Chutes · Confidential
deepseek-ai/DeepSeek-V4-Flash-0731-TEE
Open weights, run inside a TEE. Inference happens sealed, so the prompt stays inside the enclave.
- Tool calling: yes
- Image input: yes
Released
Apr 2026Modalities
Text · Tool calling · Image inputBest price on gm
-52.5%In
$0.14$0.07
Cached
$0.07$0.03
Out
$0.28$0.13
per Mtok*
//01
Recent effective price
What buyers have actually paid on this model recently, across every provider and cache hits.
Input
$0.07
$0.14Cached input
$0.03
$0.07Output
$0.13
$0.28How 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 10 windows: 1,144 requests and 2,068,825 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 | 52.5% off | $0.07 | $0.13 |
| Provider 2 | 4.0% off | $0.13 | $0.27 |
//03
Performance
Measured on the requests gm routed to this model.
- Throughput
- 23.6 tok/sover 4,640 requests
- Time to first token
- 2.5 sover 4,757 requests
- Request success rate
- 98.4% over 4,766 requests
1,258 requests · 3,236,170 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.