Nvidia Nemotron 3.5 Super VL 120B A12B vs Qwen3 8 27B
As of November 12, 2026, Qwen3 8 27B costs 13% more per input token than Nvidia Nemotron 3.5 Super VL 120B A12B ($0.17 vs $0.15 per 1M) and has a 256K-token context window versus 1M.
Nvidia Nemotron 3.5 Super VL 120B A12B vs Qwen3 8 27B side by side
| Nvidia Nemotron 3.5 Super VL 120B A12B | Qwen3 8 27B | |
|---|---|---|
| Input, per 1M tokens | $0.15 | $0.17 |
| Output, per 1M tokens | $0.50 | $0.50 |
| Cache read, per 1M tokens | $0.02 | $0.08 |
| Cache write, per 1M tokens | – | – |
| Context window | 1,049,000 tokens | 262,144 tokens |
| Max output | 943,718 tokens | 32,768 tokens |
| Image input | Yes | Yes |
| Tool calling | Yes | Yes |
| Structured output (JSON) | Yes | Yes |
| Prompt caching | Yes | Yes |
| Reasoning | Yes | Yes |
| Providers on LiteLLM | 3 | 11 |
| Price shown is from | Weights & Biases | EmpirioLabs AI |
| Added to LiteLLM | October 16, 2026 | August 27, 2026 |
Cheapest provider for each
- Nvidia Nemotron 3.5 Super VL 120B A12B: Weights & Biases at $0.15 input and $0.50 output per 1M tokens (
wandb/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B) - Qwen3 8 27B: EmpirioLabs AI at $0.17 input and $0.50 output per 1M tokens (
empiriolabs/qwen3-8-27b)
When to pick which
Pick Nvidia Nemotron 3.5 Super VL 120B A12B for
- Costs 12% less per input token: $0.15 vs $0.17 per 1M.
- Larger context window: 1,049,000 vs 262,144 tokens.
Pick Qwen3 8 27B for
- Available from 11 providers through LiteLLM, vs 3.
From differences in the data above only; where the data is equal, no reason is given.
Call Nvidia Nemotron 3.5 Super VL 120B A12B or Qwen3 8 27B with LiteLLM
Both use the OpenAI format through LiteLLM, so switching is a model name change. Set each provider's API key in the environment first.
from litellm import completion
messages = [{"role": "user", "content": "Hello!"}]
# Nvidia Nemotron 3.5 Super VL 120B A12B
response = completion(model="wandb/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B", messages=messages)
# Qwen3 8 27B
response = completion(model="empiriolabs/qwen3-8-27b", messages=messages)
# Nvidia Nemotron 3.5 Super VL 120B A12B, falling back to Qwen3 8 27B if the call fails
response = completion(model="wandb/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B", messages=messages, fallbacks=["empiriolabs/qwen3-8-27b"])FAQ
Which is cheaper, Nvidia Nemotron 3.5 Super VL 120B A12B or Qwen3 8 27B?
Nvidia Nemotron 3.5 Super VL 120B A12B is cheaper at 3 input tokens per output token: $0.2375 per 1M tokens blended ($0.15 input, $0.50 output), versus $0.2525 ($0.17 and $0.50) for Qwen3 8 27B, as of November 12, 2026.
Which has the larger context window, Nvidia Nemotron 3.5 Super VL 120B A12B or Qwen3 8 27B?
Nvidia Nemotron 3.5 Super VL 120B A12B has the larger context window: 1,049,000 tokens, versus 262,144 for Qwen3 8 27B.
Can I switch from Nvidia Nemotron 3.5 Super VL 120B A12B to Qwen3 8 27B without changing my code?
Yes. Through LiteLLM both use the OpenAI format, so switching means changing the model name from "wandb/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B" to "empiriolabs/qwen3-8-27b", or pointing a LiteLLM gateway model alias at the other model. You can also use one as a fallback for the other.