Loading model details
DeepSeek
Open weights, run inside a TEE. Inference happens sealed, so the prompt stays inside the enclave.
Released
Dec 2025Modalities
Text · Tool callingBest price on SayGM
-51.1%In
Cached
Out
per Mtok*
SayGM's best available rate for deepseek-v3.2-tee next to the published list price — 51.1% off.
| Dimension | SayGM price | List price |
|---|---|---|
| Input | $0.4885per Mtok | $1.00 |
| Output | $0.4885per Mtok | $1.00 |
| Cache read | $0.04885per Mtok | $0.10 |
What buyers have actually paid on this model recently, across every provider and cache hits.
Input
$0.69
$1.00Cached input
$0.07
$0.10Output
$0.67
$1.00Requests 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 5 windows: 1,538 requests and 2,597,287 input-side tokens. Most recent window closed 2026-09-16 15:09 UTC.
Every provider currently serving this model, ranked by discount.
| Provider | Discount | In | Out |
|---|---|---|---|
| Provider 1 | 51.1% off | $0.49 | $0.49 |
| Provider 2 | 7.0% off | $0.93 | $0.93 |
Measured on the requests SayGM routed to this model.
Fixed-seed suites SayGM runs against this model.
The best available rate for deepseek-v3.2-tee on SayGM right now is $0.49 per million input tokens and $0.49 per million output tokens.
SayGM's best available rate for deepseek-v3.2-tee is 51.1% off list price.
Yes. deepseek-v3.2-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.