Added Kimi K3.1 Pro - Highspeed: Added the Kimi K3.1 Pro - Highspeed model card and updated the Moonshot AI catalog and availability references (API compatibility, endpoint availability, and model Region availability). Kimi K3.1 Pro - Highspeed is availabl

Kimi K3.1 Pro - Highspeed

Model Details

Kimi K3.1 Pro - Highspeed is Moonshot AI's most capable open-weight model, combining native vision with a 1-million-token context window for long-running coding and knowledge workflows that sustain context across large repositories, documents, and images.

Capabilities and Features

• Context window: 1M tokens
• Reasoning: Effort configurable; values include none, low, medium, high, xhigh, and max
• Explicit Prompt Caching: Supported on Responses, Chat Completions, and InvokeModel APIs; not supported with Converse

Pricing

• Input: $4.00 (Global CRIS)
• Output: $20.00 (Global CRIS)
• Cache read: $0.20 (Global CRIS)
• Cache write (30 min): $5.00 (Global CRIS)

Service Tiers

• Standard: Pay-per-token access with no commitment
• Priority: Fastest response times for a price premium
• Flex: Lower-cost access for flexible, non-time-sensitive workloads

Regional Availability

Kimi K3.1 Pro - Highspeed is available through US Geo cross-Region inference, India geographic cross-Region inference, and Global cross-Region inference.

Quotas and Limits

• Burndown rate: 10x for output tokens

Usage Considerations and Limitations

• Prefer the OpenAI-compatible APIs over Converse
• Video inputs are not supported
• Place images before text for combined inputs
• Image detail parameter is honored only on the Chat Completions API

Sample Code

Follow the steps to set up your AWS account, generate an API key, install the SDK, and run your first inference request.

Source: AWS release notes

If you need further guidance on AWS, our experts are available at AWS@westloop.io. You may also reach us by submitting the Contact Us form.