Nemotron 3.5 Super VL vs Qwen3 30B A3B
As of November 12, 2026, Nemotron 3.5 Super VL costs 1% more per input token than Qwen3 30B A3B ($0.081 vs $0.08 per 1M) and has a 1M-token context window versus 41K.
Nemotron 3.5 Super VL vs Qwen3 30B A3B side by side
| Nemotron 3.5 Super VL | Qwen3 30B A3B | |
|---|---|---|
| Input, per 1M tokens | $0.081 | $0.08 |
| Output, per 1M tokens | $0.4725 | $0.25 |
| Cache read, per 1M tokens | $0.0135 | – |
| Cache write, per 1M tokens | – | – |
| Context window | 1,048,576 tokens | 40,946 tokens |
| Max output | 235,929 tokens | 16,384 tokens |
| Image input | Yes | – |
| Tool calling | Yes | Yes |
| Structured output (JSON) | Yes | Yes |
| Prompt caching | Yes | – |
| Reasoning | Yes | Yes |
| Providers on LiteLLM | 2 | 11 |
| Price shown is from | Kyma API | GMI Cloud |
| Added to LiteLLM | October 30, 2026 | July 2025 |
Cheapest provider for each
- Nemotron 3.5 Super VL: Kyma API at $0.081 input and $0.4725 output per 1M tokens (
kyma/nemotron-3.5-super-vl) - Qwen3 30B A3B: GMI Cloud at $0.08 input and $0.25 output per 1M tokens (
gmi/Qwen/Qwen3-30B-A3B)
When to pick which
Pick Nemotron 3.5 Super VL for
- Larger context window: 1,048,576 vs 40,946 tokens.
- Returns up to 235,929 tokens per response, vs 16,384.
Pick Qwen3 30B A3B for
- Costs 47% less per output token: $0.25 vs $0.4725 per 1M.
- Available from 11 providers through LiteLLM, vs 2.
From differences in the data above only; where the data is equal, no reason is given.
Call Nemotron 3.5 Super VL or Qwen3 30B A3B 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!"}]
# Nemotron 3.5 Super VL
response = completion(model="kyma/nemotron-3.5-super-vl", messages=messages)
# Qwen3 30B A3B
response = completion(model="gmi/Qwen/Qwen3-30B-A3B", messages=messages)
# Nemotron 3.5 Super VL, falling back to Qwen3 30B A3B if the call fails
response = completion(model="kyma/nemotron-3.5-super-vl", messages=messages, fallbacks=["gmi/Qwen/Qwen3-30B-A3B"])FAQ
Which is cheaper, Nemotron 3.5 Super VL or Qwen3 30B A3B?
Qwen3 30B A3B is cheaper at 3 input tokens per output token: $0.1225 per 1M tokens blended ($0.08 input, $0.25 output), versus $0.1789 ($0.081 and $0.4725) for Nemotron 3.5 Super VL, as of November 12, 2026.
Which has the larger context window, Nemotron 3.5 Super VL or Qwen3 30B A3B?
Nemotron 3.5 Super VL has the larger context window: 1,048,576 tokens, versus 40,946 for Qwen3 30B A3B.
Can I switch from Nemotron 3.5 Super VL to Qwen3 30B A3B without changing my code?
Yes. Through LiteLLM both use the OpenAI format, so switching means changing the model name from "kyma/nemotron-3.5-super-vl" to "gmi/Qwen/Qwen3-30B-A3B", or pointing a LiteLLM gateway model alias at the other model. You can also use one as a fallback for the other.