domino-ai-gateway

Access external LLM providers through Domino AI Gateway - a secure proxy with centralized API key management, usage monitoring, and compliance. Supports OpenAI, AWS Bedrock, Azure OpenAI, Anthropic, and more. Use when calling LLMs from Domino, configuring AI Gateway endpoints, or monitoring LLM usage and costs.

1.70x

Quality

—

Does it follow best practices?

Impact

97%

1.70x

Average score across 3 eval scenarios

Securityby

Risky

Do not use without reviewing

Evaluation results

92%

15%

Document Analysis Assistant

OpenAI client via AI Gateway with retry and logging

Criteria

Without context

With context

OpenAI client api_key

90%

100%

Gateway base_url

40%

100%

DOMINO_API_HOST env var

33%

Endpoint name as model

100%

Endpoint name constant

100%

RateLimitError import

100%

Exponential backoff

100%

Log prompt length

100%

Log response tokens

100%

Uses openai package

100%

32%

Research Report Generator

Direct API streaming with runtime auth token

Criteria

Without context

With context

Token from localhost

100%

Token stripped

37%

100%

DOMINO_API_HOST env var

100%

Correct API path

100%

Bearer auth header

100%

Streaming enabled

100%

Streaming response handling

100%

Endpoint name as model

100%

Uses requests library

100%

74%

LLM Pipeline Setup and Integration

LangChain integration with endpoint provisioning

Criteria

Without context

With context

Endpoint creation path

100%

Required endpoint fields

50%

100%

Token from localhost

100%

Bearer auth header for creation

100%

DOMINO_API_HOST usage

100%

LangChain openai_api_key

100%

LangChain gateway base URL

100%

Endpoint name as model in LangChain

100%

No hardcoded API key

100%

Repository: dominodatalab/domino-claude-plugin
Commit: 64f4433

Evaluated: 28 days ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Document Analysis Assistant Research Report Generator LLM Pipeline Setup and Integration

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.