Grok 4.5

Live

xAI500K context · Text, Vision, Tools, Reasoning

Use this model

Best discount now89.2%offYou pay 10.8% of reference.

Median discount50.0%offAcross 52 live offers.

Realized · 7 daysNot enough dataIt fills in after the nightly update.

Requests · 24h2,19152 offers from 43 sellers.

Current offers

52 of 370 offers

Availability

Providers

Sort by

ProviderDiscountPriceLatencyUptimeOfferedSoldRemaining

InferHub ?

89%

$0.22 in

$0.65 out

5.5s

100.0%

∞

$0.041

∞

InferHub ?

89%

$0.22 in

$0.65 out

5.5s

100.0%

∞

$0.079

∞

InferHub ?

89%

$0.22 in

$0.65 out

5.5s

100.0%

$115

InferHub ?

89%

$0.22 in

$0.65 out

5.5s

100.0%

∞

$0.346

∞

InferHub ?

88%

$0.23 in

$0.68 out

5.5s

100.0%

∞

$0.025

∞

OpenRouter

86%

$0.28 in

$0.84 out

2.3s

97.2%

∞

$19

∞

InferHub ?

85%

$0.29 in

$0.88 out

5.5s

100.0%

$12

Capminal Gateway

83%

$0.34 in

$1.02 out

∞

OpenRouter

83%

$0.34 in

$1.02 out

2.3s

97.2%

∞

OpenRouter

83%

$0.34 in

$1.02 out

2.3s

97.2%

∞

$0.390

∞

Total

Cumulative offers

Offered

∞

Sold

$28

Remaining

∞

Discount trend

Realized · 7 days

No trend yet.It fills in after the nightly update.

Recent fills

20:09686 tokensVenice AI direct69.7%

20:06671 tokensVenice AI direct69.1%

20:0627,902 tokensOpenRouter86.0%

20:0433,241 tokensOpenRouter86.0%

20:03621 tokensVenice AI direct69.1%

20:02531 tokensVenice AI direct69.1%

20:01527 tokensOpenRouter86.0%

19:5828,741 tokensOpenRouter86.0%

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	2.25 s	61.18 s	—	97.2%	61%
Venice AI direct	5.55 s	18.42 s	—	98.8%	35%
InferHub	18.42 s	—	40 tok/s	100.0%	4%
Mordiem	—	—	—	0.0%	0%

OpenRouter61% of traffic

97.2% success

p50 2.25 s · p95 61.18 s · —

Venice AI direct35% of traffic

98.8% success

p50 5.55 s · p95 18.42 s · —

InferHub4% of traffic

100.0% success

p50 18.42 s · p95 — · 40 tok/s

Mordiem0% of traffic

0.0% success

p50 — · p95 — · —

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 https://api.surplusintelligence.ai/v1/chat/completions \
  -H "Authorization: Bearer $SURPLUS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "grok-4.5",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

curl $SURPLUS_BASE_URL/chat/completions \
  -H "Authorization: Bearer $SURPLUS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "grok-4.5",
    "messages": [{"role": "user",
                  "content": "Hello"}]
  }'

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

Grok 4.5

Discount trend

Recent fills

Performance by provider route · 24h

Change your base URL.Keep your code.

Related models

Change your base URL.
Keep your code.