Samples: 0
NVIDIA Nemotron 3.5 Super VL: open multimodal mixture-of-experts model, 12B active of 120B total, taking text, images, documents, GUI screenshots and video, built for long-running agents.
No matching public benchmark is available for this model.
Ability score divided by token cost, ranked across measured model routes. Cost uses equal input and output token counts; higher is better value.
| Use this model | ||||||
|---|---|---|---|---|---|---|
| origin | $0.15 | $0.5 | $0.12 | Not measured | Not measured | Plans and tiers |
curl --fail-with-body 'https://api.tokenreply.com/v1/chat/completions' \
-H "Authorization: Bearer $TOKENREPLY_API_KEY" \
-H 'Content-Type: application/json' \
--data '{
"model": "nemotron-3.5-super-vl",
"messages": [
{
"role": "user",
"content": "Reply with hello."
}
]
}'