Markdown version for AI agents

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

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

Zerogpu Models

Browse all 13 AI models from Zerogpu

Total Models

13

Modes

1

Avg Input (1M Tokens)

$0.15

Avg Output (1M Tokens)

$0.72

All Zerogpu Models

Click on any model to view details

All Modes

Showing 13 of 13 models

Model Name↑	Provider	Mode	Pricing (tokens, images, audio, or pages)	Max Input Tokens	Max Output Tokens	Capabilities
deepseek-v4.1-flash zerogpu/deepseek-v4.1-flash	Zerogpu	Chat	Input $0.300000 / 1M tokensOutput $1.20 / 1M tokens	1048k	65,536	FunctionsReasoning
glm-5.3-flash zerogpu/glm-5.3-flash	Zerogpu	Chat	Input $0.100000 / 1M tokensOutput $0.350000 / 1M tokens	1048k	32,768	FunctionsReasoning
gpt-4.1-mini zerogpu/gpt-4.1-mini	Zerogpu	Chat	Input $0.400000 / 1M tokensOutput $1.60 / 1M tokens	1047k	32,768	Functions
gpt-5.4-nano zerogpu/gpt-5.4-nano	Zerogpu	Chat	Input $0.200000 / 1M tokensOutput $1.25 / 1M tokens	272k	128k	FunctionsReasoning
gpt-5.6-luna zerogpu/gpt-5.6-luna	Zerogpu	Chat	Input $0.200000 / 1M tokensOutput $1.20 / 1M tokens	272k	128k	FunctionsReasoning
gpt-6-luna zerogpu/gpt-6-luna	Zerogpu	Chat	Input $0.100000 / 1M tokensOutput $0.500000 / 1M tokens	272k	128k	FunctionsVisionReasoning
gpt-oss-120b zerogpu/gpt-oss-120b	Zerogpu	Chat	Input $0.150000 / 1M tokensOutput $0.600000 / 1M tokens	128k	32,768	FunctionsReasoning
LFM2.5-1.2B-Instruct zerogpu/LFM2.5-1.2B-Instruct	Zerogpu	Chat	Input $0.020000 / 1M tokensOutput $0.050000 / 1M tokens	32,768	8,192
LFM2.5-1.2B-Thinking zerogpu/LFM2.5-1.2B-Thinking	Zerogpu	Chat	Input $0.020000 / 1M tokensOutput $0.050000 / 1M tokens	32,768	8,192
llama-3.1-8b-instruct-fast zerogpu/llama-3.1-8b-instruct-fast	Zerogpu	Chat	Input $0.150000 / 1M tokensOutput $0.280000 / 1M tokens	131k	8,192	Functions
llama-3.2-3b-instruct-fast zerogpu/llama-3.2-3b-instruct-fast	Zerogpu	Chat	Input $0.050000 / 1M tokensOutput $0.300000 / 1M tokens	131k	8,192
qwen3-30b-a3b-fp8 zerogpu/qwen3-30b-a3b-fp8	Zerogpu	Chat	Input $0.100000 / 1M tokensOutput $0.450000 / 1M tokens	32,768	16,384	FunctionsReasoning
qwen3.6-35b-a3b zerogpu/qwen3.6-35b-a3b	Zerogpu	Chat	Input $0.200000 / 1M tokensOutput $1.50 / 1M tokens	262k	16,384	FunctionsVisionReasoning

Related Resources

Calculate Zerogpu costs →