Moonshot AI

MoonshotAI: Kimi K2 0905

by Moonshot AItext->text1 endpoint
Neura Intelligence Index
65.5/ 100
Rank
#113
Confidence
low
Benchmarks
1(3% coverage)

Overview

Kimi K2 0905 is the September update of Kimi K2 0711. It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32...

Capabilities

Text generation
Tool use / Function calling
Structured output
Long context
Top-P sampling
Stop sequences
Deterministic seed

Modalities

Input
Text
Output
Text

Technical Specifications

Context Window
262.1K tokens
Max Output
98.3K tokens
Knowledge Cutoff
2024-12-31
Tokenizer
Other
Uptime (24h)
9999.9%
Parameters
1000000000000B
Country
🇨🇳CN
Release Date
September 5, 20251y

Supported Parameters

frequency_penaltymax_tokenspresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p

Benchmark Performance

reasoning

BenchmarkScoreSource
GPQA Diamond
75.8
verified

Performance Over Time

Pricing

Per 1M tokens
Input$0.60
Output$2.50
Added
September 4, 2025
Last synced 9/20/2026