openai SDK
import os
from openai import OpenAI

# before: Groq
# client = OpenAI(base_url="https://api.groq.com/openai/v1", api_key=os.environ["GROQ_API_KEY"])
# MODEL = "openai/gpt-oss-120b"

# after: Inference APIs
client = OpenAI(base_url="https://api.inferenceapis.com/v1", api_key=os.environ["INFERENCE_API_KEY"])
MODEL = "nvidia/NVIDIA-Nemotron-3.5-Super-VL"

resp = client.chat.completions.create(model=MODEL, messages=[{"role": "user", "content": "Hello"}], max_tokens=500)

More detail, including Node, LangChain and LiteLLM: switching OpenAI-compatible providers.

FAQ

Which is cheaper, Nemotron 3.5 Super VL or GPT-OSS 120B on Groq?

It depends on the shape of the workload: Nemotron 3.5 Super VL is cheaper for generation-heavy, GPT-OSS 120B on Groq for chat assistant and long prompts or rag. The table above uses list prices: Nemotron 3.5 Super VL $0.20 / 1M tokens input, $0.65 / 1M tokens output; GPT-OSS 120B on Groq $0.15 / 1M tokens input, $0.75 / 1M tokens output.

Can I switch from GPT-OSS 120B on Groq to Nemotron 3.5 Super VL without rewriting code?

Yes, if you call it through an OpenAI-compatible client. Change the base URL to https://api.inferenceapis.com/v1, swap the API key, and set the model to nvidia/NVIDIA-Nemotron-3.5-Super-VL. Because it is a different model, re-run your prompts and evaluations before moving production traffic.

What limits apply to GPT-OSS 120B on Groq?

Free tier: 30 requests/min, 1,000 requests/day, 8,000 tokens/min, 200,000 tokens/day. Developer-tier upgrades were paused when we checked (Sep 2026). On Inference APIs there are no per-minute or per-day request or token caps; usage draws on a prepaid balance.

Why does Nemotron 3.5 Super VL use more output tokens than the visible answer?

It is a reasoning model: it thinks before it answers and the thinking is billed as output tokens. Budget for that in output-heavy workloads, and set max_tokens to a few hundred or more so the answer is not cut off.

Spotted a price or limit that has changed? Tell us and we will re-check the provider page.