NVIDIA NIM is the broadest free AI catalogue we've tested: one key, 83 models, no card. This is a hands-on review — we called the API, timed every response, and ran several of the models inside a real agent harness to see which ones can actually do work.
What you actually get
- 83 models on one key (we pulled the live list from the API on 31 August 2026), including DeepSeek V4, Kimi K3, Gemma 4, Mistral, and NVIDIA's Nemotron family.
- No credit card. Sign up at build.nvidia.com and generate a key starting
nvapi-. In 2026 this matters — half the "free" AI APIs we tested now demand a card. - OpenAI-compatible endpoint, so existing code works with a changed base URL.
- Credits don't expire: 1,000 on signup, expandable to 5,000. Rate limit is 40 requests/minute.
Speed: we measured it
Every model, same prompt, same US machine, streaming, timing generation only (excluding network latency) and using the API's own token counts:
| Model | Generation speed | Best for |
|---|---|---|
Kimi K3 moonshotai/kimi-k3 | 62.4 tok/s | Fastest here; strong all-rounder |
Gemma 4 31B google/gemma-4-31b-it | 50.9 tok/s | Lightweight chat |
Mistral Nemotron mistralai/mistral-nemotron | 34.4 tok/s | General use |
DeepSeek V4 Flash deepseek-ai/deepseek-v4-flash-0731 | 27.3 tok/s | Reasoning, coding |
Two things to take from this. First, the spread within one platform is 2.3× — which model you pick matters more than which platform. Second, these are modest numbers: Groq runs at roughly 500 tok/s, an order of magnitude quicker. NIM's selling point is breadth, not speed.
The strange part: OpenRouter is faster at NVIDIA's own model
We ran the identical model — nemotron-3-super-120b — on NVIDIA's endpoint and on OpenRouter's free tier. OpenRouter returned 45.7 tok/s. NVIDIA's own endpoint returned an empty response for the same request. Same weights, different serving infrastructure. If you specifically want Nemotron, it's worth testing both.
Which models can actually run an agent
Token speed says nothing about whether a model can complete a task. We plugged several NIM models into DeepSeek Harness and gave them real jobs — fix a broken Python script, tidy a folder, summarise CSVs — then checked the filesystem to see what actually happened:
| Model | Fix a broken script | Other tasks |
|---|---|---|
| Nemotron Super 120B | ✅ 43 s — fastest | ❌ Claimed a folder was tidied after 20 s; moved zero files |
| Kimi K3 | ✅ 56 s | ✅ Summarised three CSVs correctly in 64 s |
| DeepSeek V4 Flash | ✅ 251 s | — |
| Gemma 4 31B | ❌ Hung until 900 s timeout | — |
Note how badly throughput predicts this. DeepSeek V4 was the slowest model in the speed table yet completed the task; Gemma 4 was second fastest and never finished at all. And Nemotron's failure mode — reporting success without doing anything — is the one to watch for in any automation. Full method and results: we gave free AI models real agent jobs.
Working code
NIM is OpenAI-compatible, so only the base URL and key change:
from openai import OpenAI
client = OpenAI(
base_url="https://integrate.api.nvidia.com/v1",
api_key="nvapi-YOUR_API_KEY_HERE"
)
response = client.chat.completions.create(
model="moonshotai/kimi-k3", # fastest in our test
messages=[{"role": "user", "content": "Explain GPU computing in one paragraph."}],
max_tokens=256,
)
print(response.choices[0].message.content)Careful with older tutorials. Nearly every NIM guide online opens with model="meta/llama-3.3-70b-instruct". That model is gone — we hit a hard failure calling it in August 2026, and no Meta Llama chat models remain in the live catalogue. Substitute moonshotai/kimi-k3 or deepseek-ai/deepseek-v4-flash-0731.
To see what's actually available on any given day, ask the API rather than trusting a blog post:
curl https://integrate.api.nvidia.com/v1/models \
-H "Authorization: Bearer $NVIDIA_API_KEY"What it's genuinely good for
- Trying many models on one key. Nothing else free gives you DeepSeek, Kimi, Gemma, Mistral and Nemotron without five separate signups.
- Batch and offline work — summarising, classification, data extraction — where 30–60 tok/s is fine.
- Agent backends, with the caveat above: pick the model per job and verify the work got done.
- Beyond text: the catalogue also covers image generation, speech and vision models.
Where it falls short
- Not fast. For real-time chat or voice, Groq is roughly 10× quicker.
- Credits are finite (1,000–5,000, larger models cost more per call), so it's a place to experiment, not to run production traffic.
- The catalogue shifts. Llama's removal broke the code sample in every tutorial written before mid-2026 — including this one, until we retested.
- 40 requests/minute rules out heavy parallel fan-out.
Verdict
NIM is the best free catalogue in 2026 — no card, credits that don't expire, and 83 models behind one key, which is exactly what you want while you're still deciding which model fits your problem. Once you've decided, you'll likely move the workload somewhere faster or cheaper per token. Use it to explore; benchmark before you build on it.
All figures measured 2026-08-31 with our open harness: free-ai-api-benchmark. Free tiers change fast — we re-run rather than quote vendor pages.