LLM Models

The Large Language Model (LLM) NIM API endpoints provide simple access to use natural language based generative AI. This single API endpoint provides access to top models for use in a wide range of tasks including: chat, instruction following, question answering, summarization, creative text generation, and code generation.

NOTE: Select models are available as downloadable container images and supported with an NVIDIA AI Enterprise entitlement. These select models have additional OpenAI API spec details for running self-hosted localized NIMs. Please refer to the Downloadable NIM documentation for additional information.

URL: https://integrate.api.nvidia.com

Endpoint: POST /v1/chat/completions

Models

aisingapore

Model	Endpoint
aisingapore / sea-lion-7b-instruct	Create a chat completion (sea-lion-7b-instruct)

databricks

Model	Endpoint
databricks / dbrx-instruct	Create a chat completion (dbrx-instruct)

google

Model	Endpoint
google / gemma-7b	Create chat completion (gemma-7b)
google / gemma-2b	Create chat completion (gemma-2b)
google / codegemma-1.1-7b	Create chat completion (codegemma-1.1-7b)
google / codegemma-7b	Create chat completion (codegemma-7b)
google / recurrentgemma-2b	Create chat completion (recurrentgemma-2b)

ibm

Model	Endpoint
ibm / granite-34b-code-instruct	Create chat completion (granite-34b-code-instruct)
ibm / granite-8b-code-instruct	Create chat completion (granite-8b-code-instruct)

Model	Endpoint
meta / codellama-70b	Create chat completion (codellama-70b)
meta / llama2-70b	Create chat completion (llama2-70b)
meta / llama3-8b	Create chat completion (llama3-8b)
meta / llama3-70b	Create chat completion (llama3-70b)

microsoft

Model	Endpoint
microsoft / phi-3-medium-4k-instruct	Create chat completion (phi-3-medium-4k-instruct)
microsoft / phi-3-mini-128k-instruct	Create chat completion (phi-3-mini-128k-instruct)
microsoft / phi-3-mini-4k-instruct	Create chat completion (phi-3-mini-4k-instruct)
microsoft / phi-3-small-128k-instruct	Create chat completion (phi-3-small-128k-instruct)
microsoft / phi-3-small-8k-instruct	Create chat completion (phi-3-small-8k-instruct)

mistralai

Model	Endpoint
mistralai / mistral-7b-instruct	Create chat completion (mistral-7b-instruct)
mistralai / mixtral-8x7b-instruct	Create chat completion (mixtral-8x7b-instruct)
mistralai / mixtral-8x22b-instruct	Create chat completion (mixtral-8x22b-instruct)
mistralai / mistral-large	Create chat completion (mistral-large)

seallms

Model	Endpoint
seallms / seallm-7b-v2.5	Create chat completion (seallm-7b-v2.5)

snowflake

Model	Endpoint
snowflake / arctic	Create chat completion (arctic)