Nemotron 3.5 Super VL 120B A12B
pioneer/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4 · family nemotron · in: text, image, video → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image video.
$0.17
Blended $/1M (3:1)
$0.08
Input $/1M
$0.45
Output $/1M
$0.53
1M in + 1M out
$0.04 −50%
Cache read $/1M
#1532 of 8,487
Cheapest rank
- Provider
- Pioneer (
pioneer) - Kind
- text (outputs text)
- Context
- 262,144 tokens
- Max output
- 4,096 tokens
- Capabilities
- tools reasoning text image video
Same model, other providers
“Nemotron 3.5 Super VL 120B A12B” is offered by 3 providers — cheapest-effective first. Nvidia is the cheapest at $0.00 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Nvidia | free | free | $0.00 | 1M |
| Pioneer (this) | $0.08 | $0.45 | $0.17 | 262k |
| Nebius Token Factory | $0.3 | $0.9 | $0.45 | 1M |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Pioneer and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):