Skip to main content

DeepSeek V4 Flash 0731 Fast

Live
DeepSeek1M context · Text, Tools, Reasoning
Use this model
Best discount now53.0%offYou pay 47.0% of reference.
Median discount26.0%offAcross 16 live offers.
Realized · 7 daysNot enough dataIt fills in after the nightly update.
Requests · 24h2316 offers from 9 sellers.
Current offers
16 of 55 offers
Availability
Providers
ProviderDiscountPriceLatencyUptimeOfferedSoldRemaining
Venice AI
53%
$0.16 in
$0.33 out
-
100.0%
∞
-
Mordiem
53%
$0.16 in
$0.33 out
-
-
∞
-
Venice AI
50%
$0.17 in
$0.35 out
-
100.0%
∞
-
Mordiem
50%
$0.17 in
$0.35 out
-
-
∞
-
Venice AI
50%
$0.17 in
$0.35 out
-
100.0%
∞
-
Venice AI
27%
$0.26 in
$0.51 out
-
100.0%
∞
-
Morpheus ?
26%
$0.26 in
$0.52 out
-
-
$5
-
Morpheus ?
26%
$0.26 in
$0.52 out
-
-
$5
-
Morpheus ?
26%
$0.26 in
$0.52 out
-
-
$5
-
Morpheus ?
26%
$0.26 in
$0.52 out
-
-
$5
-
Total
Cumulative offers
Offered
∞
Sold
$0
Remaining

Discount trend

Realized · 7 days
No trend yet.It fills in after the nightly update.

Recent fills

15:582,354 tokensVenice AI direct50.0%
15:36398 tokensVenice AI direct50.0%
15:36328 tokensVenice AI direct50.4%
15:36325 tokensVenice AI direct50.4%
15:36278 tokensVenice AI direct51.1%
15:36132 tokensVenice AI direct50.8%
15:36441 tokensVenice AI direct50.0%
15:36123 tokensVenice AI direct50.0%
Settled on Base in USDC.

Performance by provider route · 24h

Measured on Surplus traffic
Venice AI direct100% of traffic
100.0% success
p50 3.04 s · p95 — · —
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 ↗
curl $SURPLUS_BASE_URL/chat/completions \
  -H "Authorization: Bearer $SURPLUS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4-flash-0731-fast",
    "messages": [{"role": "user",
                  "content": "Hello"}]
  }'

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

Related models