Loading model details
Open weights, run inside a TEE. Inference happens sealed, so the prompt stays inside the enclave.
Released
Aug 2026Modalities
Text · Tool calling · Image inputOffered by miners now
-2.1%In
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": "qwen3.8-27b-tee",
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
}'SayGM's price offered by miners now for qwen3.8-27b-tee next to list price — 2.1% off.
Compare every Qwen model across providers in our Qwen pricing breakdown.
| Dimension | SayGM price | List price |
|---|---|---|
| Input | $0.43054per Mtok | $0.44 |
| Output | $3.22905per Mtok | $3.30 |
| Cache read | $0.043054per Mtok | $0.044 |
What buyers have actually paid on this model recently, across every provider and cache hits.
Input
$0.43
$0.44Cached input
up to $0.044
Output
$3.23
$3.30Requests 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: 8 requests and 449 input-side tokens, short of the 2,000,000 tokens the window walks for. Most recent window closed 2026-10-30 15:41 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.
No requests were served on this model across the last 12 windows.
Fixed-seed suites SayGM runs against this model.
Explore the Qwen lab and compare related models.
The best price offered by miners now for qwen3.8-27b-tee on SayGM is $0.43 per million input tokens and $3.23 per million output tokens.
SayGM's best price offered by miners now for qwen3.8-27b-tee is 2.1% off list price.
Yes. qwen3.8-27b-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.
What is private AI inference? →