NVIDIA API pricing: all models, per million tokens
Input and output prices per million tokens, context windows and retirement dates for 11 NVIDIA models, from the OpenRouter catalog. Updated automatically.
| Model | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| nvidia/switchyard | variable | variable | 1,000,000 |
| nvidia/nemotron-3.5-lightning | US$ 0.07 | US$ 0.2 | 262,144 |
| nvidia/nemotron-3.5-lightning:free | US$ 0 | US$ 0 | 1,000,000 |
| nvidia/nemotron-3.5-content-safety | US$ 0.2 | US$ 0.2 | 131,072 |
| nvidia/nemotron-3.5-content-safety:free | US$ 0 | US$ 0 | 128,000 |
| nvidia/nemotron-3-ultra-550b-a55b | US$ 0.6 | US$ 2.40 | 262,144 |
| nvidia/nemotron-3-ultra-550b-a55b:free | US$ 0 | US$ 0 | 1,000,000 |
| nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free | US$ 0 | US$ 0 | 256,000 |
| nvidia/nemotron-3-super-120b-a12b | US$ 0.08 | US$ 0.45 | 262,144 |
| nvidia/nemotron-3-super-120b-a12b:free | US$ 0 | US$ 0 | 262,144 |
| nvidia/nemotron-3-nano-30b-a3b | US$ 0.06 | US$ 0.24 | 262,144 |
Reference prices from OpenRouter (aggregator); they may differ from the provider's direct pricing.
Give your AI agent these facts
Vigia is a free MCP server: your coding agent checks versions, breaking changes and vulnerabilities before it writes code. No signup, no API key.
claude mcp add --transport http vigia https://vigia.coredls.cloud/mcp
Add to CursorAdd to VS Code★ Star on GitHub
Any other MCP client
{ "mcpServers": { "vigia": { "url": "https://vigia.coredls.cloud/mcp" } } }Agent skill (SKILL.md): tells the agent when to use Vigia · GitHub Action for pull requests
For agents
GET https://vigia.coredls.cloud/v1/models?provider=nvidia