Skip to main content

Thinking Machines: Inkling

Live
openrouter1M context · Text
Use this model
Best discount now99.0%offYou pay 1.0% of reference.
Median discount45.0%offAcross 25 live offers.
Realized · 7 daysNot enough dataIt fills in after the nightly update.
Requests · 24h54025 offers from 25 sellers.
Current offers
25 of 59 offers
Availability
Providers
ProviderDiscountPriceLatencyUptimeOfferedSoldRemaining
Fireworks AI
99%
$0.00950 in
$0.0405 out
-
97.2%
∞
$0.003
Mordiem
73%
$0.25 in
$1.01 out
-
-
∞
-
OpenRouter
73%
$0.25 in
$1.01 out
-
-
∞
-
OpenRouter
73%
$0.25 in
$1.01 out
-
-
∞
-
Venice AI
60%
$0.38 in
$1.62 out
-
96.2%
∞
$0.370
OpenRouter
59%
$0.38 in
$1.62 out
-
-
∞
-
OpenRouter
59%
$0.38 in
$1.62 out
-
-
∞
-
OpenRouter
50%
$0.47 in
$2.02 out
-
-
∞
-
Mordiem
47%
$0.50 in
$2.02 out
-
-
∞
-
OpenRouter
47%
$0.50 in
$2.02 out
-
-
∞
-
Total
Cumulative offers
Offered
∞
Sold
$0.374
Remaining

Discount trend

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

Recent fills

20:07944 tokensVenice AI direct60.0%
20:04944 tokensVenice AI direct60.0%
20:03946 tokensVenice AI direct60.0%
20:0031 tokensFireworks AI direct98.7%
19:58944 tokensVenice AI direct60.0%
19:54144 tokensVenice AI direct59.7%
19:53944 tokensVenice AI direct60.0%
19:50946 tokensVenice AI direct60.0%
Settled on Base in USDC.

Performance by provider route · 24h

Measured on Surplus traffic
Venice AI direct93% of traffic
96.2% success
p50 1.24 s · p95 5.55 s · —
Fireworks AI direct7% of traffic
97.2% success
p50 503 ms · 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 $SURPLUS_BASE_URL/chat/completions \
  -H "Authorization: Bearer $SURPLUS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "inkling",
    "messages": [{"role": "user",
                  "content": "Hello"}]
  }'

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

Related models