Skip to main content

Hermes 3 Llama 3.1 405b

Live
Meta128K context · Text
Use this model
Best discount now54.9%offYou pay 45.1% of reference.
Median discount26.0%offAcross 39 live offers.
Realized · 7 daysNot enough dataIt fills in after the nightly update.
Requests · 24h32839 offers from 25 sellers.
Current offers
39 of 202 offers
Availability
Providers
ProviderDiscountPriceLatencyUptimeOfferedSoldRemaining
Venice AI
50%
$0.50 in
$0.50 out
-
96.6%
∞
$0.181
Venice AI
50%
$0.50 in
$0.50 out
-
96.6%
∞
-
Venice AI
40%
$0.60 in
$0.60 out
-
96.6%
∞
-
Morpheus ?
26%
$0.74 in
$0.74 out
-
-
$5
-
Morpheus ?
26%
$0.74 in
$0.74 out
-
-
$5
-
Morpheus ?
26%
$0.74 in
$0.74 out
-
-
$5
-
Morpheus ?
26%
$0.74 in
$0.74 out
-
-
$5
-
Morpheus ?
26%
$0.74 in
$0.74 out
-
-
$5
-
Mordiem
54%
$0.44 in
$1.20 out
-
-
∞
-
Venice AI
15%
$0.85 in
$0.85 out
-
96.6%
∞
-
Total
Cumulative offers
Offered
∞
Sold
$0.181
Remaining

Discount trend

Realized · 7 days
No trend yet.It fills in after the nightly update.

Recent fills

19:5823 tokensVenice AI direct52.2%
18:5823 tokensVenice AI direct52.2%
17:5723 tokensVenice AI direct52.2%
16:5823 tokensVenice AI direct52.2%
16:1829 tokensUncensored AI direct13.8%
16:1828 tokensVenice AI direct50.0%
16:1828 tokensVenice AI direct50.0%
16:1860 tokensVenice AI direct51.7%
Settled on Base in USDC.

Performance by provider route · 24h

Measured on Surplus traffic
Venice AI direct100% of traffic
96.6% success
p50 1.67 s · p95 4.11 s · —
Use this model

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": "hermes-3-llama-3.1-405b",
    "messages": [{"role": "user",
                  "content": "Hello"}]
  }'

SURPLUS_BASE_URL
https://api.surplusintelligence.ai/v1

Related models