NVIDIA: Nemotron 3.5 Super VL
LiveNVIDIA262K context · Text, Vision, Video, Tools, Reasoning
Best discount now30.0%offYou pay 70.0% of reference.
Median discount15.5%offAcross 2 live offers.
Realized · 7 days30.4%avgRequest-weighted average.
Requests · 24h192 offers from 2 sellers.
Current offers
2 of 2 offers
Availability
Providers
ProviderDiscountPriceLatencyUptimeSold
OpenRouter
30%
$0.10 in
$0.35 out
-
-
$0.129
OpenRouter
1%
$0.15 in
$0.49 out
-
-
-
Total
Cumulative offers
Sold
$0.129
Discount trend
Realized · 7 days63.6%
Best, twice dailyMedian 15.5%
Recent fills
22:22424,305 tokensOpenRouter30.0%
22:20424,195 tokensOpenRouter30.0%
22:06151 tokensOpenRouter31.0%
21:4233 tokensOpenRouter27.3%
21:3969 tokensOpenRouter25.0%
21:082,875 tokensOpenRouter30.0%
21:082,875 tokensOpenRouter30.0%
21:06156 tokensOpenRouter28.8%
20:3733 tokensOpenRouter27.3%
20:07156 tokensOpenRouter28.8%
19:4069 tokensOpenRouter25.0%
19:3233 tokensOpenRouter27.3%
19:1726 tokensOpenRouter20.0%
19:1778 tokensOpenRouter32.3%
19:1780 tokensOpenRouter31.3%
19:092,927 tokensOpenRouter29.9%
19:092,927 tokensOpenRouter29.9%
19:06151 tokensOpenRouter30.5%
08:4233 tokens63.6%
Settled on Base in USDC.Times in UTC
Performance by provider route · 24h
Measured on Surplus trafficNot enough data yet.Shown once 2 sellers and 20 requests report.
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 ↗Build with agents
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
- min_pnumberDrops tokens below this share of the top token’s probability
- 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
- logit_biasobjectPer-token bias on the logits
- logprobsbooleanReturn token log probabilities
- top_logprobsintegerHow many top tokens to return probabilities for
Context window 262K tokens · Max output 236K tokensOthers are passed through; most providers ignore what they don’t support. Parameter compatibility ↗
curl $SURPLUS_BASE_URL/chat/completions \ -H "Authorization: Bearer $SURPLUS_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "nemotron-3.5-super-vl", "messages": [{"role": "user", "content": "Hello"}] }'
SURPLUS_BASE_URL
https://api.surplusintelligence.ai/v1