Skip to main content

Claude Opus 4.8 Fast

Live
Anthropic1M context · Text, Vision, Tools
Use this model
Best discount now50.9%offYou pay 49.1% of reference.
Median discount35.0%offAcross 24 live offers.
Realized · 7 daysNot enough dataIt fills in after the nightly update.
Requests · 24h52324 offers from 20 sellers.
Current offers
24 of 151 offers
Availability
Providers
ProviderDiscountPriceLatencyUptimeOfferedSoldRemaining
Venice AI
50%
$5.89 in
$29.47 out
679ms
97.7%
∞
$3
Venice AI
50%
$5.91 in
$29.56 out
679ms
97.7%
∞
$0.038
Venice AI
50%
$6.00 in
$30.00 out
679ms
97.7%
∞
-
Venice AI
50%
$6.00 in
$30.00 out
679ms
97.7%
∞
-
Venice AI
50%
$6.00 in
$30.00 out
679ms
97.7%
∞
-
Mordiem
45%
$6.60 in
$33.00 out
-
-
∞
-
CheaperInference ?
45%
$6.60 in
$33.00 out
-
-
∞
-
Mordiem
40%
$7.20 in
$36.00 out
-
-
∞
-
Mordiem
35%
$7.80 in
$39.00 out
-
-
∞
-
Mordiem
35%
$7.80 in
$39.00 out
-
-
∞
-
Total
Cumulative offers
Offered
∞
Sold
$3
Remaining

Discount trend

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

Recent fills

20:0220 tokensVenice AI direct50.7%
19:542,496 tokensVenice AI direct50.7%
19:5236 tokensVenice AI direct50.7%
19:4720 tokensVenice AI direct50.7%
19:4520 tokensVenice AI direct50.7%
19:372,496 tokensVenice AI direct50.7%
19:3665 tokensVenice AI direct50.6%
19:3210 tokensVenice AI direct50.6%
Settled on Base in USDC.

Performance by provider route · 24h

Measured on Surplus traffic
Venice AI direct100% of traffic
97.7% success
p50 916 ms · p95 4.11 s · 99 tok/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": "claude-opus-4-8-fast",
    "messages": [{"role": "user",
                  "content": "Hello"}]
  }'

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

Related models