{"custom_id": "Bhola_6156_34371_6669_34884.png", "method": "POST", "url": "/v1/responses", "body": {"model": "gpt-4.1", "input": [{"role": "user", "content": [{"type": "input_text", "text": "You are analyzing a satellite/aerial image.\n\nImage dimensions:\n- Width: 513 pixels\n- Height: 513 pixels\n\nYou are analyzing a satellite/aerial image. Examine the image carefully and identify all regions that match these land cover types: farmland, built-up, meadow, forest, and water.\n\nFor each land cover type, provide bounding box coordinates for EVERY distinct region you can identify in the image.\n\nCRITICAL: You must respond with ONLY a JSON object. Do not include any explanatory text, markdown formatting, or code blocks. Your entire response should be valid JSON that can be parsed directly.\n\nReturn this exact JSON structure:\n{\n    \"farmland\": [[x1, y1, x2, y2], [x1, y1, x2, y2], ...],\n    \"built-up\": [[x1, y1, x2, y2], [x1, y1, x2, y2], ...],\n    \"meadow\": [[x1, y1, x2, y2], [x1, y1, x2, y2], ...],\n    \"forest\": [[x1, y1, x2, y2], [x1, y1, x2, y2], ...],\n    \"water\": [[x1, y1, x2, y2], [x1, y1, x2, y2], ...]\n}\n\nCoordinate format:\n- x1, y1: top-left corner (percentages 0-100)\n- x2, y2: bottom-right corner (percentages 0-100)\n- Use empty array [] if a class is not visible\n- Include multiple boxes for the same class if there are multiple regions\n\nExample valid response:\n{\"farmland\": [[10, 20, 50, 60]], \"built-up\": [[60, 10, 90, 40]], \"meadow\": [], \"forest\": [[5, 70, 30, 95]], \"water\": [[70, 50, 95, 80]]}\n\nNow analyze the provided image and return only the JSON object with bounding boxes.\n"}, {"type": "input_image", "image_url": "openai://file-4FDApBxP4NGyHzvaVBm4kt"}]}], "response_format": {"type": "json"}}}
{"custom_id": "Jamalpur_6156_31806_6669_32319.png", "method": "POST", "url": "/v1/responses", "body": {"model": "gpt-4.1", "input": [{"role": "user", "content": [{"type": "input_text", "text": "You are analyzing a satellite/aerial image.\n\nImage dimensions:\n- Width: 513 pixels\n- Height: 513 pixels\n\nYou are analyzing a satellite/aerial image. Examine the image carefully and identify all regions that match these land cover types: farmland, built-up, meadow, forest, and water.\n\nFor each land cover type, provide bounding box coordinates for EVERY distinct region you can identify in the image.\n\nCRITICAL: You must respond with ONLY a JSON object. Do not include any explanatory text, markdown formatting, or code blocks. Your entire response should be valid JSON that can be parsed directly.\n\nReturn this exact JSON structure:\n{\n    \"farmland\": [[x1, y1, x2, y2], [x1, y1, x2, y2], ...],\n    \"built-up\": [[x1, y1, x2, y2], [x1, y1, x2, y2], ...],\n    \"meadow\": [[x1, y1, x2, y2], [x1, y1, x2, y2], ...],\n    \"forest\": [[x1, y1, x2, y2], [x1, y1, x2, y2], ...],\n    \"water\": [[x1, y1, x2, y2], [x1, y1, x2, y2], ...]\n}\n\nCoordinate format:\n- x1, y1: top-left corner (percentages 0-100)\n- x2, y2: bottom-right corner (percentages 0-100)\n- Use empty array [] if a class is not visible\n- Include multiple boxes for the same class if there are multiple regions\n\nExample valid response:\n{\"farmland\": [[10, 20, 50, 60]], \"built-up\": [[60, 10, 90, 40]], \"meadow\": [], \"forest\": [[5, 70, 30, 95]], \"water\": [[70, 50, 95, 80]]}\n\nNow analyze the provided image and return only the JSON object with bounding boxes.\n"}, {"type": "input_image", "image_url": "openai://file-G7EHq1R8FBZ4VeYQdVm4ZT"}]}], "response_format": {"type": "json"}}}
{"custom_id": "Khagrachhari_7182_32832_7695_33345.png", "method": "POST", "url": "/v1/responses", "body": {"model": "gpt-4.1", "input": [{"role": "user", "content": [{"type": "input_text", "text": "You are analyzing a satellite/aerial image.\n\nImage dimensions:\n- Width: 513 pixels\n- Height: 513 pixels\n\nYou are analyzing a satellite/aerial image. Examine the image carefully and identify all regions that match these land cover types: farmland, built-up, meadow, forest, and water.\n\nFor each land cover type, provide bounding box coordinates for EVERY distinct region you can identify in the image.