LLM Perks

Llama 3.1 Nemotron 70B

Free right now Frontier
Open weights

Llama 3.1 Nemotron 70B is a language model with 70B parameters from NVIDIA. It is currently free at 2 providers with up to 16K tokens of context. Its weights are open, so it can also run locally.

Developer
NVIDIA
Parameters
70B
Context
16K tokens
Type
Text
License
Open weights

Where to use Llama 3.1 Nemotron 70B for free

Each row is a separate free endpoint with its own limits.

ProviderContextLimitCard
Together AI
nim/nvidia/llama-3.1-nemotron-70b-instruct
16K Fair use (depends on server load) — Open
NVIDIA Build
nvidia/llama-3.1-nemotron-70b-instruct
— Free serverless inference for development; limits and model availability may change. No Open

Quick start

curl https://api.together.xyz/v1/chat/completions \
  -H "Authorization: Bearer $TOGETHER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nim/nvidia/llama-3.1-nemotron-70b-instruct",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Example for Together AI. Any OpenAI-compatible client works: Cursor, Cline, OpenCode, Open WebUI.

Benchmarks

Intelligence Index
6.9
GPQA Diamond
46.5%
Humanity's Last Exam
4.2%
Terminal-Bench Hard
4.5%
τ²-Bench
23.1%
Long context (LCR)
8.3%

Source: Artificial Analysis · Llama 3.1 Nemotron Instruct 70B

Similar free models

FAQ

Is Llama 3.1 Nemotron 70B free?

Yes. As of September 26, 2026, Llama 3.1 Nemotron 70B is free at Together AI, NVIDIA Build. Each provider has its own limits — see the table above.

What is the context window of Llama 3.1 Nemotron 70B?

The largest context among free routes is 16,384 tokens. Some providers cap it lower.

How do I call Llama 3.1 Nemotron 70B via API?

Use any OpenAI-compatible client with base URL https://api.together.xyz/v1, model ID nim/nvidia/llama-3.1-nemotron-70b-instruct, and a Together AI key.

How good is Llama 3.1 Nemotron 70B?

Artificial Analysis Intelligence Index: 6.9, GPQA Diamond: 47%. For comparison, the strongest free model in the catalog right now is GLM 5.3.

Is Llama 3.1 Nemotron 70B open-weight?

Yes, the weights are published — you can download and run it locally, for example with Ollama or LM Studio.