AA
Use this model Abliterated Large Flash
LiveAbliteration AI1M context · Text, Vision, Tools, ReasoningReference · Venice · $1.25 input / $2.5 output per 1M tokens
Best discount now26.0%offYou pay 74.0% of reference.
Median discount20.0%offAcross 3 live offers.
Realized · 7 days25.7%avgRequest-weighted average.
Requests · 24h113 offers from 3 sellers.
Current offers
3 of 3 offers
Availability
Providers
ProviderDiscountPriceLatencyUptimeSold
Venice AI
25%
$0.93 in
$1.85 out
-
-
$0.002
Venice AI
20%
$1.00 in
$2.00 out
-
-
-
Venice AI
10%
$1.12 in
$2.24 out
-
-
-
Total
Cumulative offers
Sold
$0.002
Discount trend
Realized · 7 days26.9%
Best, twice dailyMedian 20.0%
Recent fills
02:4511 tokensVenice AI direct25.0%
02:45414 tokensVenice AI direct25.8%
02:45384 tokensVenice AI direct26.1%
02:4286 tokensVenice AI direct26.3%
02:4211 tokensVenice AI direct25.0%
02:42393 tokensVenice AI direct26.0%
02:42372 tokensVenice AI direct26.1%
02:4271 tokensVenice AI direct26.9%
02:2847 tokensVenice AI direct25.3%
01:2347 tokensVenice AI direct25.3%
00:1847 tokensVenice AI direct25.3%
Times in UTCSettled on Base in USDC.
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 ↗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
- toolsarrayFunctions the model may call, in the OpenAI format
- tool_choicestring | objectauto, required, none, or one named function
- response_formatobjectJSON mode or a JSON schema for structured output
- structured_outputsbooleanAccepts a JSON schema in response_format
- reasoningobjectReasoning options as an object, such as {"effort": "high"}
Context window 1M tokens · Max output 131K tokensOthers are passed through; most providers ignore what they don’t support. Parameter compatibility ↗
I want you to route every call for "abliteration-abliterated-model-large-flash" through Surplus Intelligence instead of calling the provider directly. Surplus supports the OpenAI Chat Completions API at POST /v1/chat/completions for this model, so this is a base-URL and API-key swap. Please: 1. Use https://api.surplusintelligence.ai/min10/v1 as the base URL. The min10 path requires at least a 10% estimated discount versus the reference price. 2. Authenticate with my Surplus API key from the SURPLUS_API_KEY environment variable. If it is not set, stop and tell me to create one under Surplus → Buy → API keys and export it. Never print, log, or commit the key. 3. Update every place this code creates a client or sends a request for this model. Preserve its request parameters, streaming and tool calls where applicable, timeouts, retries, and response handling. Do not change clients for unrelated models. 4. Make one small test call. Show me the reply and token usage, and report the X-SI-Adapted-Params response header if it is present.