NVIDIA NIM
Catatan dari sumber
Free with NVIDIA Developer Program membership. 100+ models. Rate-limited (no daily token cap).
Cara claim API key gratis
Langkah umum — detail pastinya ikutin halaman resmi NVIDIA NIM.
- 1.Buka halaman API key NVIDIA NIM ↗
- 2.Daftar akun baru, atau login kalau udah punya.
- 3.Generate API key di dashboard / settings.
- 4.Pakai API key + Base URL
https://integrate.api.nvidia.com/v1di SDK atau HTTP client.
Model tersedia (118)
- Modality
- Text
- Context
- 262K
- Output
- 262K
- Rate limit
- ~40 RPM
- Modality
- Text (reasoning)
- Context
- 128K
- Output
- ~163K
- Rate limit
- ~40 RPM
- Modality
- Text
- Context
- 128K
- Output
- 8K
- Rate limit
- ~40 RPM
- Modality
- Text
- Context
- 128K
- Output
- 4K
- Rate limit
- ~40 RPM
- Modality
- Text
- Context
- 128K
- Output
- 8K
- Rate limit
- ~40 RPM
- Modality
- Text
- Context
- 128K
- Output
- 4K
- Rate limit
- ~40 RPM
- Modality
- Text
- Context
- 128K
- Output
- 4K
- Rate limit
- ~40 RPM
- Modality
- Text
- Context
- 128K
- Output
- 32K
- Rate limit
- ~40 RPM
| Model | Modality | Context | Output | Rate limit |
|---|---|---|---|---|
nvidia/nemotron-3-super-120b-a12b nvidia/nemotron-3-super-120b-a12b | Text | 262K | 262K | ~40 RPM |
deepseek-ai/deepseek-r1 deepseek-ai/deepseek-r1 | Text (reasoning) | 128K | ~163K | ~40 RPM |
google/gemma-4-31b google/gemma-4-31b | Text | 128K | 8K | ~40 RPM |
meta/llama-3.1-405b-instruct meta/llama-3.1-405b-instruct | Text | 128K | 4K | ~40 RPM |
minimax/minimax-m2.7 minimax/minimax-m2.7 | Text | 128K | 8K | ~40 RPM |
mistralai/mistral-large-2-instruct mistralai/mistral-large-2-instruct | Text | 128K | 4K | ~40 RPM |
nvidia/llama-3.1-nemotron-ultra-253b-v1 nvidia/llama-3.1-nemotron-ultra-253b-v1 | Text | 128K | 4K | ~40 RPM |
nvidia/nemotron-3-nano-30b-a3b nvidia/nemotron-3-nano-30b-a3b | Text | 128K | 32K | ~40 RPM |
FAQ
Apakah API NVIDIA NIM gratis?
Ya — menurut sumber: "Free with NVIDIA Developer Program membership. 100+ models. Rate-limited (no daily token cap)." Data dari mnfst/awesome-free-llm-apis, freellm.net, cheahjs/free-llm-api-resources, models.dev, terakhir di-sync 19 Jul 2026 — cek sumber untuk kondisi terbaru.
Ada berapa model gratis di NVIDIA NIM?
118 model tercantum per 19 Jul 2026, termasuk nvidia/nemotron-3-super-120b-a12b, deepseek-ai/deepseek-r1, google/gemma-4-31b.
Berapa rate limit NVIDIA NIM?
Beda-beda per model, contoh: nvidia/nemotron-3-super-120b-a12b: ~40 RPM; deepseek-ai/deepseek-r1: ~40 RPM; google/gemma-4-31b: ~40 RPM. Limit lengkap per model, lihat tabel di atas.
Berapa context window maksimal di NVIDIA NIM?
262K (nvidia/nemotron-3-super-120b-a12b).