NVIDIA NIM
INFERENCE82 MODEL · CONTEXT MAKS 1M
Catatan dari sumber
Free with NVIDIA Developer Program membership. 100+ models. Rate-limited per model.
Setup dalam 5 menit
Pilih target snippet
OPENAI SDK (NODE.JS)
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://integrate.api.nvidia.com/v1",
apiKey: process.env.NVIDIA_NIM_API_KEY,
});
const response = await client.chat.completions.create({
model: "deepseek-ai-deepseek-v4-1-flash",
messages: [{ role: "user", content: "Halo!" }],
});
console.log(response.choices[0].message.content);.ENV
NVIDIA_NIM_API_KEY=your-api-key-hereBelum punya API key? Ambil di halaman resmi NVIDIA NIM ↗.
Cara claim API key gratis
Langkah umum — detail pastinya ikuti halaman resmi NVIDIA NIM.
- 01Buka halaman API key NVIDIA NIM ↗
- 02Daftar akun baru, atau login kalau sudah punya.
- 03Generate API key di dashboard / settings.
- 04Pakai API key + Base URL
https://integrate.api.nvidia.com/v1di SDK atau HTTP client.
Model tersedia (82)
| MODEL | MODALITY | CONTEXT | OUTPUT | RATE LIMIT |
|---|---|---|---|---|
| deepseek-ai/deepseek-v4.1-flashdeepseek-ai-deepseek-v4-1-flash | text + image + reasoning | 1.0M | — | Up to 40 RPM |
| minimaxai/minimax-m3.1-flashminimaxai-minimax-m3-1-flash | text + image + video + reasoning | 1.0M | — | Up to 40 RPM |
| Nemotron 3.5 Super VL 120B A12Bnemotron-3-5-super-vl-120b-a12b | vision + reasoning | 1.0M | — | — |
| nvidia/nemotron-3-ultra-550b-a55b | Text | 1M | 262K | 40 RPM, 10,000 RPD |
| stepfun-ai/step-5-previewstepfun-ai-step-5-preview | text + image + reasoning | 1.0M | — | Up to 40 RPM |
| z-ai/glm-5.3z-ai-glm-5-3 | text + reasoning | 1.0M | 128K | Up to 40 RPM |
| z-ai/glm-5.3-flashz-ai-glm-5-3-flash | text + image + video + pdf + reasoning | 1.0M | 128K | Up to 40 RPM |
| google/gemma-4-31b-it | Text + Image + Video | 262K | 8K | 40 RPM, 10,000 RPD |
| moonshotai/kimi-k2.6moonshotai-kimi-k2-6 | text + image + video + reasoning | 262K | — | Up to 40 RPM |
| Nemotron 3 Super 120B A12Bnemotron-3-super-120b-a12b | reasoning | 262K | — | — |
| poolside/laguna-xs-2.1poolside-laguna-xs-2-1 | text + reasoning | 262K | — | Up to 40 RPM |
| Nemotron 3 Nano Omni 30B A3B Reasoningnemotron-3-nano-omni-30b-a3b-reasoning | vision + audio + reasoning | 256K | — | — |
| meta/llama-guard-4-12bmeta-llama-guard-4-12b | text + image | 164K | — | Up to 40 RPM |
| 01-ai/yi-large01-ai-yi-large | text | 131K | — | Up to 40 RPM |
| adept/fuyu-8badept-fuyu-8b | text | 131K | — | Up to 40 RPM |
| ai21labs/jamba-1.5-large-instructai21labs-jamba-1-5-large-instruct | text | 131K | — | Up to 40 RPM |
| aisingapore/sea-lion-7b-instructaisingapore-sea-lion-7b-instruct | text | 131K | — | Up to 40 RPM |
| bigcode/starcoder2-15bbigcode-starcoder2-15b | text | 131K | — | Up to 40 RPM |
| databricks/dbrx-instructdatabricks-dbrx-instruct | text | 131K | — | Up to 40 RPM |
| deepseek-ai/deepseek-coder-6.7b-instructdeepseek-ai-deepseek-coder-6-7b-instruct | text | 131K | — | Up to 40 RPM |
| google/codegemma-1.1-7bgoogle-codegemma-1-1-7b | text | 131K | — | Up to 40 RPM |
| google/codegemma-7bgoogle-codegemma-7b | text | 131K | — | Up to 40 RPM |
| google/deplotgoogle-deplot | text | 131K | — | Up to 40 RPM |
| google/gemma-2bgoogle-gemma-2b | text | 131K | — | Up to 40 RPM |
