Kimi K3.1 Pro
2780.1B total, 106B active · 1024k context · Kimi K3.1 Pro License · released 2026-11-02
chatcodingagenticvisionreasoning
Cheapest way to run it in Canada today
Nothing in stock in Canada today runs Kimi K3.1 Pro fully in memory at 128k context at 15 tok/s or more. A shorter context needs less memory; the table below shows what comes closest.
What to run it on in Canada
Fully in memory at 128k context, priced at retailers today.
Nothing we price holds this model fully in memory.
All hardware that runs it
Everything we price, best value first. Two cards split the model by layers.
Nothing we price can run it at this context.
Memory needed
Weights, KV cache and runtime buffers at each context length (KV cache at fp16).
| Quant | File |
|---|
Run it
Copy a command for the runtime you use.
No published builds to run yet.
Notes
Custom licence; the card does not state its commercial-use terms, so check the LICENSE file. Weights are MXFP4 (quantization-aware training) and the model is recommended on vLLM, SGLang or TokenSpeed; multi-turn use requires passing back reasoning_content and tool_calls.
Questions
- What licence is Kimi K3.1 Pro released under?
- Kimi K3.1 Pro License.