Anthropic ANTHROPIC_API_KEY
Google Gemini GOOGLE_API_KEY
Fireworks AI FIREWORKS_API_KEY
Perplexity PERPLEXITY_API_KEY
Together AI TOGETHERAPI_KEY
Model Recommendations by Use Case Choosing the right model depends on your specific requirements. Here’s a guide to help you select the best provider and model for your needs:
Best for: Building agents and applications that need to call external tools or functions
anthropic/claude-opus-4-5 - Excellent tool calling reliability with structured outputsanthropic/claude-sonnet-4-5-20250929 - Strong tool use with fast performanceopenai/gpt-5 - Native function calling support with structured responsesopenai/gpt-4o - Reliable tool calling for production applicationsdeepseek/deepseek-chat - Advanced tool use with multi-step reasoning
Coding & Development Best for: Code generation, debugging, and technical implementations
deepseek/deepseek-coder - Purpose-built for coding tasksopenai/gpt-5-codex - Specialized for code generation and completionanthropic/claude-opus-4-5 - Strong code understanding and generationanthropic/claude-sonnet-4-5-20250929 - Excellent coding with faster responsesxai/grok-code-fast-1 - Fast code-focused model
Reasoning & Complex Problem Solving Best for: Mathematical reasoning, logical analysis, and complex decision-making
anthropic/claude-opus-4-5 - Advanced reasoning capabilitiesopenai/o3 - Deep reasoning for complex problemsopenai/o1 - Strong multi-step reasoningdeepseek/deepseek-reasoner - Specialized reasoning modelxai/grok-4-fast-reasoning - Optimized for reasoning tasks
Speed & Efficiency Best for: High-throughput applications requiring fast responses
anthropic/claude-haiku-4-5-20251001 - Fast performance at lower costgoogle/gemini-2.5-flash - Optimized for throughput and low latencyopenai/gpt-5-mini - Lightweight, fast modelopenai/gpt-5-nano - Ultra-fast for simple tasksxai/grok-4-fast-non-reasoning - Quick responses without extended reasoning
Long Context Tasks Best for: Processing large documents, codebases, or extended conversations
google/gemini-2.5-pro - Up to 1M+ token context windowgoogle/gemini-2.0-flash - Large context with fast performanceanthropic/claude-opus-4-5 - Extended context for complex analysisanthropic/claude-sonnet-4-5-20250929 - Strong long-context capabilitiesopenai/gpt-4-32k - Extended 32K context window
Vision & Multimodal Best for: Image understanding, document analysis, and visual tasks
openai/gpt-4o - Strong vision capabilities with chatanthropic/claude-opus-4-5 - Advanced multimodal understandinganthropic/claude-sonnet-4-5-20250929 - Multimodal with fast performancegoogle/gemini-2.5-pro - Advanced vision and multimodal processingxai/grok-2-vision-1212 - Multimodal understanding
Many providers offer multiple model tiers (e.g., mini, standard, pro, opus) that balance cost, speed, and capability. Start with smaller models for testing and scale up based on your performance requirements.
Supported Models OpenAI Chat Models
openai/gpt-5.1openai/gpt-5openai/gpt-5-miniopenai/gpt-5-nanoopenai/gpt-5-chat-latestopenai/gpt-5-codexopenai/gpt-5-proopenai/gpt-4.1openai/gpt-4.1-miniopenai/gpt-4.1-nanoopenai/gpt-4oopenai/gpt-4o-2024-05-13openai/gpt-4o-miniopenai/gpt-4o-search-previewopenai/gpt-4o-mini-search-previewopenai/chatgpt-4o-latestopenai/gpt-4-turboopenai/gpt-4-turbo-2024-04-09openai/gpt-4openai/gpt-4-0125-previewopenai/gpt-4-1106-previewopenai/gpt-4-1106-vision-previewopenai/gpt-4-0613openai/gpt-4-0314openai/gpt-4-32kopenai/gpt-3.5-turboopenai/gpt-3.5-turbo-0125openai/gpt-3.5-turbo-1106openai/gpt-3.5-turbo-0613openai/gpt-3.5-0301openai/gpt-3.5-turbo-instructopenai/gpt-3.5-turbo-16k-0613
Reasoning Models
openai/o1openai/o1-proopenai/o1-miniopenai/o1-previewopenai/o3openai/o3-proopenai/o3-miniopenai/o3-deep-researchopenai/o4-miniopenai/o4-mini-deep-research
Image Generation Audio Transcription Embedding Models Model Price openai/text-embedding-3-large$0.13 / 1M tokens openai/text-embedding-3-small$0.02 / 1M tokens openai/text-embedding-ada-002$0.10 / 1M tokens
Anthropic (Claude) Claude 4.5 Series
anthropic/claude-opus-4-5anthropic/claude-haiku-4-5-20251001anthropic/claude-sonnet-4-5-20250929
Claude 4 Series
anthropic/claude-opus-4-1-20250805anthropic/claude-opus-4-20250514anthropic/claude-sonnet-4-20250514
Claude 3.7 Series
anthropic/claude-3-7-sonnet-20250219
Claude 3.5 Series
anthropic/claude-3-5-sonnet-20241022anthropic/claude-3-5-haiku-20241022
Claude 3 Series
anthropic/claude-3-opus-20240229anthropic/claude-3-sonnet-20240229anthropic/claude-3-haiku-20240307
Google (Gemini) Gemini 3 Series
google/gemini-3-pro-preview
Gemini 2.5 Series
google/gemini-2.5-progoogle/gemini-2.5-flashgoogle/gemini-2.5-flash-lite
Gemini 2.0 Series
google/gemini-2.0-flashgoogle/gemini-2.0-flash-expgoogle/gemini-2.0-flash-001google/gemini-2.0-flash-lite
Gemini 1.5 Series
google/gemini-1.5-progoogle/gemini-1.5-flash
Embedding Models
google/text-embedding-004
xAI (Grok) Grok 4 Series
xai/grok-4-fast-reasoningxai/grok-4-fast-non-reasoningxai/grok-code-fast-1xai/grok-4-0709
Grok 3 Series
xai/grok-3xai/grok-3-mini
Grok 2 Series
xai/grok-2xai/grok-2-1212xai/grok-2-vision-1212
Legacy DeepSeek
deepseek/deepseek-chatdeepseek/deepseek-reasonerdeepseek/deepseek-coder
Mistral
mistral/mistral-large-latestmistral/mistral-medium-latestmistral/mistral-small-latestmistral/codestral-2508mistral/open-mistral-nemo-2407mistral/pixtral-12b
Fireworks AI
fireworks_ai/accounts/fireworks/models/llama-v3p1-8b-instruct 
