NVIDIA — Coding Model
Nemotron 3 Nano 30B A3B API — 128k tokens context.
NVIDIA's Nemotron 3 Nano is a mixture-of-experts model that is strong on reasoning traces and the cheapest model we serve per token. It is available from the Starter plan upward.
Model ID
nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B
Nemotron 3 Nano 30B A3B specifications
| Model ID | nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B |
|---|---|
| Vendor | NVIDIA |
| Usage tier | Tier 1 |
| Context window | 128k tokens |
| Quantization | FP8 |
| Input | $0.06 per 1M tokens |
| Output | $0.24 per 1M tokens |
| Cache read | $0.0060 per 1M tokens |
| Approx. output speed | ~180 tokens/sec |
Why run Nemotron 3 Nano 30B A3B on IN2PETA
- Mixture-of-experts architecture
- Strong reasoning traces
- Cheapest per-token in the catalog
- OpenAI-compatible endpoint — switch providers by changing one base URL, not by rewriting your client.
Calling the Nemotron 3 Nano 30B A3B API
Nemotron 3 Nano 30B A3B is served from an OpenAI-compatible gateway. Change your base URL and API key, and existing OpenAI clients work unchanged.
curl https://code.in2peta.com/v1/coding/chat/completions \
-H "Authorization: Bearer $IN2PETA_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B",
"messages": [{"role": "user", "content": "Explain this function"}]
}'Set ANTHROPIC_BASE_URL to the same host to point Claude Code at the same gateway. See Getting Started for key setup, and Coding Endpoints for the full API reference.
Plans that include Nemotron 3 Nano 30B A3B
Not included
Includes this model
Includes this model
Includes this model
Frequently asked questions
How do I access the Nemotron 3 Nano 30B A3B API?
Point any OpenAI-compatible client at https://code.in2peta.com and send requests to /v1/coding/chat/completions with "model": "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B". The gateway is OpenAI-compatible, so existing SDKs work by changing the base URL and API key.
How much does the Nemotron 3 Nano 30B A3B API cost?
Nemotron 3 Nano 30B A3B is $0.06 per million input tokens and $0.24 per million output tokens, with cache reads at $0.006 per million. There is no per-request fee on top of token usage.
Which IN2PETA plans include Nemotron 3 Nano 30B A3B?
Nemotron 3 Nano 30B A3B is available on Starter ($2/mo), Go ($5/mo), Pro ($15/mo). Requests for a model outside your plan return HTTP 403 with the allowed model list in the error body.
What is the context window of Nemotron 3 Nano 30B A3B?
Nemotron 3 Nano 30B A3B serves a 128k tokens context window and runs FP8 quantised on IN2PETA.
Start with Nemotron 3 Nano 30B A3B today
Nemotron 3 Nano 30B A3B is available from the Starter plan at $2/month.