Nemotron 3.5 Super VL 120B A12B
trustedtokens/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B · family nemotron · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image.
This is a text model — providers price it per unit, not per token, so models.dev carries no token price (fields read “—”). See TrustedTokens’s docs for per-unit rates.
- Provider
- TrustedTokens (
trustedtokens) - Kind
- text (outputs text)
- Context
- 262,144 tokens
- Max output
- 8,192 tokens
- Capabilities
- tools reasoning text image
Same model, other providers
“Nemotron 3.5 Super VL 120B A12B” is offered by 7 providers — cheapest-effective first. Nvidia is the cheapest at $0.00 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Nvidia | free | free | $0.00 | 1M |
| InferAll | free | free | $0.00 | 1M |
| Pioneer | $0.08 | $0.45 | $0.17 | 262k |
| Together AI | $0.15 | $0.5 | $0.24 | 262k |
| Nebius Token Factory | $0.3 | $0.9 | $0.45 | 1M |
| Thinking Machines | $0.57 | $1.44 | $0.79 | 262k |
| TrustedTokens (this) | — | — | — | 262k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at TrustedTokens 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","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):