BedrockModels

Embedding models available through the AWS Bedrock API.

Amazon Nova Lite - Balanced performance and cost

Amazon Nova Micro - Ultra-fast, low-cost model for simple tasks

Amazon Nova Premier - Amazon's most capable model

Amazon Nova Pro - High-performance model for complex tasks

Claude 4.1 Opus sets new standards in:

Claude 4.5 Opus - Anthropic's intelligent, efficient, and the best model in the world for coding, agents, and computer use. It’s also meaningfully better at everyday tasks like deep research and working with slides and spreadsheets. Opus 4.5 is a step forward in what AI systems can do, and a preview of larger changes to how work gets done.

Claude Opus 4.6 is a frontier model with strong capabilities in software engineering, agentic tasks, and long context reasoning, as well as in knowledge work—including financial analysis, document creation, and multi-step research workflows.

Claude Opus 4.7 is Anthropic's latest generally available Opus model for advanced coding, long-running agents, knowledge work, and higher-resolution vision tasks.

Claude Haiku 4.5 - Anthropic's most powerful model for powering real-world agents, with industry-leading capabilities around coding, and computer use.

Claude 4.5 Sonnet - High-performance model with enhanced capabilities

Claude 4.6 Sonnet laude Sonnet 4.6 suggests the best combination of speed and intelligence. It’s a full upgrade of the model’s skills across coding, computer use, long-context reasoning, agent planning, knowledge work, and design.

Claude 4 Opus - Anthropic's previous flagship model

Claude 4 Sonnet - High-performance model with exceptional reasoning and efficiency

Google Gemma 3 12B IT - Instruction-tuned model with multimodal and structured output support

Google Gemma 3 27B IT - Largest Gemma 3 model with full multimodal and structured output support

Google Gemma 3 4B IT - Compact instruction-tuned model for on-device and edge deployment

Meta's Llama 3 70B Instruct

Meta's Llama 3 8B Instruct

Meta's Llama 3.1 405B Instruct

Meta's Llama 3.1 70B Instruct

Meta's Llama 3.1 8B Instruct

Meta's Llama 3.2 11B Instruct

Meta's Llama 3.2 1B Instruct

Meta's Llama 3.2 3B Instruct

Meta's Llama 3.2 90B Instruct

Meta's Llama 3.3 70B Instruct

MiniMax M2.5 - Agent-native frontier model optimized for efficient reasoning and task decomposition

Moonshot Kimi K2.5 - Multimodal model with improved reasoning, coding, and multilingual capabilities

Moonshot Kimi K2 Thinking - Advanced reasoning model with extended thinking capabilities

OpenAI GPT-OSS 120B - Mixture-of-Experts model for complex reasoning tasks

OpenAI GPT-OSS 20B - Efficient Mixture-of-Experts model for speed-sensitive applications