Skip to main content

DeepSeek V4.1 Flash 1017

Live
DeepSeek1M context · Text, Vision, Tools, Reasoning
Use this model
Best discount now85.7%offYou pay 14.3% of reference.
Median discount44.0%offAcross 14 live offers.
Realized · 7 days78.9%avgRequest-weighted average.
Requests · 24h90,61314 offers from 7 sellers.
Current offers
13 of 18 offers
Availability
Providers
ProviderDiscountPriceLatencyUptimeSold
OpenRouter
85%
$0.0435 in
$0.17 out
3.0s
97.6%
$178
OpenRouter
85%
$0.0435 in
$0.17 out
3.0s
97.6%
$30
Venice AI
45%
$0.16 in
$0.65 out
4.1s
99.5%
$7
Venice AI
43%
$0.17 in
$0.67 out
4.1s
99.5%
$0.046
Alibaba DashScope — China
43%
$0.17 in
$0.67 out
5.5s
99.0%
-
Venice AI
43%
$0.17 in
$0.67 out
4.1s
99.5%
-
Alibaba DashScope — China
43%
$0.17 in
$0.67 out
5.5s
99.0%
-
Venice AI
43%
$0.17 in
$0.67 out
4.1s
99.5%
$0.123
Venice AI
43%
$0.17 in
$0.67 out
4.1s
99.5%
-
Alibaba DashScope — China
43%
$0.17 in
$0.67 out
5.5s
99.0%
-
Total
Cumulative offers
Sold
$215

Discount trend

Realized · 7 days
90.0%
Best, twice dailyMedian 44.0%

Recent fills

06:40821,859 tokensOpenRouter85.5%
06:40323,605 tokensOpenRouter85.5%
06:40205,846 tokensOpenRouter85.5%
06:39313,291 tokensOpenRouter85.5%
06:39437 tokensOpenRouter85.5%
06:391,739 tokensOpenRouter85.5%
06:39555 tokensOpenRouter85.6%
06:39478 tokensOpenRouter85.5%
06:3914,637 tokensOpenRouter85.7%
06:39821,423 tokensOpenRouter85.5%
06:39165,315 tokensOpenRouter85.5%
06:396,291 tokensOpenRouter85.5%
06:381,431 tokensOpenRouter85.6%
06:38203,528 tokensOpenRouter85.5%
06:38820,859 tokensOpenRouter85.5%
06:3898,937 tokensOpenRouter85.5%
06:38139,778 tokensOpenRouter85.5%
06:3814,308 tokensOpenRouter85.5%
06:38478 tokensOpenRouter85.5%
06:37117,136 tokensVenice AI direct45.6%
Settled on Base in USDC.Times in UTC

Performance by provider route · 24h

Measured on Surplus traffic
OpenRouter62% of traffic
97.6% success
p50 5.55 s · p95 61.18 s · 180 tok/s
Alibaba DashScope — China36% of traffic
99.0% success
p50 7.49 s · p95 45.32 s · 180 tok/s
Venice AI direct2% of traffic
99.5% success
p50 5.55 s · p95 24.87 s · 180 tok/s
Use this model

Change your base URL.
Keep your code.

Any OpenAI-compatible client works. Add /min30 to the path to only buy at 30% off or better.

Read the quickstart ↗
Build with agents
curl $SURPLUS_BASE_URL/chat/completions \
  -H "Authorization: Bearer $SURPLUS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4.1-flash-1017",
    "messages": [{"role": "user",
                  "content": "Hello"}]
  }'

SURPLUS_BASE_URL
https://api.surplusintelligence.ai/v1

Related models