log inget an API key

DeepSeek-V4.1-Flash (TEE)

DeepSeek

deepseek-v4.1-flash-teeget started →
Confidential

Open weights, run inside a TEE. Inference happens sealed, so the prompt stays inside the enclave.

  • Tool calling: yes
  • Image input: yes

Released

Sep 2026

Modalities

Text · Tool calling · Image input

Best reported price on SayGM

-10.0%

In

$0.30$0.27

Cached

$0.006$0.005

Out

$1.20$1.08

per Mtok*

Call DeepSeek-V4.1-Flash (TEE) from the API

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": "deepseek-v4.1-flash-tee",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ]
}'

SayGM vs. list price

SayGM's best reported rate for deepseek-v4.1-flash-tee next to the published list price — 10.0% off.

Compare every DeepSeek model across providers in our DeepSeek pricing breakdown.

DimensionSayGM priceList price
Input$0.27per Mtok$0.30
Output$1.08per Mtok$1.20
Cache read$0.0054per Mtok$0.006
//01

Recent effective price

What buyers have actually paid on this model recently, across every provider and cache hits.

Input

$0.27

$0.30

Cached input

$0.005

$0.006

Output

$1.08

$1.20

How 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 6 windows: 395 requests and 6,298,855 input-side tokens. Most recent window closed 2026-10-10 03:15 UTC.

//02

Who's serving this model

Every provider currently serving this model, ranked by discount.

ProviderDiscountInOut
Provider 110.0% off$0.27$1.08
//03

Performance

Measured on the requests SayGM routed to this model.

Throughput
51.1 tok/sover 672 requests
Time to first token
2.3 sover 664 requests
Request success rate
100.0% over 32 requests
732 requests · 21,662,383 tokens billed · last 12 windowsWindow closed 2026-10-10 03:15 UTC
//04

Benchmarks

Fixed-seed suites SayGM runs against this model.

GPQA-Diamond2026-10-01
78.1%
100.0% answered · 0.0% refused
MATH-5002026-10-01
94.8%
100.0% answered · 0.0% refused

More from DeepSeek

Explore the DeepSeek lab and compare related models.

DeepSeek-V3.2 (TEE) DeepSeek-V4-Flash-0731 DeepSeek-V4-Flash-0731 (TEE) DeepSeek-V4.1-Flash

Frequently asked questions

How much does deepseek-v4.1-flash-tee cost on SayGM?

The best reported rate for deepseek-v4.1-flash-tee on SayGM is $0.27 per million input tokens and $1.08 per million output tokens.

How much cheaper is SayGM than list price?

SayGM's best reported rate for deepseek-v4.1-flash-tee is 10.0% off list price.

Is deepseek-v4.1-flash-tee OpenAI-compatible on SayGM?

Yes. deepseek-v4.1-flash-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.

Related reading

What is private AI inference? →