Model provider

ZeroGPU

Explore models served by ZeroGPU.

13models

Pricing & endpoints

13 offers · USD per million tokens
ModelProviderModel IDContextOutputInput / output · 1MReasoningToolsStructuredRoute
GLM-5.3-FlashZeroGPU
glm-5.3-flash
1,048,57632,768— / ————
View route
BGE Small EN v1.5ZeroGPU
bge-small-en-v1.5
5120— / ————
View route
Qwen3.6 35B-A3BZeroGPU
qwen3.6-35b-a3b
262,14416,384— / ————
View route
all-MiniLM-L6-v2ZeroGPU
all-minilm-l6-v2
2560— / ————
View route
Whisper TinyZeroGPU
whisper-tiny
448448— / ————
View route
DeepSeek V4.1 FlashZeroGPU
deepseek-v4.1-flash
1,048,57665,536— / ————
View route
GPT OSS 120BZeroGPU
gpt-oss-120b
131,072131,072— / ————
View route
Chatterbox NanoZeroGPU
chatterbox-nano
00— / ————
View route
GPT-5.4 nanoZeroGPU
gpt-5.4-nano
400,000128,000— / ————
View route
Llama-3.1-8B-InstructZeroGPU
llama-3.1-8b-instruct-fast
131,0728,192— / ————
View route
GPT-5.6 LunaZeroGPU
gpt-5.6-luna
272,000128,000— / ————
View route
GPT-4.1 miniZeroGPU
gpt-4.1-mini
1,047,57632,768— / ————
View route
Qwen3 30B A3BZeroGPU
qwen3-30b-a3b-fp8
32,76816,384— / ————
View route
1–13 of 13

Prices, limits and configurations apply to each serving offer. Open a model for its complete specifications and provider comparison.