Qwen3 VL 30B A3B
LiveAlibaba128K context · Text, VisionBenchmark price · $0.25 input / $0.9 output per 1M tokens
Best discount now46.9%offYou pay 53.1% of reference.
Median discount15.0%offAcross 21 live offers.
Realized · 7 days12.4%avgRequest-weighted average.
Requests · 24h7321 offers from 17 sellers.
Current offers
21 of 101 offers
Availability
Providers
ProviderDiscountPriceLatencyUptimeCacheSold
Uncensored AI
43%
$0.14 in
$0.63 out
-
97.8%
0.0%
-
Venice AI
32%
$0.17 in
$0.61 out
-
-
-
-
Venice AI
19%
$0.20 in
$0.72 out
-
-
-
-
Uncensored AI
31%
$0.17 in
$0.77 out
-
97.8%
0.0%
-
Venice AI
15%
$0.21 in
$0.77 out
-
-
-
-
OpenRouter
15%
$0.21 in
$0.77 out
-
-
-
-
OpenRouter
13%
$0.21 in
$0.77 out
-
-
-
-
Mordiem
10%
$0.22 in
$0.80 out
-
-
-
-
Mordiem
10%
$0.23 in
$0.81 out
-
-
-
-
Mordiem
10%
$0.23 in
$0.81 out
-
-
-
-
Total
Cumulative offers
Sold
$0.008
Discount trend
Realized · 7 days74.5%−10.1 pts vs last week
Best, twice dailyMedian 15.0%
Recent fills
23:29490 tokensUncensored AI+56.9%
23:03110 tokensUncensored AI30.4%
22:32606 tokensUncensored AI34.3%
22:31140 tokens40.2%
22:29352 tokensUncensored AI+56.5%
21:58136 tokensUncensored AI29.6%
21:29240 tokensUncensored AI+56.0%
20:54276 tokensUncensored AI29.9%
20:29365 tokensUncensored AI+57.0%
19:48143 tokensUncensored AI30.3%
19:30487 tokensUncensored AI+57.1%
18:44297 tokensUncensored AI30.0%
18:28328 tokensUncensored AI+56.6%
17:39256 tokensUncensored AI30.0%
17:28307 tokensUncensored AI+56.5%
16:46583 tokensUncensored AI30.3%
16:46421 tokensUncensored AI30.3%
16:45421 tokensUncensored AI30.3%
16:45626 tokensUncensored AI30.3%
16:45416 tokensUncensored AI30.4%
Times in UTCSettled on Base in USDC.
Performance by provider route · 24h
Measured on Surplus traffic| Route | p50 latency | p95 latency | Throughput | Success rate | ShareShare of traffic |
|---|---|---|---|---|---|
| Uncensored AI direct | 10.11 s | - | - | 97.8% | 100% |
Uncensored AI direct100% of traffic
97.8% 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 ↗Parameters this model acceptsPOST /v1/chat/completions
- modelstringThis model’s id
- messagesarrayThe conversation, as role and content pairs
- streambooleanSend the answer as server-sent events
- max_tokensintegerMost output tokens to generate
- temperaturenumberSampling temperature
- top_pnumberNucleus sampling
- top_kintegerTop-k sampling
- stopstring | arrayStop sequences
- seedintegerDeterministic sampling
- toolsarrayFunctions the model may call, in the OpenAI format
- tool_choicestring | objectauto, required, none, or one named function
- response_formatobjectJSON mode or a JSON schema for structured output
- structured_outputsbooleanAccepts a JSON schema in response_format
- reasoningobjectReasoning options as an object, such as {"effort": "high"}
- include_reasoningbooleanStripped before the request reaches the provider
- frequency_penaltynumberPenalises tokens by how often they appeared
- presence_penaltynumberPenalises tokens that appeared at all
- repetition_penaltynumberPenalises repeated tokens
Context window 128K tokens · Max output 4K tokensOthers are passed through; most providers ignore what they don’t support. Parameter compatibility ↗
from openai import OpenAI client = OpenAI( api_key="inf_your_key_here", base_url="$SURPLUS_BASE_URL" ) response = client.chat.completions.create( model="qwen3-vl-30b-a3b-thinking", messages=[{"role": "user", "content": "Hello!"}] )
SURPLUS_BASE_URL
https://api.surplusintelligence.ai/v1