| google/recurrentgemma-2bgoogle-recurrentgemma-2b | text | 131K | — | Up to 40 RPM |
| ibm/granite-3.0-3b-a800m-instructibm-granite-3-0-3b-a800m-instruct | text | 131K | — | Up to 40 RPM |
| ibm/granite-3.0-8b-instructibm-granite-3-0-8b-instruct | text | 131K | — | Up to 40 RPM |
| ibm/granite-34b-code-instructibm-granite-34b-code-instruct | text | 131K | — | Up to 40 RPM |
| ibm/granite-8b-code-instructibm-granite-8b-code-instruct | text | 131K | — | Up to 40 RPM |
| meta/codellama-70bmeta-codellama-70b | text | 131K | — | Up to 40 RPM |
| meta/llama-3.2-11b-vision-instructmeta-llama-3-2-11b-vision-instruct | text + image | 131K | 4K | Up to 40 RPM |
| meta/llama2-70bmeta-llama2-70b | text | 131K | — | Up to 40 RPM |
| microsoft/kosmos-2microsoft-kosmos-2 | text | 131K | — | Up to 40 RPM |
| microsoft/phi-3-vision-128k-instructmicrosoft-phi-3-vision-128k-instruct | text | 131K | — | Up to 40 RPM |
| microsoft/phi-3.5-moe-instructmicrosoft-phi-3-5-moe-instruct | text | 131K | — | Up to 40 RPM |
| mistralai/codestral-22b-instruct-v0.1mistralai-codestral-22b-instruct-v0-1 | text | 131K | — | Up to 40 RPM |
| mistralai/mistral-7b-instruct-v0.3mistralai-mistral-7b-instruct-v0-3 | text | 131K | 64K | Up to 40 RPM |
| mistralai/mistral-large-2-instructmistralai-mistral-large-2-instruct | text | 131K | — | Up to 40 RPM |
| mistralai/mixtral-8x22b-v0.1mistralai-mixtral-8x22b-v0-1 | text | 131K | — | Up to 40 RPM |
| Muse Glimmer 30Bmuse-glimmer-30b | vision + reasoning | 131K | — | — |
| nv-mistralai/mistral-nemo-12b-instructnv-mistralai-mistral-nemo-12b-instruct | text | 131K | 4K | Up to 40 RPM |
| nvidia/cosmos-reason2-8bnvidia-cosmos-reason2-8b | text + image + video + reasoning | 131K | 16K | Up to 40 RPM |
| nvidia/llama-3.1-nemotron-51b-instructnvidia-llama-3-1-nemotron-51b-instruct | text | 131K | — | Up to 40 RPM |
| nvidia/llama-3.1-nemotron-70b-instructnvidia-llama-3-1-nemotron-70b-instruct | text | 131K | 8K | Up to 40 RPM |
| nvidia/llama-3.1-nemotron-ultra-253b-v1nvidia-llama-3-1-nemotron-ultra-253b-v1 | text + reasoning | 131K | 16K | Up to 40 RPM |
| nvidia/llama3-chatqa-1.5-70bnvidia-llama3-chatqa-1-5-70b | text | 131K | — | Up to 40 RPM |
| nvidia/mistral-nemo-minitron-8b-8k-instructnvidia-mistral-nemo-minitron-8b-8k-instruct | text | 131K | — | Up to 40 RPM |
| nvidia/nemotron-4-340b-instructnvidia-nemotron-4-340b-instruct | text | 131K | — | Up to 40 RPM |
| nvidia/nemotron-4-340b-rewardnvidia-nemotron-4-340b-reward | text | 131K | — | Up to 40 RPM |
| nvidia/nemotron-nano-3-30b-a3bnvidia-nemotron-nano-3-30b-a3b | text + reasoning | 131K | — | Up to 40 RPM |
| nvidia/nemotron-parsenvidia-nemotron-parse | text | 131K | — | Up to 40 RPM |
| nvidia/neva-22bnvidia-neva-22b | text | 131K | — | Up to 40 RPM |
| nvidia/nvclipnvidia-nvclip | text | 131K | — | Up to 40 RPM |
| nvidia/riva-translate-4b-instructnvidia-riva-translate-4b-instruct | text | 131K | — | Up to 40 RPM |
| nvidia/vilanvidia-vila | text | 131K | — | Up to 40 RPM |
| openai/gpt-oss-20b | Text | 131K | 131K | 40 RPM, 10,000 RPD |
| writer/palmyra-creative-122bwriter-palmyra-creative-122b | text | 131K | — | Up to 40 RPM |
| writer/palmyra-fin-70b-32kwriter-palmyra-fin-70b-32k | text | 131K | — | Up to 40 RPM |
