DeepSeek V4.1 Flash Uncensored
LiveDeepSeek1M context · Text, Tools
Best discount now88.0%offYou pay 12.0% of reference.
Median discount88.0%offAcross 1 live offer.
Realized · 7 days82.4%avgRequest-weighted average.
Requests · 24h851 offer from 1 seller.
Current offers
1 of 1 offers
Availability
Providers
ProviderDiscountPriceLatencyUptimeSold
Uncensored AI
87%
$0.0343 in
$0.26 out
-
-
$0.087
Total
Cumulative offers
Sold
$0.087
Discount trend
Realized · 7 days87.4%
Best, twice dailyMedian 88.0%
Recent fills
03:084,681 tokensUncensored AI direct78.5%
03:084,740 tokensUncensored AI direct84.1%
03:074,841 tokensUncensored AI direct82.8%
03:063,762 tokensUncensored AI direct82.5%
03:062,619 tokensUncensored AI direct82.3%
03:064,173 tokensUncensored AI direct84.4%
03:053,621 tokensUncensored AI direct82.6%
03:04510 tokensUncensored AI direct85.5%
03:04510 tokensUncensored AI direct85.5%
03:04510 tokensUncensored AI direct85.5%
03:04510 tokensUncensored AI direct85.5%
03:04510 tokensUncensored AI direct87.4%
03:033,652 tokensUncensored AI direct78.8%
03:033,842 tokensUncensored AI direct83.3%
03:023,596 tokensUncensored AI direct82.7%
03:00104 tokensUncensored AI direct80.2%
02:5747 tokensUncensored AI direct82.8%
02:5712,000 tokensUncensored AI direct81.2%
02:573,630 tokensUncensored AI direct81.5%
02:553,178 tokensUncensored AI direct86.8%
Settled on Base in USDC.Times in UTC
Performance by provider route · 24h
Measured on Surplus trafficNot enough data yet.Shown once 2 sellers and 20 requests report.
Use this modelChange your base URL.
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
Parameters this model acceptsPOST /v1/chat/completions
- modelstringThis model’s id
- messagesarrayThe conversation, as role and content pairs
- streambooleanSend the answer as server-sent events
- max_tokensintegerMost output tokens to generate
- temperaturenumberSampling temperature
- top_pnumberNucleus sampling
- stopstring | arrayStop sequences
- toolsarrayFunctions the model may call, in the OpenAI format
- tool_choicestring | objectauto, required, none, or one named function
Context window 1M tokens · Max output 393K tokensOthers are passed through; most providers ignore what they don’t support. Parameter compatibility ↗
curl $SURPLUS_BASE_URL/chat/completions \ -H "Authorization: Bearer $SURPLUS_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "deepseek-v4.1-flash-uncensored", "messages": [{"role": "user", "content": "Hello"}] }'
SURPLUS_BASE_URL
https://api.surplusintelligence.ai/v1