GitHub

Model	Providers	Speed	Latency
microsoft/phi-3-vision-128k-instructFree	初叶🍂Furry API AI Claw API	N/A	N/A
phi-3-vision-128k-instructFree	Dext API Koyeb AI Gateway	N/A	N/A
cognitivecomputations/dolphin-mistral-24b-venice-edition:freeMistralFree	猫羽雫API 猫羽霖API	N/A	N/A
dolphin-mistral-24b-venice-editionMistralFree		N/A	N/A
microsoft/phi-4-mini-flash-reasoningFree		N/A	N/A
microsoft/phi-3.5-vision-instructFree		N/A	N/A
phi-4-reasoningFree		N/A	N/A
李/microsoft/phi-4-mini-flash-reasoning微软Free		N/A	N/A
李/microsoft/phi-3.5-vision-instruct微软Free		N/A	N/A
GitHub ModelsFree ReasoningToolsOpen Weights128KMicrosoft Phi 3.5 MoE Instruct is a mixture-of-experts instruction-tuned variant in the Phi series, optimized for following instructions and conversational tasks.	+8 moreShow fewer	N/A	N/A
GitHub ModelsFree 128KReasoningToolsOpen WeightsMicrosoft Phi 4 Multimodal Instruct is a multimodal instruction-tuned variant in the Phi series, optimized for following instructions and conversational tasks.	+10 moreShow fewer	N/A	N/A
微软Free Microsoft Phi 4 Mini Instruct is a compact instruction-tuned variant in the Phi series, optimized for quick responses and high throughput.	+6 moreShow fewer	N/A	N/A
MicrosoftFree ChatMicrosoft Phi-4 is a compact open-weight language model in the Phi series, optimized for reasoning, math, code generation, and efficient on-device or API deployment.	+1 moreShow fewer	N/A	N/A

Free Phi API