awesome-free-ai-coding · every free model · every provider · filter the list

NVIDIA NIM (build.nvidia.com) free tier

🔌 LLM APIs with free tier · no card · not offered in Russia, Pakistan, Bangladesh and 11 more places · live — last verified by a probe on 2026-11-01 · build.nvidia.com · back to the whole list

What you get

Free endpoints for the models build.nvidia.com marks “Free Endpoint”, open-weight models from several labs among them, called with a free NVIDIA Developer Program key at integrate.api.nvidia.com/v1 (OpenAI-compatible)

Free models

glm-5.3-flash, nemotron-3-ultra, laguna-xs-2.1, muse-glimmer-30b, nemotron-3.5-lightning, gemma-4-31b, gpt-oss-20b, nemotron-3-nano-omni, diffusiongemma, llama-3.2-90b-vision, llama-3.2-11b-vision, deepseek-v4.1-flash, nemotron-3.5-super-vl-120b-a12b, step-5-preview-600b-a27b

Limits, in the vendor’s words

Published ceiling: 40 requests/minute; 10,000 requests/day per account

No card, but an API key requires an NVIDIA Developer Program account and phone verification in a supported country. Published ceilings can vary by model and traffic can cause throttling. Vendor forum reports describe new personal keys that can list models but receive 404 on chat calls; an issued key alone does not establish working inference. Model pages identify available and deprecated endpoints; copy current IDs from the catalog.

Where it is offered

Not offered in Russia, Pakistan, Bangladesh, Iran, Kazakhstan, Belarus, Uzbekistan, Kyrgyzstan and 6 more places (source, read 2026-09-26). That leaves out 5.5% of the developers GitHub counts, beyond the countries under comprehensive US embargo (Innovation Graph, 2026 Q1).

What happens to what you send

What you send may be used to train or improve models. In the vendor’s words: “Your input and output will be recorded to provide you with this trial experience and to improve NVIDIA products and services, including AI models” (source).

Connect

Base URL: https://integrate.api.nvidia.com/v1
Key: NVIDIA_NIM_API_KEY — get one at https://build.nvidia.com
Callable ids: z-ai/glm-5.3-flash, deepseek-ai/deepseek-v4.1-flash, nvidia/nemotron-3-ultra-550b-a55b, poolside/laguna-xs-2.1, google/gemma-4-31b-it, meta/muse-glimmer-30b, nvidia/nemotron-3.5-lightning-30b-a3b, openai/gpt-oss-20b, nvidia/nemotron-3-nano-omni-30b-a3b-reasoning, google/diffusiongemma-26b-a4b-it, meta/llama-3.2-90b-vision-instruct, meta/llama-3.2-11b-vision-instruct, nvidia/nemotron-3.5-super-vl-120b-a12b, stepfun-ai/step-5-preview, minimaxai/minimax-m3.1-flash, nvidia/nemotron-3.5-bolt-e4b, mistralai/mistral-large-4-1t-a52b
Note: Use available chat endpoints marked Free Endpoint. /v1/models also lists older IDs without a free mark, so catalog membership alone does not establish free access.

Try it from your terminal with your key in NVIDIA_NIM_API_KEY — it goes from your machine to the vendor and nowhere else:

curl -s https://integrate.api.nvidia.com/v1/chat/completions \
  -H "Authorization: Bearer $NVIDIA_NIM_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{"model":"z-ai/glm-5.3-flash","messages":[{"role":"user","content":"2+2? MAKE NO MISTAKES."}]}'

Evidence

Probe: the models catalog at https://integrate.api.nvidia.com/v1/models, each listed family checked for its free mark on the vendor’s free list at https://api.ngc.nvidia.com/v2/search/catalog/resources/ENDPOINT?q=%7B%22filters%22%3A%5B%7B%22field%22%3A%22label%22%2C%22value%22%3A%22nim_type_preview%22%7D%5D%2C%22page%22%3A0%2C%22pageSize%22%3A100%2C%22query%22%3A%22%2A%22%7D
Source: https://build.nvidia.com/explore/discover
Source: https://build.nvidia.com/moonshotai/kimi-k3
Source: https://forums.developer.nvidia.com/t/request-for-nvidia-nim-api-rate-limit-increase-40-200-rpm/369798.json
Source: https://forums.developer.nvidia.com/t/account-access-verification-update/360900.json
Source: https://build.nvidia.com/api/runtime/config/otp-unsupported-countries.yaml
Source: https://build.nvidia.com/nvidia/nemotron-3-super-120b-a12b
Source: https://build.nvidia.com/minimaxai/minimax-m3.1-flash
Source: https://build.nvidia.com/nvidia/nemotron-3.5-bolt-e4b
Source: https://build.nvidia.com/z-ai/glm-5-3
Source: https://build.nvidia.com/mistralai/mistral-large-4-1t-a52b
Source: https://build.nvidia.com/mistralai/mistral-large-4-1t-a52b/modelcard

History

Each line is a change to what this page publishes, dated the day it reached the list, in UTC.

2026-10-29 — Free models changed: added nemotron-3.5-super-vl-120b-a12b, step-5-preview-600b-a27b
2026-10-28 — Free models changed: dropped glm-5.3
2026-10-20 — Free models changed: dropped nemotron-3-super
2026-10-15 — Free models changed: added glm-5.3
2026-10-15 — Free models changed: dropped glm-5.3, kimi-k3
2026-10-02 — Free models changed: added deepseek-v4.1-flash
2026-09-29 — Free models changed: added glm-5.3, glm-5.3-flash
2026-09-28 — Free models changed: dropped mistral-nemotron
2026-09-24 — Free models changed: added diffusiongemma, gemma-4-31b, gpt-oss-20b, llama-3.2-11b-vision, llama-3.2-90b-vision, mistral-nemotron, muse-glimmer-30b, nemotron-3-nano-omni, nemotron-3.5-lightning
2026-09-22 — Free models changed: added kimi-k3, laguna-xs-2.1, nemotron-3-super, nemotron-3-ultra; dropped nemotron
2026-07-27 — Free models changed: dropped llama-4
2026-07-19 — Added: Free hosted NIM endpoints for 100+ models via the free NVIDIA Developer Program (OpenAI-compatible at integrate.api.nvidia.com/v1)

Generated from registry.yaml on 2026-11-01 and re-verified twice a week; the full list, the Atom feed and the machinery are at https://github.com/mvalentsev/awesome-free-ai-coding.

Something wrong or missing? Suggest a service or a change — or read how the list works.