$0.0500
/ 1M tokens
Input
New instructions, files and conversation context sent each turn.
Trim retrieved context before it reaches the model.
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 is a large language model (LLM) trained by NVIDIA.
Try Nemotron 3.5 Lightning 30B with a real request, review its parameters and validate the output before integrating the API.
Use the quick estimate above for a single run, then review the full CoreAPI and official-price comparison.
Credits make budgets comparable across token, request and runtime billing. The USD amount remains the source of truth at checkout.
| CoreAPI Price (USD / M Tokens) |
|---|
| Input: $0.0500/M Output: $0.2000/M |
A stable model identity for search and evaluation, paired with live catalog data that can change without rewriting the page's core SEO structure.
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 is a large language model (LLM) trained by NVIDIA.
One workspace to compare models, tune prompts, inspect routing, migrate code and ship a tested starting point.
Example data — not live metricsRun the same prompt across leading models and get a recommendation with evidence.
Model the five billing dimensions, test a realistic workload and decide where Opus earns its premium before you ship.
Replay real workloads instead of comparing token prices in isolation. Load a preset, then adjust every billing dimension.
New instructions, files and conversation context sent each turn.
Trim retrieved context before it reaches the model.
Previously cached prompt tokens reused in later requests.
Keep system prompts and repository maps byte-stable.
Reasoning, code and text generated by the model.
Use explicit completion criteria and output limits.
Use Opus when the task spans architecture, multiple files and ambiguous implementation trade-offs.
A strong choice when an agent must preserve intent across many tool calls and recovery steps.
Reserve it for security, migration and production reviews where a missed issue costs more than tokens.
Classification, extraction and simple chat usually achieve better unit economics on Sonnet or Haiku.
Keep your preferred SDK and change the base URL, key and model ID.
import Anthropic from '@anthropic-ai/sdk';
const client = new Anthropic({
apiKey: process.env.COREAPI_KEY,
baseURL: 'https://unixcore.io',
});
const message = await client.messages.create({
model: 'nemotron-3.5-lightning',
max_tokens: 4096,
messages: [{ role: 'user', content: 'Review this change.' }],
});Copy a working endpoint and code example, then open the complete API reference when you need every parameter.
Authenticate once, call the model endpoint and keep the same billing and observability workflow across providers.
Access comprehensive sample code and API resources for Nemotron 3.5 Lightning 30B to streamline your integration process. Our detailed documentation provides step-by-step guidance, helping you leverage the full potential of Nemotron 3.5 Lightning 30B in your projects.
Scan the model facts that matter before you choose an architecture or estimate production workload.
| Supported capabilities | Supported |
|---|---|
| Capability metadata is not available yet. Review the overview and API parameters for supported behavior. | |
Use Nemotron 3.5 Lightning 30B for production workflows that match its text capabilities, then compare alternatives before committing to a long-term integration.
Production chat and agent workflows
Coding, analysis and structured generation
High-volume automation through one API
Compare other models available through CoreAPI for different quality, latency, capability and pricing trade-offs.
Review live heartbeat data, endpoint availability and observed response times before moving into production.
Follow meaningful availability, pricing and capability changes for Nemotron 3.5 Lightning 30B without losing the stable model page.
Release notes, pricing changes, benchmark updates and migration guidance accumulate here while the canonical URL stays unchanged.
Nemotron 3.5 Lightning 30B is available through the CoreAPI model catalog and API documentation.
CurrentPrice, context, availability and limits are treated as dynamic properties instead of being embedded in the page title or model identity.
The provider and model slug form a durable canonical URL; future content and data updates remain on this page.