GPT-6 Luna vs Nemotron 3.5 Super VL
As of November 12, 2026, GPT-6 Luna costs 23% more per input token than Nemotron 3.5 Super VL ($0.10 vs $0.081 per 1M) and has a 922K-token context window versus 1M.
GPT-6 Luna vs Nemotron 3.5 Super VL side by side
| GPT-6 Luna | Nemotron 3.5 Super VL | |
|---|---|---|
| Input, per 1M tokens | $0.10 | $0.081 |
| Output, per 1M tokens | $0.50 | $0.4725 |
| Cache read, per 1M tokens | $0.01 | $0.0135 |
| Cache write, per 1M tokens | $0.125 | – |
| Context window | 922,000 tokens | 1,048,576 tokens |
| Max output | 128,000 tokens | 235,929 tokens |
| Image input | Yes | Yes |
| Tool calling | Yes | Yes |
| Structured output (JSON) | Yes | Yes |
| Prompt caching | Yes | Yes |
| Reasoning | Yes | Yes |
| Providers on LiteLLM | 13 | 2 |
| Price shown is from | OpenAI | Kyma API |
| Added to LiteLLM | September 22, 2026 | October 30, 2026 |
Cheapest provider for each
- GPT-6 Luna: OpenAI at $0.10 input and $0.50 output per 1M tokens (
gpt-6-luna) - Nemotron 3.5 Super VL: Kyma API at $0.081 input and $0.4725 output per 1M tokens (
kyma/nemotron-3.5-super-vl)
When to pick which
Pick GPT-6 Luna for
- Supports PDF input, which Nemotron 3.5 Super VL doesn't list.
- Available from 13 providers through LiteLLM, vs 2.
Pick Nemotron 3.5 Super VL for
- Costs 19% less per input token: $0.081 vs $0.10 per 1M.
- Larger context window: 1,048,576 vs 922,000 tokens.
From differences in the data above only; where the data is equal, no reason is given.
Call GPT-6 Luna or Nemotron 3.5 Super VL 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!"}]
# GPT-6 Luna
response = completion(model="gpt-6-luna", messages=messages)
# Nemotron 3.5 Super VL
response = completion(model="kyma/nemotron-3.5-super-vl", messages=messages)
# GPT-6 Luna, falling back to Nemotron 3.5 Super VL if the call fails
response = completion(model="gpt-6-luna", messages=messages, fallbacks=["kyma/nemotron-3.5-super-vl"])FAQ
Which is cheaper, GPT-6 Luna or Nemotron 3.5 Super VL?
Nemotron 3.5 Super VL is cheaper at 3 input tokens per output token: $0.1789 per 1M tokens blended ($0.081 input, $0.4725 output), versus $0.20 ($0.10 and $0.50) for GPT-6 Luna, as of November 12, 2026.
Which has the larger context window, GPT-6 Luna or Nemotron 3.5 Super VL?
Nemotron 3.5 Super VL has the larger context window: 1,048,576 tokens, versus 922,000 for GPT-6 Luna.
Can I switch from GPT-6 Luna to Nemotron 3.5 Super VL without changing my code?
Yes. Through LiteLLM both use the OpenAI format, so switching means changing the model name from "gpt-6-luna" to "kyma/nemotron-3.5-super-vl", or pointing a LiteLLM gateway model alias at the other model. You can also use one as a fallback for the other.