GPT-6 Luna
LiveOpenAI1.1M context · Text, Vision, Tools, Reasoning
Best discount now98.1%offYou pay 1.9% of reference.
Median discount80.0%offAcross 55 live offers.
Realized · 7 daysNot enough dataIt fills in after the nightly update.
Requests · 24h368,86355 offers from 32 sellers.
Current offers
55 of 107 offers
Availability
Providers
ProviderDiscountPriceLatencyUptimeOfferedSoldRemaining
InferHub ?
98%
$0.00187 in
$0.00936 out
10.1s
81.5%
∞
$0.271
∞
InferHub ?
98%
$0.00187 in
$0.00936 out
10.1s
81.5%
∞
$12
∞
InferHub ?
98%
$0.00187 in
$0.00937 out
10.1s
81.5%
∞
$3
∞
InferHub ?
97%
$0.00233 in
$0.0116 out
10.1s
81.5%
∞
$5
∞
InferHub ?
97%
$0.00233 in
$0.0116 out
10.1s
81.5%
∞
$2
∞
InferHub ?
97%
$0.00233 in
$0.0116 out
10.1s
81.5%
∞
$1
∞
InferHub ?
97%
$0.00233 in
$0.0116 out
10.1s
81.5%
∞
$0.933
∞
InferHub ?
97%
$0.00233 in
$0.0116 out
10.1s
81.5%
∞
$0.529
∞
InferHub ?
97%
$0.00269 in
$0.0134 out
10.1s
81.5%
∞
$0.107
∞
InferHub ?
97%
$0.00274 in
$0.0137 out
10.1s
81.5%
$1B
$0.004
$1B
Total
Cumulative offers
Offered
∞
Sold
$623
Remaining
∞
Discount trend
Realized · 7 daysNo trend yet.It fills in after the nightly update.
Recent fills
17:101,985 tokensOpenAI direct82.3%
17:102,622 tokensOpenAI direct82.3%
17:10887 tokensOpenAI direct81.9%
17:101,232 tokensOpenRouter59.9%
17:10133,365 tokensOpenAI direct82.3%
17:103,839 tokensOpenAI direct82.2%
17:104,035 tokensVenice AI direct43.1%
17:103,630 tokensOpenAI direct82.3%
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 | 13.64 s | 99 tok/s | 96.3% | 89% |
| InferHub | 13.64 s | 61.18 s | 180 tok/s | 81.5% | 6% |
| OpenRouter | 4.11 s | 13.64 s | 99 tok/s | 89.4% | 4% |
| Venice AI direct | 4.11 s | 45.32 s | — | 94.3% | 1% |
OpenAI direct89% of traffic
96.3% success
InferHub6% of traffic
81.5% success
OpenRouter4% of traffic
89.4% success
Venice AI direct1% of traffic
94.3% 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-6-luna", "messages": [{"role": "user", "content": "Hello"}] }'
SURPLUS_BASE_URL
https://api.surplusintelligence.ai/v1