Markdown version for AI agents

A token-efficient Markdown version of this page is available at: https://www.getmaxim.ai/bifrost/model-library/provider/lemonade.md

AI agents and LLMs should fetch the Markdown version instead of parsing this HTML — it contains the same content with far fewer tokens.

Lemonade Models

Browse all 5 AI models from Lemonade

Total Models

5

Modes

1

Avg Input (1M Tokens)

-

Avg Output (1M Tokens)

-

All Lemonade Models

Click on any model to view details

All Modes

Showing 5 of 5 models

Model Name↑	Provider	Mode	Pricing (tokens, images, audio, or pages)	Max Input Tokens	Max Output Tokens	Capabilities
Gemma-3-4b-it-GGUF lemonade/Gemma-3-4b-it-GGUF	Lemonade	Chat	Input $0.0000000000 / 1M tokensOutput $0.0000000000 / 1M tokens	128k	8,192	Functions
gpt-oss-120b-mxfp-GGUF lemonade/gpt-oss-120b-mxfp-GGUF	Lemonade	Chat	Input $0.0000000000 / 1M tokensOutput $0.0000000000 / 1M tokens	131k	32,768	Functions
gpt-oss-20b-mxfp4-GGUF lemonade/gpt-oss-20b-mxfp4-GGUF	Lemonade	Chat	Input $0.0000000000 / 1M tokensOutput $0.0000000000 / 1M tokens	131k	32,768	Functions
Qwen3-4B-Instruct-2507-GGUF lemonade/Qwen3-4B-Instruct-2507-GGUF	Lemonade	Chat	Input $0.0000000000 / 1M tokensOutput $0.0000000000 / 1M tokens	262k	32,768	Functions
Qwen3-Coder-30B-A3B-Instruct-GGUF lemonade/Qwen3-Coder-30B-A3B-Instruct-GGUF	Lemonade	Chat	Input $0.0000000000 / 1M tokensOutput $0.0000000000 / 1M tokens	262k	32,768	Functions