NVIDIA Nemotron Nano 12B v2 VL BF16
LiveNVIDIA128K context · Text, VisionBenchmark price · $0.2 input / $0.6 output per 1M tokens
Best discount now99.0%offYou pay 1.0% of reference.
Median discount94.0%offAcross 181 live offers.
Realized · 7 days98.9%avgRequest-weighted average.
Requests · 24h84181 offers from 23 sellers.
Current offers
181 of 187 offers
Availability
Providers
ProviderDiscountPriceLatencyUptimeCacheSold
Amazon Bedrock
99%
$0.00200 in
$0.00600 out
503ms
76.0%
0.0%
$0.001
Amazon Bedrock
98%
$0.00218 in
$0.00653 out
503ms
76.0%
0.0%
$0.007
Amazon Bedrock
98%
$0.00218 in
$0.00653 out
503ms
76.0%
0.0%
-
Amazon Bedrock
98%
$0.00218 in
$0.00653 out
503ms
76.0%
0.0%
-
Amazon Bedrock
98%
$0.00218 in
$0.00653 out
503ms
76.0%
0.0%
-
Amazon Bedrock
98%
$0.00218 in
$0.00653 out
503ms
76.0%
0.0%
-
Amazon Bedrock
98%
$0.00218 in
$0.00653 out
503ms
76.0%
0.0%
-
Amazon Bedrock
98%
$0.00218 in
$0.00653 out
503ms
76.0%
0.0%
-
Amazon Bedrock
98%
$0.00218 in
$0.00653 out
503ms
76.0%
0.0%
-
Amazon Bedrock
98%
$0.00218 in
$0.00653 out
503ms
76.0%
0.0%
-
Total
Cumulative offers
Sold
$0.009
Discount trend
Realized · 7 days99.3%+0.1 pts vs last week
Best, twice dailyMedian 94.0%
Recent fills
17:1820,179 tokensAWS Bedrock99.0%
17:1331 tokensAWS Bedrock100.0%
16:3327 tokensAWS Bedrock100.0%
16:1331 tokensAWS Bedrock100.0%
15:2827 tokensAWS Bedrock100.0%
15:1820,123 tokensAWS Bedrock99.0%
15:1421 tokensAWS Bedrock100.0%
14:4926 tokensAWS Bedrock100.0%
14:37255 tokensAWS Bedrock100.0%
14:33254 tokensAWS Bedrock100.0%
14:29254 tokensAWS Bedrock100.0%
14:25254 tokensAWS Bedrock100.0%
14:2333 tokensAWS Bedrock100.0%
14:21255 tokensAWS Bedrock100.0%
14:19255 tokensAWS Bedrock100.0%
14:1331 tokensAWS Bedrock100.0%
13:1827 tokensAWS Bedrock100.0%
13:1820,069 tokensAWS Bedrock99.0%
13:1331 tokensAWS Bedrock100.0%
12:5127 tokensAWS Bedrock100.0%
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 |
|---|---|---|---|---|---|
| AWS Bedrock | 503 ms | - | 3623 tok/s | 76.0% | 100% |
AWS Bedrock100% of traffic
76.0% 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
- 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
- frequency_penaltynumberPenalises tokens by how often they appeared
- presence_penaltynumberPenalises tokens that appeared at all
Context window 128K tokens · Max output 8K 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="nvidia-nemotron-nano-12b-v2", messages=[{"role": "user", "content": "Hello!"}] )
SURPLUS_BASE_URL
https://api.surplusintelligence.ai/v1