GPT-5.4
LiveOpenAI1M context · Text, Vision, Tools, Reasoning
Best discount now98.2%offYou pay 1.8% of reference.
Median discount45.0%offAcross 101 live offers.
Realized · 7 daysNot enough dataIt fills in after the nightly update.
Requests · 24h6,627101 offers from 52 sellers.
Current offers
100 of 1012 offers
Availability
Providers
ProviderDiscountPriceLatencyUptimeOfferedSoldRemaining
InferHub ?
98%
$0.0451 in
$0.27 out
7.5s
78.0%
∞
$0.235
∞
InferHub ?
98%
$0.0451 in
$0.27 out
7.5s
78.0%
∞
$0.705
∞
InferHub ?
98%
$0.0452 in
$0.27 out
7.5s
78.0%
∞
$0.007
∞
InferHub ?
98%
$0.0452 in
$0.27 out
7.5s
78.0%
∞
$0.001
∞
InferHub ?
98%
$0.0452 in
$0.27 out
7.5s
78.0%
$888
-
$888
InferHub ?
98%
$0.0452 in
$0.27 out
7.5s
78.0%
$888
-
$888
InferHub ?
98%
$0.0452 in
$0.27 out
7.5s
78.0%
∞
-
∞
InferHub ?
98%
$0.0452 in
$0.27 out
7.5s
78.0%
$1B
-
$1B
InferHub ?
98%
$0.0484 in
$0.29 out
7.5s
78.0%
∞
$0.002
∞
InferHub ?
97%
$0.0563 in
$0.34 out
7.5s
78.0%
$567
-
$567
Total
Cumulative offers
Offered
∞
Sold
$154
Remaining
∞
Discount trend
Realized · 7 daysNo trend yet.It fills in after the nightly update.
Recent fills
17:10566 tokensOpenAI direct95.0%
17:101,669 tokensOpenAI direct95.0%
17:109,314 tokensOpenAI direct95.0%
17:10566 tokensOpenAI direct95.0%
17:0938,715 tokensOpenAI direct95.0%
17:091,666 tokensOpenAI direct95.0%
17:09566 tokensOpenAI direct95.0%
17:091,672 tokensOpenAI direct95.0%
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 | 18.42 s | 111.50 s | 40 tok/s | 97.4% | 89% |
| Venice AI direct | 1.67 s | 111.50 s | — | 52.7% | 7% |
| InferHub | 5.55 s | 24.87 s | — | 78.0% | 4% |
| OpenRouter | — | — | — | 44.4% | 0% |
| Mordiem | — | — | — | 5.0% | 0% |
OpenAI direct89% of traffic
97.4% success
Venice AI direct7% of traffic
52.7% success
InferHub4% of traffic
78.0% success
OpenRouter0% of traffic
44.4% success
Mordiem0% of traffic
5.0% 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-5.4", "messages": [{"role": "user", "content": "Hello"}] }'
SURPLUS_BASE_URL
https://api.surplusintelligence.ai/v1