The right model for every task. Try Nexus
Docs
Log in
Get started
Moonshot AI logo

Kimi K2.6

Ready
model path:accounts/fireworks/models/kimi-k2p6
Deploy on demandFine-tune

Kimi K2.6 is an open-source, native multimodal agentic model that advances practical capabilities in long-horizon coding, coding-driven design, proactive autonomous execution, and swarm-based task orchestration.

Kimi K2.6 API Features

Fine-tuning

Docs

Kimi K2.6 can be customized with your data to improve responses. Fireworks uses LoRA to efficiently train and deploy your personalized model

On-demand Deployment

Docs

On-demand deployments allow you to use Kimi K2.6 on dedicated GPUs with Fireworks' high-performance serving stack with high reliability and no rate limits.

Metadata

State
Ready
Created on
17 APR, 2026
Kind
Base model
Provider
Moonshot AI
Huggingface
moonshotai/Kimi-K2.6

Specifications

Calibrated
No
Mixture-of-Experts
Yes
Parameters
1.02T

Supporting Functionality

Fine-tuning
Supported
Serverless
Not Supported
Context Length
262k tokens
Function Calling
Supported
Embeddings
Not Supported
Rerankers
Not Supported
Supporting image input
Supported

Kimi K2.6 FAQs

Only on serverless, starting on September 25, 2026. On-demand deployment will continue to be available. Migrate serverless workloads to GLM-5.3 or Kimi K3.