GPT 5 Mini
LiveOpenAI400K context · Text, Tools, ReasoningBenchmark price · $0.25 input / $2 output per 1M tokens
Best discount now75.3%offYou pay 24.7% of reference.
Median discount50.0%offAcross 53 live offers.
Realized · 7 days75.4%avgRequest-weighted average.
Requests · 24h4,31153 offers from 26 sellers.
Current offers
53 of 75 offers
Availability
Providers
ProviderDiscountPriceLatencyUptimeCacheSold
OpenAI
75%
$0.0617 in
$0.49 out
916ms
86.7%
39.7%
$7
OpenAI
75%
$0.0617 in
$0.49 out
916ms
86.7%
39.7%
$0.047
OpenAI
75%
$0.0617 in
$0.49 out
916ms
86.7%
39.7%
$0.020
OpenAI
75%
$0.0617 in
$0.49 out
916ms
86.7%
39.7%
$0.015
OpenAI
75%
$0.0617 in
$0.49 out
916ms
86.7%
39.7%
$0.081
OpenAI
75%
$0.0617 in
$0.49 out
916ms
86.7%
39.7%
-
OpenAI
75%
$0.0617 in
$0.49 out
916ms
86.7%
39.7%
$0.032
OpenAI
75%
$0.0617 in
$0.49 out
916ms
86.7%
39.7%
-
OpenAI
75%
$0.0617 in
$0.49 out
916ms
86.7%
39.7%
-
OpenAI
75%
$0.0617 in
$0.49 out
916ms
86.7%
39.7%
$0.001
Total
Cumulative offers
Sold
$7
Discount trend
Realized · 7 days77.2%−22.0 pts vs last week
Best, twice dailyMedian 50.0%
Recent fills
23:392,632 tokensOpenAI direct75.3%
23:39466 tokensOpenAI direct75.4%
23:39966 tokensOpenAI direct75.3%
23:38688 tokensOpenAI direct75.3%
23:38605 tokensOpenAI direct75.5%
23:38668 tokensOpenAI direct75.4%
23:372,418 tokensOpenAI direct75.3%
23:372,247 tokensOpenAI direct75.3%
23:37554 tokensOpenAI direct75.3%
23:37549 tokensOpenAI direct75.3%
23:37786 tokensOpenAI direct75.3%
23:37347 tokensOpenAI direct75.1%
23:37791 tokensOpenAI direct75.2%
23:352,377 tokensOpenAI direct75.3%
23:351,675 tokensOpenAI direct75.3%
23:3413,550 tokensOpenAI direct75.3%
23:34473 tokensOpenAI direct75.2%
23:347,442 tokensOpenAI direct75.3%
23:342,622 tokensOpenAI direct75.3%
23:34497 tokensOpenAI direct75.2%
Times in UTCSettled on Base in USDC.
Performance by provider route · 24h
Measured on Surplus traffic| Route | p50 latency | p95 latency | Throughput | Success rate | ShareShare of traffic |
|---|---|---|---|---|---|
| OpenAI direct | 4.11 s | 18.42 s | - | 86.7% | 100% |
| Uncensored AI direct | - | - | - | 14.8% | 0% |
OpenAI direct100% of traffic
86.7% success
Uncensored AI direct0% of traffic
14.8% 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 ↗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
- seedintegerDeterministic sampling
- 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
- frequency_penaltynumberPenalises tokens by how often they appeared
- presence_penaltynumberPenalises tokens that appeared at all
- logit_biasobjectPer-token bias on the logits
- logprobsbooleanReturn token log probabilities
- top_logprobsintegerHow many top tokens to return probabilities for
Context window 400K tokens · Max output 128K tokensOthers are passed through; most providers ignore what they don’t support. Parameter compatibility ↗
from openai import OpenAI client = OpenAI( api_key="inf_your_key_here", base_url="$SURPLUS_BASE_URL" ) response = client.chat.completions.create( model="gpt-5-mini", messages=[{"role": "user", "content": "Hello!"}] )
SURPLUS_BASE_URL
https://api.surplusintelligence.ai/v1