name = "paligemma" description = "Gemini multimodal model for text, image, audio, video, and document tasks" release_date = "2024-05-14" last_updated = "2024-08-26" attachment = true reasoning = false temperature = true tool_call = false open_weights = true [cost] input = 0.0 output = 0.0 [limit] context = 128_000 output = 8_192 [modalities] input = ["text", "image"] output = ["text"]