GPT-5.5
LiveOpenAI1M context · Text, Vision, Tools, Reasoning
Best discount now98.8%offYou pay 1.2% of reference.
Median discount60.5%offAcross 126 live offers.
Realized · 7 daysNot enough dataIt fills in after the nightly update.
Requests · 24h6,028126 offers from 66 sellers.
Current offers
126 of 1056 offers
Availability
Providers
ProviderDiscountPriceLatencyUptimeOfferedSoldRemaining
InferHub ?
98%
$0.0613 in
$0.37 out
13.6s
86.5%
∞
$32
∞
InferHub ?
98%
$0.0613 in
$0.37 out
13.6s
86.5%
$1B
$0.221
$1B
InferHub ?
98%
$0.0645 in
$0.39 out
13.6s
86.5%
∞
$3
∞
InferHub ?
97%
$0.11 in
$0.67 out
13.6s
86.5%
∞
$13
∞
InferHub ?
97%
$0.11 in
$0.67 out
13.6s
86.5%
∞
-
∞
InferHub ?
97%
$0.11 in
$0.67 out
13.6s
86.5%
∞
$0.006
∞
InferHub ?
97%
$0.11 in
$0.67 out
13.6s
86.5%
$888
$0.001
$888
InferHub ?
97%
$0.11 in
$0.67 out
13.6s
86.5%
$888
$0.005
$888
InferHub ?
97%
$0.11 in
$0.68 out
13.6s
86.5%
$567
-
$567
InferHub ?
97%
$0.11 in
$0.68 out
13.6s
86.5%
$567
-
$567
Total
Cumulative offers
Offered
∞
Sold
$110
Remaining
∞
Discount trend
Realized · 7 daysNo trend yet.It fills in after the nightly update.
Recent fills
17:1063 tokensOpenAI direct93.7%
17:094,341 tokensOpenAI direct93.8%
17:093,233 tokensOpenAI direct93.8%
17:093,223 tokensOpenAI direct93.8%
17:0966 tokensOpenAI direct93.7%
17:09739 tokensVenice AI direct50.0%
17:0960 tokensOpenAI direct93.8%
17:0819 tokensOpenAI direct93.9%
Settled 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 | 1.24 s | 18.42 s | 99 tok/s | 97.1% | 67% |
| Venice AI direct | 2.25 s | 13.64 s | — | 67.1% | 22% |
| InferHub | 61.18 s | 82.59 s | — | 86.5% | 11% |
OpenAI direct67% of traffic
97.1% success
Venice AI direct22% of traffic
67.1% success
InferHub11% of traffic
86.5% 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 ↗curl $SURPLUS_BASE_URL/chat/completions \ -H "Authorization: Bearer $SURPLUS_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "gpt-5.5", "messages": [{"role": "user", "content": "Hello"}] }'
SURPLUS_BASE_URL
https://api.surplusintelligence.ai/v1