Loading model details
Open weights, run inside a TEE. Inference happens sealed, so the prompt stays inside the enclave.
Released
Apr 2026Modalities
Text · Tool calling · Image inputBest price on SayGM
-55.1%In
Cached
Out
per Mtok*
Create an API key and set it as GM_API_KEY in your terminal.
curl "https://api.saygm.com/v1/chat/completions" \
-H "Authorization: Bearer $GM_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "nemotron-3-nano-omni-30b-tee",
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
}'SayGM's best available rate for nemotron-3-nano-omni-30b-tee next to the published list price — 55.1% off.
| Dimension | SayGM price | List price |
|---|---|---|
| Input | $0.01098825per Mtok | $0.0245 |
| Output | $0.0438633per Mtok | $0.0978 |
| Cache read | $0.001098825per Mtok | $0.00245 |
What buyers have actually paid on this model recently, across every provider and cache hits.
Input
$0.0110
$0.0245Cached input
$0.00110
$0.00245Output
$0.0439
$0.0978Requests are load balanced across every provider serving this model, each offering its own rate, so what you pay is a blend rather than a single number. These are the blended rates actually paid — priced at what a provider offered, capped at list.
Measured over 16 windows: 1,109 requests and 2,011,707 input-side tokens. Most recent window closed 2026-09-25 01:02 UTC.
Every provider currently serving this model, ranked by discount.
| Provider | Discount | In | Out |
|---|---|---|---|
| Provider 1 | 55.1% off |
The best available rate for nemotron-3-nano-omni-30b-tee on SayGM right now is $0.0110 per million input tokens and $0.0439 per million output tokens.
SayGM's best available rate for nemotron-3-nano-omni-30b-tee is 55.1% off list price.
Yes. nemotron-3-nano-omni-30b-tee is served on SayGM's OpenAI-compatible chat/completions surface, so an unmodified OpenAI SDK pointed at SayGM's base URL works with it.
| $0.0110 |
| $0.0439 |
Measured on the requests SayGM routed to this model.
Fixed-seed suites SayGM runs against this model.
What is private AI inference? →