Loading model details
Open weights, run inside a TEE. Inference happens sealed, so the prompt stays inside the enclave.
Released
Apr 2025Modalities
Text · Tool callingOffered by miners now
-5.0% offeredIn
Cached
Out
per Mtok*
Create an API key and set it as SAYGM_API_KEY in your terminal.
curl "https://api.saygm.com/v1/chat/completions" \
-H "Authorization: Bearer $SAYGM_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen3-32b-tee",
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
}'SayGM's price offered by miners now for qwen3-32b-tee next to the published list price — 5.0% off.
Compare every Qwen model across providers in our Qwen pricing breakdown.
| Dimension | SayGM price | List price |
|---|---|---|
| Input | $0.0988per Mtok | $0.104 |
| Output | $0.3952per Mtok | $0.416 |
| Cache read | $0.00988per Mtok | $0.0104 |
What buyers have actually paid on this model recently, across every provider and cache hits.
Input
$0.060
$0.104Cached input
$0.0069
$0.0104Output
$0.269
$0.416Requests 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 168 windows: 82 requests and 6,934 input-side tokens, short of the 2,000,000 tokens the window walks for. Most recent window closed 2026-10-10 16:28 UTC.
Every provider currently serving this model, ranked by discount.
No provider is currently serving this model.
Measured on the requests SayGM routed to this model.
Explore the Qwen lab and compare related models.
The best price offered by miners now for qwen3-32b-tee on SayGM is $0.099 per million input tokens and $0.395 per million output tokens.
SayGM's best price offered by miners now for qwen3-32b-tee is 5.0% off list price.
Yes. qwen3-32b-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.
Fixed-seed suites SayGM runs against this model.
No benchmark run has been published for this model.
What is private AI inference? →