AI Providers

NVIDIA NIM

NVIDIA NIM provides hosted inference for large open-source models with fast GPU clusters. New accounts receive free API credits, and it has some of the largest models available including DeepSeek R1 671B and Qwen3 Coder 480B.

Getting your API key

  1. 1Visit integrate.api.nvidia.com and sign in with your NVIDIA account.
  2. 2Go to API Keys and generate a new key.
  3. 3Copy the key (starts with nvapi-).
  4. 4Paste it in Capsul under Settings → API Keys → NVIDIA NIM.

Available models in Capsul

ModelID
Nemotron Ultra 253Bnvidia/llama-3.1-nemotron-ultra-253b-v1
Kimi K2moonshotai/kimi-k2
DeepSeek R1 671Bdeepseek-ai/deepseek-r1
DeepSeek V3deepseek-ai/deepseek-v3-0324
Llama 4 Maverickmeta/llama-4-maverick-17b-128e-instruct
GLM-4.1V 9B Thinkingthudm/glm-4.1v-9b-thinking
Qwen3 Coder 480Bqwen/qwen3-coder-480b-a35b-instruct
QwQ 32Bqwen/qwq-32b

Free credits

New NVIDIA accounts receive a generous amount of free credits. Usage and remaining credits are visible in the NVIDIA developer portal. Because Capsul uses your own key, you are billed directly by NVIDIA — Capsul never charges you for AI usage.