The right model for every task. Try Nexus
Moonshot AI logo

Kimi K3.1 Pro

Ready
model path:accounts/fireworks/models/kimi-k3p1-pro

Kimi K3.1 Pro is an open-weight, natively multimodal agentic model from Moonshot AI. Post-trained from Kimi K3 with large-scale joint reinforcement learning across hundreds of downstream domains, it is the first model in the K3.1 series. With a 1-million-token context window, it delivers substantial improvements in coding, 3D creation, financial research, factual accuracy, and other agentic capabilities. Its Mixture-of-Experts architecture has 2.8T total parameters, 104B activated parameters and 93 layers. It supports text and image inputs and uses MXFP4 weights with MXFP8 activations through quantization-aware training.

Kimi K3.1 Pro API Features

Serverless

Docs

Kimi K3.1 Pro is available via Fireworks' serverless API, where you pay per token. There are several ways to call the Fireworks API, including Fireworks' Python client, the REST API, or OpenAI's Python client.

On-demand Deployment

Docs

On-demand deployments allow you to use Kimi K3.1 Pro on dedicated GPUs with Fireworks' high-performance serving stack with high reliability and no rate limits.

Available Serverless

$2.00 / $0.20 / $10.00

Run queries immediately, pay only for usage

Per 1M Tokens (input/cached input/output)

Metadata

State
Ready
Created on
2 NOV, 2026
Kind
Base model
Provider
Moonshot AI

Specifications

Calibrated
No
Mixture-of-Experts
Yes
Parameters
2.78T

Supporting Functionality

Fine-tuning
Not Supported
Serverless
Supported
Context Length
1040k tokens
Function Calling
Supported
Embeddings
Not Supported
Rerankers
Not Supported
Supporting image input
Supported