Cheaper Inference
Model record / nvidia
nemotron-3.5-lightning is available for text generation from nvidia. Its reported context window is 262,144 tokens, with up to 131,072 output tokens. Observed input: text (verified request). The served catalog lists streaming.
Ready when you are
Marketplace pricing, capped at list, optimized further.
POST /v1/chat/completions
curl https://api.cheaperinference.com/v1/chat/completions \ -H "Authorization: Bearer ci_live_YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "nemotron-3.5-lightning", "messages": [ { "role": "user", "content": "Reply with the single word OK." } ] }'POST /v1/responses
curl https://api.cheaperinference.com/v1/responses \ -H "Authorization: Bearer ci_live_YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "input": [ { "role": "user", "content": "Reply with the single word OK." } ], "model": "nemotron-3.5-lightning", "store": false }'POST /v1/messages
curl https://api.cheaperinference.com/v1/messages \ -H "Authorization: Bearer ci_live_YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "nemotron-3.5-lightning", "messages": [ { "role": "user", "content": "Reply with the single word OK." } ], "max_tokens": 1024 }'$0.105625 estimated at displayed rates
1,000,000 ÷ 1,000,000 × $0.065 + 250,000 ÷ 1,000,000 × $0.1625
The same billed quantities at the listed reference rates: $0.1625.
Uses uncached input at the displayed standard rates, with no extra modalities or tools. Billed output includes any charged reasoning tokens. Actual token counts, price tiers, and marketplace prices can change the total.
Price quote effective .
Python: pip install openai · Node.js: npm install openai. Set CHEAPER_INFERENCE_API_KEY on your server.
import osfrom openai import OpenAIclient = OpenAI( api_key=os.environ["CHEAPER_INFERENCE_API_KEY"], base_url="https://api.cheaperinference.com/v1",)request = { "input": [ { "role": "user", "content": "Reply with the single word OK.", }, ], "model": "nemotron-3.5-lightning", "store": False,}response = client.responses.create(**request)print(response.output_text)import OpenAI from "openai";const client = new OpenAI({ apiKey: process.env.CHEAPER_INFERENCE_API_KEY, baseURL: "https://api.cheaperinference.com/v1",});const response = await client.responses.create({ "input": [ { "role": "user", "content": "Reply with the single word OK." } ], "model": "nemotron-3.5-lightning", "store": false});console.log(response.output_text);For other supported endpoints and their exact parameters, use the request samples and parameter reference on this page. Read the API integration guide.
| Model | Current pricing | Context limit | Image input listed |
|---|---|---|---|
| nemotron-3.5-lightning (this model)nvidia | $0.065 input / $0.1625 output per 1M tokens | 262,144 tokens | No |
| nemotron-3.5-lightning-freenvidia | $0.00 input / $0.00 output per 1M tokens | 1,000,000 tokens | No |
| nvidia-nemotron-3.5-lightning-30b-a3bNVIDIA | $0.065 input / $0.1625 output per 1M tokens | 1,000,000 tokens | No |
This model takes the fields in its sample request. It has no other stated parameters.
See how much this model saves and when its recorded price has been lowest.
This model averaged 35.0% below comparable direct provider prices across the selected range. Its strongest observed window was 12:00 PM–10:00 AM in UTC.
Average saved
35.0%
Cheapest time
12:00 PM–10:00 AM
Hourly coverage
23/24
Signal quality
Growing
Hover a bar for savings per token and observation counts.
Source buckets are UTC; labels are converted to UTC.
Last 24 hours
#217
of 332 ranked models
Last 7 days
#281
of 389 ranked models
Last 30 days
#296
of 400 ranked models
| $0.195 input / $1.56 output per 1M tokens |
| 204,800 tokens |
| No |