Models
Browse 11 foundation models available through BedrockRouter — including 7 Anthropic Claude models and 4 MiniMax models. Pricing reflects AWS Bedrock on-demand rates.
anthropic.claude-opus-4-5-20251101-v1:0Anthropic's most capable model. Best for complex reasoning, agentic workflows, and frontier-level coding tasks.
Context
200K tokens
Max output
32K tokens
Input
$15.00 / 1M tok
Output
$75.00 / 1M tok
anthropic.claude-haiku-4-5-20251015-v1:0Fastest and most affordable Claude model. Near-Sonnet quality at a fraction of the cost — perfect for high-volume tasks.
Context
200K tokens
Max output
8K tokens
Input
$1.00 / 1M tok
Output
$5.00 / 1M tok
minimax.minimax-m2-v1:0MiniMax's flagship reasoning model. Strong on coding, agents, and tool calling — competitive with frontier models at lower cost.
Context
192K tokens
Max output
8K tokens
Input
$1.20 / 1M tok
Output
$4.80 / 1M tok
anthropic.claude-sonnet-4-5-20250929-v1:0Best balance of intelligence and cost. Industry-leading on coding benchmarks. Drop-in replacement for most production workloads.
Context
200K tokens
Max output
16K tokens
Input
$3.00 / 1M tok
Output
$15.00 / 1M tok
minimax.minimax-m1-v1:0Open-weight reasoning model with 1M-token context. Strong long-document understanding and agentic workflows.
Context
1M tokens
Max output
16K tokens
Input
$0.40 / 1M tok
Output
$2.20 / 1M tok
minimax.text-01-v1:0Hybrid attention model with 4M-token context. Excellent for retrieval-augmented generation over large knowledge bases.
Context
4M tokens
Max output
8K tokens
Input
$0.20 / 1M tok
Output
$1.10 / 1M tok
anthropic.claude-3-5-sonnet-20241022-v2:0The previous generation flagship. Strong reasoning, vision, and tool use — widely deployed in production.
Context
200K tokens
Max output
8K tokens
Input
$3.00 / 1M tok
Output
$15.00 / 1M tok
anthropic.claude-3-5-haiku-20241022-v1:0Fast, affordable model from the Claude 3.5 generation. Great for chat, summarization, and lightweight tool use.
Context
200K tokens
Max output
8K tokens
Input
$0.80 / 1M tok
Output
$4.00 / 1M tok
minimax.abab-7-v1:0Compact, fast chat model. Optimized for low-latency conversational interfaces and assistants.
Context
64K tokens
Max output
4K tokens
Input
$0.15 / 1M tok
Output
$0.60 / 1M tok
anthropic.claude-3-haiku-20240307-v1:0The most affordable Claude 3 model. Sub-second latency makes it ideal for simple, high-volume tasks.
Context
200K tokens
Max output
4K tokens
Input
$0.25 / 1M tok
Output
$1.25 / 1M tok
anthropic.claude-3-opus-20240229-v1:0Powerful Claude 3 generation flagship. Excellent on long-form analysis and creative writing.
Context
200K tokens
Max output
4K tokens
Input
$15.00 / 1M tok
Output
$75.00 / 1M tok
BedrockRouter is a transparent proxy — you pay AWS Bedrock's standard on-demand rates directly, billed through your own AWS account. We add zero markup. Prices shown are per 1 million tokens and reflect public Bedrock pricing as of November 2025. Final pricing is determined by AWS at request time.