Access large language models in one governed platform. Choose the model that fits your task and work across models without switching between separate tools.
The next generation of Anthropic's intelligent model, Claude Opus 4.5 is an industry leader across coding, agents, computer use, and enterprise workflows.
Claude Haiku 4.5 delivers near-frontier performance for a wide range of use cases, and stands out as one of the best coding and agent models–with the right speed and cost to power free products and high-volume user experiences.
Claude Opus 5 is Anthropic's most intelligent model, extending the Opus line's leadership across coding, agents, computer use, and enterprise workflows.
Claude Sonnet 4.5 is Anthropic's model optimized with significant improvements across all benchmarks.
Claude Sonnet 5 is Anthropic's most powerful model for powering real-world agents, with industry-leading capabilities around coding and computer use, and the ideal balance of performance and practicality for most internal and external use cases.
Gemini 2.5 Pro is Google's advanced reasoning Gemini model, capable of solving complex problems. It can comprehend vast datasets and challenging problems from different information sources.
Gemini 3 Pro Image is designed to tackle the most challenging image generation by incorporating state-of-the-art reasoning capabilities. It is the best model for complex and multi-turn image generation and editing.
Gemini 3.1 Flash Image (Nano Banana 2) is optimized for image understanding and generation and offers a balance of price and performance.
Gemini 3.1 Pro is Google's most advanced reasoning Gemini model, capable of solving complex problems.
Gemini 3.5 Flash delivers strong agentic capabilities at high speed and value, with configurable thinking levels for balancing latency and reasoning depth.
Gemini 3.5 Flash-Lite trades depth for speed and cost efficiency, making it suitable for high-throughput classification, routing, and extraction tasks.
Gemini 3.6 Flash is optimized for multi-step orchestration, full-stack code refactoring, and general reasoning, with improved token efficiency and code generation over Gemini 3.5 Flash.
Gemini 3.7 Flash brings Pro-level agentic capability to the Flash tier, with large gains in code generation and terminal execution over Gemini 3.6 Flash.
gpt-oss-120b is OpenAI's most powerful open-weight model, which fits into a single H100 GPU.
gpt-oss-20b is OpenAI's medium-sized open-weight model for low latency, local, or specialized use-cases.
Mistral Medium is a versatile model designed for a wide range of tasks, including programming, mathematical reasoning, understanding long documents, summarization, and dialogue.
Mistral Small 3.1 (25.03) is the enhanced version of Mistral Small 3, featuring multimodal capabilities and an extended context length of up to 128k.
Mistral Large 3 (675B parameters) served via AWS Bedrock; strong coding, reasoning, and multilingual capabilities with image input support.
GPT-4.1 excels at instruction following and tool calling, with broad knowledge across domains. It features a 1M token context window, and low latency without a reasoning step.
Fast, intelligent, flexible GPT model. GPT-4o (“o” for “omni”) is OpenAI's versatile, high-intelligence flagship model.
GPT-4o mini (“o” for “omni”) is a fast, affordable small model for focused tasks.
GPT-5 is OpenAI's previous model for coding, reasoning, and agentic tasks across domains.
An earlier GPT-5 model for coding and agentic tasks, with configurable reasoning and non-reasoning effort.
An earlier GPT-5 generation model for complex professional work.
OpenAI's cost-efficient model for coding and complex professional work.
OpenAI's previous frontier model for the most complex coding and professional work.
GPT-5.6 model optimized for cost-sensitive workloads.
OpenAI's frontier model for complex professional work.
GPT-5.6 model that balances intelligence and cost.
A lightweight, cost-effective search model optimized for quick, grounded answers with real-time web search.
An advanced search model designed for complex queries, delivering deeper content understanding with enhanced search result accuracy and 2x more search results than standard Sonar.
Built on Gemma-3-12b-pt, this model has been continually pre-trained on Traditional Chinese datasets and refined through instruction tuning. It is optimized for multi-turn dialogue and everyday office tasks, making it a highly capable assistant for both conversation and professional workflows.
Grok 4.2 is xAI's high-performance reasoning model with industry-leading speed and agentic tool calling, combining a very low hallucination rate with strict prompt adherence.
Grok 4.3 is xAI's fast, reliable model with strong tool calling and instruction following capabilities.
Grok 4.6 is SpaceXAI's frontier model built for coding, agentic tasks, and knowledge work.
