Skip to main content

Llama 3.2 3B

Live
Meta128K context · Text, Tools
Use this model
Best discount now95.0%offYou pay 5.0% of reference.
Median discount27.4%offAcross 56 live offers.
Realized · 7 daysNot enough dataIt fills in after the nightly update.
Requests · 24h59156 offers from 39 sellers.
Current offers
56 of 422 offers
Availability
Providers
ProviderDiscountPriceLatencyUptimeOfferedSoldRemaining
OpenRouter
94%
$0.00252 in
$0.0167 out
-
-
$2
-
Mordiem
75%
$0.0125 in
$0.0825 out
-
-
∞
-
OpenRouter
75%
$0.0125 in
$0.0825 out
-
-
∞
-
OpenRouter
60%
$0.0200 in
$0.13 out
-
-
∞
-
OpenRouter
60%
$0.0200 in
$0.13 out
-
-
∞
-
Mordiem
60%
$0.0200 in
$0.13 out
-
-
∞
-
Mordiem
54%
$0.0229 in
$0.15 out
-
-
∞
-
Venice AI
50%
$0.0250 in
$0.17 out
-
99.1%
∞
$0.169
Venice AI
50%
$0.0250 in
$0.17 out
-
99.1%
$210
-
OpenRouter
50%
$0.0250 in
$0.17 out
-
-
∞
-
Total
Cumulative offers
Offered
∞
Sold
$0.170
Remaining

Discount trend

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

Recent fills

20:1015,853 tokensVenice AI direct49.9%
20:0615,851 tokensVenice AI direct49.9%
20:0315,852 tokensVenice AI direct49.9%
20:0315,854 tokensVenice AI direct49.9%
19:5715,854 tokensVenice AI direct49.9%
19:5415,852 tokensVenice AI direct49.9%
19:5315,852 tokensVenice AI direct49.9%
19:5015,853 tokensVenice AI direct49.9%
Settled on Base in USDC.

Performance by provider route · 24h

Measured on Surplus traffic
Venice AI direct100% of traffic
99.1% success
p50 5.55 s · p95 13.64 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": "llama-3.2-3b-instruct",
    "messages": [{"role": "user",
                  "content": "Hello"}]
  }'

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

Related models