Qwen3.8 2.4T A95B
LiveQwen1M context · Text, Tools, Reasoning
Best discount now98.0%offYou pay 2.0% of reference.
Median discount37.5%offAcross 31 live offers.
Realized · 7 daysNot enough dataIt fills in after the nightly update.
Requests · 24h51931 offers from 26 sellers.
Current offers
31 of 247 offers
Availability
Providers
ProviderDiscountPriceLatencyUptimeOfferedSoldRemaining
Fireworks AI
98%
$0.0400 in
$0.12 out
4.1s
99.2%
∞
$18
∞
Together AI
98%
$0.0400 in
$0.12 out
-
-
∞
-
∞
OpenRouter
81%
$0.38 in
$1.14 out
-
-
∞
$0.473
∞
OpenRouter
60%
$0.80 in
$2.40 out
-
-
∞
$0.132
∞
Mordiem
60%
$0.80 in
$2.40 out
-
-
∞
-
∞
OpenRouter
60%
$0.80 in
$2.40 out
-
-
∞
-
∞
Mordiem
50%
$1.00 in
$3.00 out
-
-
∞
-
∞
Venice AI
50%
$1.00 in
$3.00 out
-
-
$210
-
$210
OpenRouter
50%
$1.00 in
$3.00 out
-
-
∞
-
∞
Venice AI
50%
$1.00 in
$3.00 out
-
-
∞
-
∞
Total
Cumulative offers
Offered
∞
Sold
$19
Remaining
∞
Discount trend
Realized · 7 daysNo trend yet.It fills in after the nightly update.
Recent fills
20:0626,488 tokensFireworks AI direct98.0%
20:0327,990 tokensFireworks AI direct98.0%
20:0181 tokensFireworks AI direct98.0%
20:0169 tokensFireworks AI direct98.2%
20:00128 tokensFireworks AI direct98.1%
20:0029,656 tokensFireworks AI direct98.0%
20:00125 tokensFireworks AI direct98.1%
19:57123 tokensFireworks AI direct98.2%
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 |
|---|---|---|---|---|---|
| Fireworks AI direct | 2.25 s | 111.50 s | — | 99.2% | 100% |
Fireworks AI direct100% of traffic
99.2% success
Use this modelChange your base URL.
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": "qwen3.8-2.4t-a95b", "messages": [{"role": "user", "content": "Hello"}] }'
SURPLUS_BASE_URL
https://api.surplusintelligence.ai/v1