FW-Kimi-K3

Models available for use with Fireworks on Foundry deliver optimized, best-in-class performance on the Fireworks Inference Cloud. Fireworks on Foundry is a Non-Microsoft Product. The following terms apply to a Customer's use of Fireworks on Foundry: When you use Fireworks on Foundry, data is shared between Microsoft and Fireworks AI, Customer Data will be sent outside of Microsoft systems, Customer Data will not be processed pursuant to any Foundry data residency documentation, and different compliance and data handling rules will apply. See Trust Center - Fireworks AI for details. Customers are responsible for evaluating whether data sharing between Microsoft and Fireworks is appropriate for their organization's compliance requirements.

About this model

Kimi K3 is Moonshot AI's most capable model, a native-vision Mixture-of-Experts model with 2.8 trillion total parameters and a 1-million-token context window. It combines Kimi Delta Attention, Attention Residuals, and Stable LatentMoE to improve scaling efficiency and information flow across sequence length and model depth. Kimi K3 is designed for long-horizon coding, knowledge work, reasoning, and multimodal tasks.

Key model capabilities

• Long-horizon coding with support for sustained engineering tasks and large repositories
• Native vision for workflows that combine software engineering and visual reasoning
• Agentic knowledge work and long-context research
• 1-million-token context window
• Tool-assisted, multi-step reasoning
• Mixture-of-Experts architecture with 2.8T total parameters and 16 of 896 experts activated