Models

Very low-cost multimodal model that processes text, images and video quickly. A strong default for high-volume workloads.

amazon/nova-lite300K context$0.06/M input$0.24/M output

Text-only model optimized for the lowest latency and cost. Great for classification, routing, extraction and short chat turns.

amazon/nova-micro128K context$0.035/M input$0.14/M output

Highly capable multimodal model with the best balance of accuracy, speed and cost across a wide range of tasks.

amazon/nova-pro300K context$0.8/M input$3.2/M output

Anthropic's fastest model with near-frontier intelligence. Available through Bring Your Own Key with your AWS account.

anthropic/claude-haiku-4.5200K context$1/M input$5/M output

Anthropic's high-intelligence model for complex agents and coding. Available through Bring Your Own Key with your AWS account.

anthropic/claude-sonnet-4.5200K context$3/M input$15/M output

Open reasoning model trained with large-scale reinforcement learning. Excels at math, code and multi-step logic.

deepseek/deepseek-r1128K context$1.35/M input$5.4/M output

Hybrid reasoning model with sparse attention for long contexts. Strong at coding, tool use and agentic workflows.

deepseek/deepseek-v3.2128K context$0.62/M input$1.85/M output

Multilingual 70B instruction-tuned model with performance close to much larger models on reasoning, math and general knowledge.

meta/llama-3.3-70b-instruct128K context$0.72/M input$0.72/M output

Mixture-of-experts multimodal model with 128 experts and a 1M-token context window, tuned for assistant and chat use cases.

meta/llama-4-maverick1.0M context$0.24/M input$0.97/M output

124B multimodal model with frontier-level image understanding, strong document and chart analysis, and long-context reasoning.

mistral/pixtral-large128K context$2/M input$6/M output

OpenAI's open-weight 117B mixture-of-experts reasoning model. Available through Bring Your Own Key with your AWS account.

openai/gpt-oss-120b128K context$0.15/M input$0.6/M output

Dense 32B model with hybrid thinking, solid multilingual ability and good instruction following at a low price.

qwen/qwen3-32b131K context$0.15/M input$0.6/M output

Efficient mixture-of-experts coding model with 3B active parameters, built for repository-scale code understanding and agentic coding.

qwen/qwen3-coder-30b-a3b262K context$0.15/M input$0.6/M output