Skip to main content
Vijil supports direct evaluation of agents and models hosted on major cloud platforms. This guide covers configuration for each supported provider.

Supported Providers

ProviderHub IDSupported Targets
OpenAIopenaiGPT-4o, GPT-4, GPT-3.5
AnthropicanthropicClaude 3 family
AWS Bedrockbedrock / bedrockAgentsFoundation models, Bedrock Agents
Google Vertex AIvertexGemini family
DigitalOceandigitaloceanGenAI Platform agents
CustomcustomAny OpenAI-compatible endpoint

OpenAI

Store your OpenAI credentials via the API or dashboard before running an evaluation. Supported models include gpt-4o, gpt-4-turbo, gpt-4, and gpt-3.5-turbo.

Anthropic

Store your Anthropic credentials before running an evaluation. Supported models include the claude-3 family.

AWS Bedrock

Bedrock supports both foundation models and custom Bedrock Agents.

Foundation Models

Store your Bedrock access keys and specify the region to evaluate Foundation Models.
For Bedrock foundation models, prepend us. to the model ID from AWS’s supported models list.

Bedrock Agents

For Bedrock Agents, securely supply your agent_id, agent_alias_id, and AWS access configurations.

Google Vertex AI

Authenticate with Google Cloud and retrieve your application default credentials. Store the provided client_id, client_secret, and refresh_token in Vijil before targeting models from the gemini-1.5 or gemini-1.0 families.

DigitalOcean

Follow DigitalOcean’s guide to get your agent_id and agent_key, and securely provide them to Vijil.

Custom Endpoints

Evaluate any agent with an OpenAI-compatible API by storing your custom endpoint’s API key and providing the URL of the endpoint.
For local agents not yet deployed, use LocalAgentExecutor instead.

Rate Limiting

Control evaluation pace to avoid API throttling. You can set limits for the number of requests per interval when registering credentials.
ProviderRequests/minNotes
OpenAI60-100Depends on tier
Anthropic60-100Depends on tier
Bedrock30-60Model-dependent
Vertex AI60-120Project quotas apply

Work in Progress

The programmatic evaluation capabilities are currently in private preview and subject to change.

Next Steps

Running Evaluations

Execute and monitor evaluations

Custom Agents

Evaluate local agents

Understanding Results

Interpret evaluation results

Configure Protection

Set up Dome guardrails
Last modified on April 14, 2026