What is the context window of K2-Think by NanoGPT?

K2-Think by NanoGPT has a context window of 128K tokens. It supports up to 128K input tokens and can generate up to 33K output tokens.

What input and output types does K2-Think support?

K2-Think by NanoGPT accepts text as input and can generate text as output.

Is K2-Think by NanoGPT open source?

No, K2-Think by NanoGPT has closed weights. The model is only available through the NanoGPT API.

Back to Models

K2-Think API

NanoGPT

About

Process massive datasets with K2-Think, featuring an expansive 128K context window for long-document analysis. This model delivers cost-effective pricing at $0.17/1M input and $0.68/1M output tokens. Access K2-Think via the NanoGPT API with up to 33K output tokens.

Capabilities

Input Modalities

text

Output Modalities

text

Reasoning

Structured Output

Tool Use

WeightsClosed

Temperature

Fixed

Attachment

Not Supported

Limits

Context Window

128K

Tokens

Input Limit

128K

Tokens

Max Output

33K

Tokens

Pricing

Standard (per 1M tokens)

Input

$0.17

Output

$0.68

Frequently Asked Questions

K2-Think by NanoGPT costs $0.17 per 1M input tokens and $0.68 per 1M output tokens.

Model Details

LLM360/K2-Think

Provider

NanoGPT

Family

kimi-thinking

Release Date

Jul 26, 2025

Knowledge Cutoff

N/A

API Integration

NPM Package

@ai-sdk/openai-compatible

Environment Variables

NANO_GPT_API_KEY

API Base URL

https://nano-gpt.com/api/v1

Documentation