Claude Sonnet 4.6
LiveAnthropic1M context · Text, Vision, Tools, Reasoning
Best discount now97.3%offYou pay 2.7% of reference.
Median discount33.0%offAcross 82 live offers.
Realized · 7 daysNot enough dataIt fills in after the nightly update.
Requests · 24h3,43082 offers from 57 sellers.
Current offers
82 of 579 offers
Availability
Providers
ProviderDiscountPriceLatencyUptimeOfferedSoldRemaining
InferHub ?
97%
$0.0813 in
$0.41 out
-
96.0%
∞
-
∞
InferHub ?
97%
$0.0813 in
$0.41 out
-
96.0%
$115
-
$115
InferHub ?
97%
$0.0813 in
$0.41 out
-
96.0%
$1B
-
$1B
InferHub ?
97%
$0.0828 in
$0.41 out
-
96.0%
∞
-
∞
InferHub ?
96%
$0.12 in
$0.60 out
-
96.0%
$567
-
$567
InferHub ?
96%
$0.12 in
$0.60 out
-
96.0%
$567
-
$567
InferHub ?
96%
$0.12 in
$0.60 out
-
96.0%
$567
-
$567
InferHub ?
90%
$0.30 in
$1.50 out
-
96.0%
∞
$0.095
∞
InferHub ?
90%
$0.30 in
$1.50 out
-
96.0%
∞
-
∞
InferHub ?
90%
$0.30 in
$1.50 out
-
96.0%
∞
-
∞
Total
Cumulative offers
Offered
∞
Sold
$266
Remaining
∞
Discount trend
Realized · 7 daysNo trend yet.It fills in after the nightly update.
Recent fills
17:094,433 tokensVenice AI direct60.6%
17:094,396 tokensVenice AI direct60.6%
17:0913,527 tokensVenice AI direct60.6%
17:0916,570 tokensVenice AI direct60.6%
17:08324 tokensVenice AI direct60.6%
17:0716,505 tokensVenice AI direct60.6%
17:0675,093 tokensVenice AI direct60.6%
17:0513,652 tokensVenice AI direct60.6%
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 |
|---|---|---|---|---|---|
| OpenRouter | 5.55 s | 111.50 s | 54 tok/s | 98.2% | 70% |
| Venice AI direct | 3.04 s | 274.34 s | 40 tok/s | 98.9% | 29% |
| InferHub | 4.11 s | — | — | 96.0% | 1% |
OpenRouter70% of traffic
98.2% success
Venice AI direct29% of traffic
98.9% success
InferHub1% of traffic
96.0% 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": "claude-sonnet-4.6", "messages": [{"role": "user", "content": "Hello"}] }'
SURPLUS_BASE_URL
https://api.surplusintelligence.ai/v1