DeepSeek V4 Flash
LiveDeepSeek1M context · Text, Tools, Reasoning
Best discount now97.0%offYou pay 3.0% of reference.
Median discount0.0%offAcross 93 live offers.
Realized · 7 daysNot enough dataIt fills in after the nightly update.
Requests · 24h56,50793 offers from 52 sellers.
Current offers
91 of 748 offers
Availability
Providers
ProviderDiscountPriceLatencyUptimeOfferedSoldRemaining
InferHub ?
74%
$0.00112 in
$0.0138 out
4.1s
92.5%
∞
$11
∞
InferHub ?
49%
$0.00224 in
$0.0275 out
4.1s
92.5%
∞
$2
∞
InferHub ?
+159%
$0.0133 in
$0.0266 out
4.1s
92.5%
∞
$0.166
∞
InferHub ?
+159%
$0.0133 in
$0.0266 out
4.1s
92.5%
∞
$0.112
∞
InferHub ?
3%
$0.00450 in
$0.0413 out
4.1s
92.5%
∞
$0.290
∞
InferHub ?
+211%
$0.0160 in
$0.0319 out
4.1s
92.5%
∞
$0.036
∞
OpenRouter
+245%
$0.0177 in
$0.0354 out
4.1s
77.8%
∞
$11
∞
InferHub ?
+250%
$0.0180 in
$0.0360 out
4.1s
92.5%
∞
$0.012
∞
OpenRouter
+255%
$0.0182 in
$0.0364 out
4.1s
77.8%
∞
$4
∞
InferHub ?
+28%
$0.00598 in
$0.0548 out
4.1s
92.5%
$1B
$0.041
$1B
Total
Cumulative offers
Offered
∞
Sold
$34
Remaining
∞
Discount trend
Realized · 7 daysNo trend yet.It fills in after the nightly update.
Recent fills
17:10218,868 tokensInferHub12.7%
17:1024,671 tokensOpenRouter+11.1%
17:094,438 tokensOpenRouter19.8%
17:09112,718 tokensOpenRouter+644.2%
17:094,203 tokensVenice AI direct+37.0%
17:0915,498 tokensOpenRouter+9.3%
17:094,196 tokensVenice AI direct+37.5%
17:09112,289 tokensOpenRouter+694.4%
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 |
|---|---|---|---|---|---|
| Venice AI direct | 13.64 s | 82.59 s | 40 tok/s | 98.4% | 37% |
| OpenRouter | 7.49 s | 45.32 s | 73 tok/s | 77.8% | 36% |
| InferHub | 7.49 s | 24.87 s | 180 tok/s | 92.5% | 18% |
| Mordiem | 18.42 s | 111.50 s | 22 tok/s | 87.4% | 6% |
| DeepSeek direct | 3.04 s | 24.87 s | 329 tok/s | 96.4% | 1% |
| Uncensored AI direct | 10.11 s | 82.59 s | 134 tok/s | 99.6% | 1% |
| Bankr | 10.11 s | 150.53 s | — | 100.0% | 1% |
| Capminal Gateway | 13.64 s | 150.53 s | — | 74.9% | 0% |
Venice AI direct37% of traffic
98.4% success
OpenRouter36% of traffic
77.8% success
InferHub18% of traffic
92.5% success
Mordiem6% of traffic
87.4% success
DeepSeek direct1% of traffic
96.4% success
Uncensored AI direct1% of traffic
99.6% success
Bankr1% of traffic
100.0% success
Capminal Gateway0% of traffic
74.9% 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": "deepseek-v4-flash", "messages": [{"role": "user", "content": "Hello"}] }'
SURPLUS_BASE_URL
https://api.surplusintelligence.ai/v1