MoonshotAI logo

MoonshotAI AI models

4 MoonshotAI models on FastRouter, all behind one OpenAI-compatible API. Compare pricing, context windows and benchmarks, then open any model for its providers and code samples.

Filter in catalog
Models
4
Largest context
1.05M
Kimi K3.1 Pro
Lowest input /1M
$0.68
Kimi K2.7 Code
Top intelligence
46.5
Kimi K3.1 Pro

All MoonshotAI models

MoonshotAI logo

Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and the first in the K3.1 series, a post-trained version of Kimi K3 with substantially more post-training compute, built on the same Kimi Delta Attention and Attention Residuals architecture (K3: 2.8T total, 104B active parameters; Moonshot calls K3.1 Pro 3T-class). It has a 1M-token context window with flat pricing across the full window, accepts text and images, and returns text, with always-on reasoning (effort: low, high, or max; default max) that cannot be turned off. It is designed for long-horizon coding, agentic and tool-using workflows, and complex knowledge work, and is exposed through an OpenAI-compatible chat completions API. Moonshot has said full weights will be released by November 4, 2026.

moonshotai/kimi-k3.1-proOct 23, 2026
Context
1.05M
Price /1M
$2.00 in$10.00 out
Intel
46.5
MoonshotAI logo

Kimi K3 is Moonshot AI’s 2.8-trillion-parameter flagship multimodal reasoning model with a 1M-token context window, designed for long-horizon coding, complex knowledge work, visual reasoning, and tool-using workflows. It uses Kimi Delta Attention and Attention Residuals to support efficient million-token contexts and always runs in high-effort reasoning mode. The model is exposed via an OpenAI-compatible chat completions API.

moonshotai/kimi-k3Jul 16, 20265.0s latency
Context
1.05M
Price /1M
$2.70 in$13.50 out
Intel
—
MoonshotAI logo

Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built for reliable end-to-end programming tasks over long contexts. It supports text and image input, always operates in thinking mode, and is designed for long-horizon coding, agentic task decomposition, tool use, and multi-turn workflows.

moonshotai/kimi-k2.7-codeJun 12, 20262.3s latency
Context
262K
Price /1M
$0.68 in$3.40 out
Intel
—
MoonshotAI logo

Moonshot AI's Kimi-K2.6 is a frontier-scale, open-source Mixture-of-Experts (MoE) multimodal model with 1 trillion total parameters (32B active), a 256K-262K token context window, and native support for text, image, and video inputs, excelling in long-horizon coding, agentic workflows, multi-agent orchestration, and complex software engineering.

moonshotai/kimi-k2.6Apr 20, 202617s latency
Context
262K
Price /1M
$0.75 in$3.50 out
Intel
—

Frequently asked questions

Model scores sourced from ArtificialAnalysis

MoonshotAI AI Models & API Pricing | FastRouter.ai