IN
Use this model Mercury 3
LiveInception1M context · Text, Tools, Reasoning
Best discount now40.0%offYou pay 60.0% of reference.
Median discount32.0%offAcross 7 live offers.
Realized · 7 days18.7%avgRequest-weighted average.
Requests · 24h107 offers from 4 sellers.
Current offers
7 of 10 offers
Availability
Providers
ProviderDiscountPriceLatencyUptimeSold
Venice AI
40%
$0.0600 in
$0.21 out
-
41.9%
-
Venice AI
32%
$0.0680 in
$0.24 out
-
41.9%
-
Venice AI
32%
$0.0680 in
$0.24 out
-
41.9%
-
Venice AI
32%
$0.0680 in
$0.24 out
-
41.9%
-
Venice AI
32%
$0.0680 in
$0.24 out
-
41.9%
-
Venice AI
25%
$0.0750 in
$0.26 out
-
41.9%
-
Venice AI
10%
$0.0897 in
$0.31 out
-
41.9%
-
Total
Cumulative offers
Sold
$0.000
Discount trend
Realized · 7 days33.3%
Best, twice dailyMedian 32.0%
Recent fills
01:4219 tokensVenice AI direct33.3%
00:55153 tokens19.6%
00:3717 tokensVenice AI direct20.0%
00:004,954 tokens19.2%
00:004,945 tokens20.1%
00:0011 tokens0.0%
23:4822 tokens16.7%
23:4839 tokens18.2%
23:39153 tokens19.6%
23:3217 tokens20.0%
Settled on Base in USDC.Times in UTC
Performance by provider route · 24h
Measured on Surplus traffic| Route | p50 latency | p95 latency | Throughput | Success rate | ShareShare of traffic |
|---|---|---|---|---|---|
| Venice AI direct | — | — | — | 41.9% | 100% |
Venice AI direct100% of traffic
41.9% success
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
- stopstring | arrayStop sequences
- 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
- reasoning_effortstringHow hard to think, as a string such as "high"
- reasoningobjectReasoning options as an object, such as {"effort": "high"}
- include_reasoningbooleanStripped before the request reaches the provider
Context window 1M tokens · Max output 131K 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": "mercury-3", "messages": [{"role": "user", "content": "Hello"}] }'
SURPLUS_BASE_URL
https://api.surplusintelligence.ai/v1