GPT-5.6 Sol
LiveOpenAI1.1M context · Text, Vision, Tools, Reasoning
Best discount now95.1%offYou pay 4.9% of reference.
Median discount65.3%offAcross 77 live offers.
Realized · 7 daysNot enough dataIt fills in after the nightly update.
Requests · 24h28,15577 offers from 43 sellers.
Current offers
77 of 957 offers
Availability
Providers
ProviderDiscountPriceLatencyUptimeOfferedSoldRemaining
InferHub ?
95%
$0.0988 in
$0.49 out
10.1s
84.8%
$1B
$0.002
$1B
InferHub ?
95%
$0.0990 in
$0.49 out
10.1s
84.8%
$115
$0.185
$115
InferHub ?
95%
$0.10 in
$0.50 out
10.1s
84.8%
∞
$47
∞
InferHub ?
93%
$0.14 in
$0.70 out
10.1s
84.8%
$500
$2
$498
InferHub ?
93%
$0.14 in
$0.70 out
10.1s
84.8%
∞
$14
∞
InferHub ?
90%
$0.20 in
$1.00 out
10.1s
84.8%
$888
$0.016
$888
InferHub ?
90%
$0.20 in
$1.00 out
10.1s
84.8%
∞
$0.447
∞
InferHub ?
90%
$0.20 in
$1.00 out
10.1s
84.8%
$888
$0.001
$888
InferHub ?
90%
$0.20 in
$1.00 out
10.1s
84.8%
∞
$0.307
∞
InferHub ?
90%
$0.20 in
$1.00 out
10.1s
84.8%
∞
-
∞
Total
Cumulative offers
Offered
∞
Sold
$380
Remaining
∞
Discount trend
Realized · 7 daysNo trend yet.It fills in after the nightly update.
Recent fills
17:10140,240 tokensOpenAI direct80.2%
17:1016 tokensVenice AI direct13.9%
17:09107,375 tokensOpenAI direct80.2%
17:0927,300 tokensOpenRouter60.0%
17:09107,419 tokensOpenAI direct80.2%
17:09139,783 tokensOpenAI direct80.2%
17:0926,407 tokensOpenRouter60.0%
17:0936,266 tokensOpenRouter60.0%
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 | 3.04 s | 45.32 s | 99 tok/s | 96.5% | 69% |
| InferHub | 18.42 s | 82.59 s | 54 tok/s | 84.8% | 19% |
| OpenRouter | 3.04 s | 24.87 s | 99 tok/s | 99.3% | 8% |
| Venice AI direct | 1.67 s | 5.55 s | — | 98.0% | 4% |
OpenAI direct69% of traffic
96.5% success
InferHub19% of traffic
84.8% success
OpenRouter8% of traffic
99.3% success
Venice AI direct4% of traffic
98.0% 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-5.6-sol", "messages": [{"role": "user", "content": "Hello"}] }'
SURPLUS_BASE_URL
https://api.surplusintelligence.ai/v1