NewJoin us for the Forge keynote livestream on November 3rd
DocsLog inGet started
Moonshot AI logo

Kimi K2.7 Code

Ready
model path:accounts/fireworks/models/kimi-k2p7-code
Deploy on demandFine-tune

Kimi K2.7 Code is a coding-focused agentic model built upon Kimi K2.6. With substantial improvements on real-world long-horizon coding tasks, it strengthens end-to-end task completion across complex software engineering workflows while improving token efficiency, reducing thinking-token usage by approximately 30% compared with Kimi K2.6.

Kimi K2.7 Code API Features

Fine-tuning

Docs

Kimi K2.7 Code 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 K2.7 Code on dedicated GPUs with Fireworks' high-performance serving stack with high reliability and no rate limits.

Metadata

State
Ready
Created on
12 JUN, 2026
Kind
Base model
Provider
Moonshot AI
Huggingface
moonshotai/Kimi-K2.7-Code

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 K2.7 Code 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.