← Back to all models

Phi-3-mini instruct (128k)

phi-3-mini-128k-instruct

Provider: GitHub Models, Context: 128000, Output Limit: 4096

Available at 6 Providers

Provider Source Input Price ($/1M) Output Price ($/1M) Description Free
githubmodels models-dev Input: $0.00 Output: $0.00 Provider: GitHub Models, Context: 128000, Output Limit: 4096
azure models-dev Input: $0.13 Output: $0.52 Provider: Azure, Context: 128000, Output Limit: 4096
azurecognitiveservices models-dev Input: $0.13 Output: $0.52 Provider: Azure Cognitive Services, Context: 128000, Output Limit: 4096
azureai litellm Input: $0.13 Output: $0.52 Source: azure_ai, Context: 128000
fireworksai litellm Input: $0.10 Output: $0.10 Source: fireworks_ai, Context: 131072
openrouter openrouter Input: $0.10 Output: $0.10 Phi-3 Mini is a powerful 3.8B parameter model designed for advanced language understanding, reasoning, and instruction following. Optimized through supervised fine-tuning and preference adjustments, it excels in tasks involving common sense, mathematics, logical reasoning, and code processing. At time of release, Phi-3 Medium demonstrated state-of-the-art performance among lightweight models. This model is static, trained on an offline dataset with an October 2023 cutoff date. Context: 128000