Kimi K3
Specifications
- Input
- Output
- Context window
- 1M tokens
- Released
- Jul 2026
Performance
- Speed
- 39 t/s
- TTFT
- 928 ms
- Latency
- 19.9s
- Intelligence
- —
Pricing
- Input
- €3.00 per 1M tokens
- Output
- €15.00 per 1M tokens
About this model
Kimi K3 is an open-weight, native multimodal agentic model and our most capable model to date. It is a 2.8T-parameter model built on Kimi Delta Attention (KDA) and Attention Residuals (AttnRes), with native vision capabilities and a 1-million-token context window. It is the world's first open 3T-class model, designed for frontier intelligence across long-horizon coding, knowledge work, and reasoning.
Technical specifications
- Capabilities
- Input modalities
- Output modalities
- Reasoning
- Hybrid Default on
See also
Add Model to Comparison
Search for a model to add