Moonshot V1 32k

A language model with hundreds of billions of parameters launched by Moonshot AI, supporting a 32K context window, focusing on long - text understanding and code generation optimization, integrating a dynamic resolution function, supporting the processing of structured long texts such as PDFs and code libraries, and outperforming GPT - 4o by 12.7% in the Ruler long - context benchmark test.

Intelligence(Weak)

Speed(Slow)

Input Supported Modalities

Is Reasoning Model

32,000

Context Window

Maximum Output Tokens

Knowledge Cutoff

Go Compare

Pricing

￥1 /M tokens

Input

￥8 /M tokens

Output

￥2.75 /M tokens

Blended Price

Quick Simple Comparison

Input

Output

kimi-latest

moonshot-v1-32k

￥0.14

moonshot-v1-8k

￥0.07

Basic Parameters

moonshot-v1-32kTechnical Parameters

Parameter Count

Not Announced

Context Length

32.00k tokens

Training Data Cutoff

Open Source Category

Open Source

Multimodal Support

Text Only

Throughput

Release Date

2025-01-01

Response Speed

0 tokens/s

Benchmark Scores

Below is the performance of moonshot-v1-32k in various standard benchmark tests. These tests evaluate the model's capabilities in different tasks and domains.

Intelligence Index

Large Language Model Intelligence Level

Coding Index

Indicator of AI model performance on coding tasks

Math Index

Capability indicator in solving mathematical problems, mathematical reasoning, or performing math-related tasks

MMLU Pro

Massive Multitask Multimodal Understanding - Testing understanding of text, images, audio, and video

GPQA

Graduate Physics Questions Assessment - Testing advanced physics knowledge with diamond science-level questions

54.4

Graduate Physics Questions Assessment - Testing advanced physics knowledge with diamond science-level questions