| writer/palmyra-med-70bwriter-palmyra-med-70b | text | 131K | — | Up to 40 RPM |
| writer/palmyra-med-70b-32kwriter-palmyra-med-70b-32k | text | 131K | — | Up to 40 RPM |
| zyphra/zamba2-7b-instructzyphra-zamba2-7b-instruct | text | 131K | — | Up to 40 RPM |
| Llama 3.1 Nemotron Safety Guard 8B v3llama-3-1-nemotron-safety-guard-8b-v3 | text | 128K | — | — |
| nvidia/nemotron-3.5-content-safetynvidia-nemotron-3-5-content-safety | text + image + reasoning | 128K | — | Up to 40 RPM |
| google/diffusiongemma-26b-a4b-itgoogle-diffusiongemma-26b-a4b-it | text + vision | 8K | 32K | — |
| meta/llama-3.2-90b-vision-instructmeta-llama-3-2-90b-vision-instruct | text + vision | 8K | — | — |
| mistralai/mistral-large-3-675b-instruct-2512mistralai-mistral-large-3-675b-instruct-2512 | — | 8K | — | — |
| nvidia/ising-calibration-1.5-31bnvidia-ising-calibration-1-5-31b | — | 8K | — | — |
| nvidia/llama-3.1-nemoguard-8b-content-safetynvidia-llama-3-1-nemoguard-8b-content-safety | — | 8K | — | — |
| nvidia/llama-3.1-nemoguard-8b-topic-controlnvidia-llama-3-1-nemoguard-8b-topic-control | — | 8K | — | — |
| nvidia/nemotron-3.5-bolt-e4bnvidia-nemotron-3-5-bolt-e4b | — | 8K | — | — |
| nvidia/nemotron-3.5-lightning-30b-a3bnvidia-nemotron-3-5-lightning-30b-a3b | — | 8K | — | — |
| nvidia/nemotron-parse-2.0nvidia-nemotron-parse-2-0 | — | 8K | — | — |
| nvidia/riva-translate-4b-instruct-v2nvidia-riva-translate-4b-instruct-v2 | — | 8K | — | — |
| nvidia/embed-qa-4nvidia-embed-qa-4 | embedding | — | — | Up to 40 RPM |
| nvidia/llama-3.2-nemoretriever-1b-vlm-embed-v1nvidia-llama-3-2-nemoretriever-1b-vlm-embed-v1 | embedding + rerank | — | — | Up to 40 RPM |
| nvidia/llama-3.2-nv-embedqa-1b-v1nvidia-llama-3-2-nv-embedqa-1b-v1 | embedding | — | — | Up to 40 RPM |
| nvidia/llama-nemotron-embed-vl-1b-v2nvidia-llama-nemotron-embed-vl-1b-v2 | embedding + text + image | 8K | 2K | Up to 40 RPM |
| nvidia/nemotron-3-embed-1bnvidia-nemotron-3-embed-1b | embedding | — | — | Up to 40 RPM |
| nvidia/nemotron-3.5-embed-1bnvidia-nemotron-3-5-embed-1b | embedding | — | — | Up to 40 RPM |
| nvidia/nemotron-3.5-embed-8bnvidia-nemotron-3-5-embed-8b | embedding | — | — | Up to 40 RPM |
| nvidia/nv-embedqa-mistral-7b-v2nvidia-nv-embedqa-mistral-7b-v2 | embedding | — | — | Up to 40 RPM |
| snowflake/arctic-embed-lsnowflake-arctic-embed-l | embedding | — | — | Up to 40 RPM |
Model ini di provider lain
deepseek-ai-deepseek-v4-1-flash
nemotron-3-super-120b-a12b
openai/gpt-oss-20b
FAQ
Apakah API NVIDIA NIM gratis?
Ya — menurut sumber: "Free with NVIDIA Developer Program membership. 100+ models. Rate-limited per model." Data dari mnfst/awesome-free-llm-apis, freellm.net, models.dev, terakhir di-sync 31 Okt 2026 — cek sumber untuk kondisi terbaru.
Ada berapa model gratis di NVIDIA NIM?
82 model tercantum per 31 Okt 2026, termasuk deepseek-ai/deepseek-v4.1-flash, minimaxai/minimax-m3.1-flash, Nemotron 3.5 Super VL 120B A12B.
Berapa rate limit NVIDIA NIM?
Beda-beda per model, contoh: deepseek-ai/deepseek-v4.1-flash: Up to 40 RPM; minimaxai/minimax-m3.1-flash: Up to 40 RPM; nvidia/nemotron-3-ultra-550b-a55b: 40 RPM, 10,000 RPD. Limit lengkap per model, lihat tabel di atas.
Berapa context window maksimal di NVIDIA NIM?
1M.
DISINKRON 31 OKT 2026 · SUMBER: mnfst/awesome-free-llm-apis, freellm.net, models.dev