Free NVIDIA API
NVIDIA NIM's recurring free tier (build.nvidia.com) — DeepSeek, Llama, Nemotron and Gemma at 40 RPM.
FreeLLMAPI is a free, open-source LLM API that routes across every provider with a real free tier. The NVIDIA models below are on the free tier of NVIDIA NIM — reachable through one OpenAI-compatible key, with automatic failover when a provider hits its rate limit.
Free NVIDIA models (20)
| Model | Context | Free limits | Capabilities |
|---|---|---|---|
| minimaxai/minimax-m3 | 197K | 40 rpm | tools |
| z-ai/glm-5.2 | 200K | 40 rpm | tools |
| nvidia/nemotron-3-ultra-550b-a55b | 1.0M | 40 rpm | tools |
| openai/gpt-oss-120b | 131K | 40 rpm | tools |
| nvidia/llama-3.3-nemotron-super-49b-v1.5 | 131K | 40 rpm | tools |
| thinkingmachines/inkling | 1.0M | 40 rpm | tools, vision |
| google/diffusiongemma-26b-a4b-it | 262K | 40 rpm | vision |
| openai/gpt-oss-20b | 131K | 40 rpm | tools |
| stepfun-ai/step-3.7-flash | 66K | 40 rpm | tools |
| poolside/laguna-xs-2.1 | 262K | 40 rpm | tools |
| meta/llama-3.1-70b-instruct | 131K | 40 rpm | tools |
| meta/llama-3.3-70b-instruct | 131K | 40 rpm | tools |
| meta/llama-3.2-90b-vision-instruct | 131K | 40 rpm | tools, vision |
| google/gemma-4-31b-it | 262K | 40 rpm | — |
| nvidia/nemotron-3-nano-30b-a3b | 262K | 40 rpm | — |
| nvidia/nemotron-3-super-120b-a12b | 262K | 40 rpm | tools |
| nvidia/nemotron-nano-12b-v2-vl | 128K | 40 rpm | tools, vision |
| nvidia/nvidia-nemotron-nano-9b-v2 | 131K | 40 rpm | tools |
How to use NVIDIA for free
- Install FreeLLMAPI — the open-source router (GitHub). It runs locally and keeps your keys on your machine.
- Add a free key for NVIDIA NIM on the Keys page — no credit card required.
- Point your OpenAI client at the local endpoint and pick a model:
from openai import OpenAI
# FreeLLMAPI runs locally; grab your unified key + endpoint on the Keys page.
client = OpenAI(base_url="http://localhost:3001/v1", api_key="freellmapi-...")
resp = client.chat.completions.create(
model="meta/llama-3.1-70b-instruct",
messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)
Frequently asked questions
Is the NVIDIA API really free?
Yes — these NVIDIA models run on genuine provider free tiers (on the free tier of NVIDIA NIM). Inference costs nothing; you only add a free provider key.
Do I need a credit card?
No. The providers here offer free tiers that work without a card. You add the free key once and FreeLLMAPI routes to it.
How do I call NVIDIA through FreeLLMAPI?
Install the open-source router, add the provider's free key on the Keys page, then point any OpenAI SDK at your local endpoint — see the code sample above.