Sulat.com
AI models
$10 off the fastest DeepSeek V4.1 Flash, Kimi K3 and GLM 5.3 from Synthetic
ZenMux logo

Model details

Kimi K2 0905

Kimi K2 0905 is built on a mixture-of-experts architecture that balances massive scale with operational efficiency. By utilizing 1 trillion total parameters while activating only 32 billion per request, the model achieves a high level of precision for complex tasks. It is specifically engineered to excel in software development, offering advanced capabilities in code generation, file editing, and frontend design. The model is designed to act as a versatile toolkit for developers, supporting intricate agentic workflows where it can manage multiple tools simultaneously and handle large-scale data analysis with ease.

The model features a significant expansion in its processing capacity, supporting a 256,000-token context window that allows for deep, multi-turn interactions without losing coherence. Its lineage emphasizes practical utility in professional environments, evidenced by its seamless compatibility with agentic frameworks like LangChain and Claude Code. Beyond its coding prowess, the model maintains state-of-the-art creative writing performance with improved factual stability. With support for fine-tuning via methods like LoRA, it offers developers a path to customize the model for specific organizational needs while maintaining high-speed, reliable performance in production-grade applications.

ZenMuxmoonshotai/kimi-k2-0905deprecated

Quick Info

Powered by
Provider
ZenMux
Model key
moonshotai/kimi-k2-0905
Release date
Sep 4, 2025
Last updated
Sep 4, 2025
Knowledge cutoff
2025-01-01
Input modalities
Output modalities
Capabilities

Cost

Input token cost
$0.60
Output token cost
$2.50

Limits

Output tokens
64,000 tokens
Context window
262,000 tokens

Latest news about Kimi K2 0905

NovitaAI

CoverageRelease Notes

Opper AI's Moonshot release tracker confirms Kimi K2 0905 was released on 5 September 2025 with a 262K token context window, listed input pricing of $0.60 per million tokens and output pricing of $2.50 per million tokens. The tracker places Kimi K2 0905 in the Moonshot release sequence between the original Kimi K2 and The tracker attributes an intelligence score of 15 to Kimi K2 0905 within its composite methodology, without detailing the scoring approach. Out of 7 tracked Moonshot releases shown on the page, 5 are noted as running on Opper, giving developers a consolidated view of the Kimi family's pricing and capability progressio

Jiekou.AI

CoverageBenchmark

MoonshotAI's Kimi K2 0905 is documented as a Mixture-of-Experts model with 1 trillion total parameters and 32 billion active parameters (rumoured), featuring a 262K token context window and a release date of September 4, 2025. Benchable reports a 100% success rate across all tracked benchmarks, perfect accuracy in Hall Pricing on the page is listed at $0.6 per 1M prompt tokens and $2.5 per 1M completion tokens, with Moonshot AI's own endpoint shown as the primary provider entry alongside additional routing endpoints. The model supports tools, response format, and structured outputs, aligning with Moonshot's positioning of the 0905 up

Videos about Kimi K2 0905