Skip to main content

RoostGPT AI Provider Support for Unit, API and other Tests

Overview

RoostGPT supports multiple AI providers for comprehensive test generation across unit tests, API tests, Integration Tests, Functional Tests and more. This document outlines the supported providers and their available models.

Supported Providers:

  • OpenAI
  • Claude AI (Anthropic)
  • Azure OpenAI
  • Vertex AI (Google Cloud)
  • AWS Bedrock

OpenAI Models

Model NameContext WindowBest ForKey Features
GPT-5ExtendedComplex test scenarios, enterpriseExpert-level intelligence, built-in reasoning
GPT-5 ThinkingExtendedAdvanced test logic, edge casesExtended reasoning mode
GPT-4.5LargeStandard test generationBalanced performance, cost-effective
GPT-4oLargeFast test generationMultimodal, real-time processing
GPT-4o miniStandardHigh-volume generationCost-efficient, fast
GPT-4 Turbo128K tokensProduction environmentsProven reliability
o3ExtendedComplex reasoning tasksAdvanced chain-of-thought
o4-miniStandardCost-efficient reasoningFaster reasoning model

Claude AI (Anthropic) Models

Model NameContext WindowBest ForKey Features
Claude Opus 4.1200K tokensComplex coding tasks, unit testsBest coding model, 74.5% on SWE-bench
Claude Sonnet 4200K-1M tokensGeneral test generationSuperior coding and reasoning, instruction following
Claude Sonnet 3.7200K tokensHybrid reasoning tasksFast and extended thinking modes
Claude Sonnet 3.5200K tokensLegacy supportStrong coding capabilities
Claude Haiku 3.5200K tokensQuick, simple testsFast, cost-effective

 

Azure OpenAI Models

Azure OpenAI provides the same OpenAI models with enterprise features.

Model NameContext WindowAdditional Features
GPT-5 SeriesExtendedVNET integration, Private endpoints
GPT-4.5LargeManaged Identity, Regional deployment
GPT-4o SeriesLargeSLA guarantees, Azure Monitor
GPT-4 Turbo128K tokensStandard and Provisioned deployments
o3, o4-miniExtended/StandardAzure AD authentication

 

Vertex AI (Google Cloud) Models

Model NameContext WindowBest ForKey Features
Gemini 2.5 Pro2M tokensComplex API testing, large codebasesDeep Think mode, long context
Gemini 2.5 Pro Deep Think2M tokensHighly complex test logicEnhanced reasoning, problem-solving
Gemini 2.5 Flash1M tokensFast test generation, CI/CDBest price-performance, agentic
Gemini 2.5 Flash-LiteStandardHigh-volume testingMost cost-effective
Gemini 2.0 Flash1M tokensModern applicationsNative tool use, improved speed
Gemini 2.0 Flash-LiteStandardBudget projectsCost-efficient, low latency

 

AWS Bedrock Models

AWS Bedrock provides access to multiple foundation models from various providers in a fully managed service.

Available Model Families

ProviderModelsContext WindowBest For
AnthropicClaude Opus 4.1, Sonnet 4, Sonnet 3.7200K-1M tokensCode generation, unit tests

 

OpenAI

  • GPT-4o, GPT-5

Azure OpenAI

  • GPT-4o, GPT-5

Claude

  • Claude Sonnet 4.1

 

Support Resources


Back to top