Chutes · Confidential
deepseek-ai/DeepSeek-V3.2-TEE
Open weights, run inside a TEE. Inference happens sealed, so the prompt stays inside the enclave.
- Tool calling: yes
- Image input: yes
Released
Dec 2025Modalities
Text · Tool calling · Image inputBest price on gm
-55.5%In
$1.00$0.44
Cached
$0.50$0.22
Out
$1.00$0.44
per Mtok*
//01
Recent effective price
What buyers have actually paid on this model recently, across every provider and cache hits.
Input
$0.76
$1.00Cached input
$0.37
$0.50Output
$0.73
$1.00How the effective price is calculated
Requests 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: 1,823 requests and 2,045,581 input-side tokens. Most recent window closed 2026-08-11 02:24 UTC.
//02
Who's serving this model
Every provider currently serving this model, ranked by discount.
| Provider | Discount | In | Out |
|---|---|---|---|
| Provider 1 | 55.5% off | $0.44 | $0.44 |
| Provider 2 | 52.5% off | $0.47 | $0.47 |
| Provider 3 | 52.5% off | $0.47 | $0.47 |
| Provider 4 | 4.0% off | $0.96 | $0.96 |
| Provider 5 | — | $1.00 | $1.00 |
//03
Performance
Measured on the requests gm routed to this model.
- Throughput
- 6.2 tok/sover 27,901 requests
- Time to first token
- 2.7 sover 27,914 requests
- Request success rate
- 100.0% over 27,923 requests
4,194 requests · 6,496,521 tokens billed · last 12 windowsWindow closed 2026-08-11 02:24 UTC
//04
Benchmarks
Fixed-seed suites gm runs against this model.
No benchmark run has been published for this model.