\n\nCRITICAL: You must respond with ONLY a JSON object. Do not include any explanatory text, markdown formatting, or code blocks. Your entire response should be valid JSON that can be parsed directly.\n\nReturn this exact JSON structure:\n{\n    \"farmland\": [[x1, y1, x2, y2], [x1, y1, x2, y2], ...],\n    \"built-up\": [[x1, y1, x2, y2], [x1, y1, x2, y2], ...],\n    \"meadow\": [[x1, y1, x2, y2], [x1, y1, x2, y2], ...],\n    \"forest\": [[x1, y1, x2, y2], [x1, y1, x2, y2], ...],\n    \"water\": [[x1, y1, x2, y2], [x1, y1, x2, y2], ...]\n}\n\nCoordinate format:\n- x1, y1: top-left corner (percentages 0-100)\n- x2, y2: bottom-right corner (percentages 0-100)\n- Use empty array [] if a class is not visible\n- Include multiple boxes for the same class if there are multiple regions\n\nExample valid response:\n{\"farmland\": [[10, 20, 50, 60]], \"built-up\": [[60, 10, 90, 40]], \"meadow\": [], \"forest\": [[5, 70, 30, 95]], \"water\": [[70, 50, 95, 80]]}\n\nNow analyze the provided image and return only the JSON object with bounding boxes.\n"}, {"type": "input_image", "image_url": "openai://file-GU6dPFjbCm4pxdFb4wZvG3"}]}], "response_format": {"type": "json"}}}
{"custom_id": "Gaibandha_5130_19494_5643_20007.png", "method": "POST", "url": "/v1/responses", "body": {"model": "gpt-4.1", "input": [{"role": "user", "content": [{"type": "input_text", "text": "You are analyzing a satellite/aerial image.\n\nImage dimensions:\n- Width: 513 pixels\n- Height: 513 pixels\n\nYou are analyzing a satellite/aerial image. Examine the image carefully and identify all regions that match these land cover types: farmland, built-up, meadow, forest, and water.\n\nFor each land cover type, provide bounding box coordinates for EVERY distinct region you can identify in the image.\n\nCRITICAL: You must respond with ONLY a JSON object. Do not include any explanatory text, markdown formatting, or code blocks. Your entire response should be valid JSON that can be parsed directly.\n\nReturn this exact JSON structure:\n{\n    \"farmland\": [[x1, y1, x2, y2], [x1, y1, x2, y2], ...],\n    \"built-up\": [[x1, y1, x2, y2], [x1, y1, x2, y2], ...],\n    \"meadow\": [[x1, y1, x2, y2], [x1, y1, x2, y2], ...],\n    \"forest\": [[x1, y1, x2, y2], [x1, y1, x2, y2], ...],\n    \"water\": [[x1, y1, x2, y2], [x1, y1, x2, y2], ...]\n}\n\nCoordinate format:\n- x1, y1: top-left corner (percentages 0-100)\n- x2, y2: bottom-right corner (percentages 0-100)\n- Use empty array [] if a class is not visible\n- Include multiple boxes for the same class if there are multiple regions\n\nExample valid response:\n{\"farmland\": [[10, 20, 50, 60]], \"built-up\": [[60, 10, 90, 40]], \"meadow\": [], \"forest\": [[5, 70, 30, 95]], \"water\": [[70, 50, 95, 80]]}\n\nNow analyze the provided image and return only the JSON object with bounding boxes.\n"}, {"type": "input_image", "image_url": "openai://file-Kvi1TyutNufDCR3hhkitGR"}]}], "response_format": {"type": "json"}}}
{"custom_id": "Khulna_21033_9747_21546_10260.png", "method": "POST", "url": "/v1/responses", "body": {"model": "gpt-4.1", "input": [{"role": "user", "content": [{"type": "input_text", "text": "You are analyzing a satellite/aerial image.\n\nImage dimensions:\n- Width: 513 pixels\n- Height: 513 pixels\n\nYou are analyzing a satellite/aerial image. Examine the image carefully and identify all regions that match these land cover types: farmland, built-up, meadow, forest, and water.\n\nFor each land cover type, provide bounding box coordinates for EVERY distinct region you can identify in the image.\n\nCRITICAL: You must respond with ONLY a JSON object. Do not include any explanatory text, markdown formatting, or code blocks. Your entire response should be valid JSON that can be parsed directly.\n\nReturn this exact JSON structure:\n{\n    \"farmland\": [[x1, y1, x2, y2], [x1, y1, x2, y2], ...],\n    \"built-up\": [[x1, y1, x2, y2], [x1, y1, x2, y2], ...],\n    \"meadow\": [[x1, y1, x2, y2], [x1, y1, x2, y2], ...],\n    \"forest\": [[x1, y1, x2, y2], [x1, y1, x2, y2], ...],\n    \"water\": [[x1, y1, x2, y2], [x1, y1, x2, y2], ...]\n}\n\nCoordinate format:\n- x1, y1: top-left corner (percentages 0-100)\n- x2, y2: bottom-right corner (percentages 0-100)\n- Use empty array [] if a class is not visible\n- Include multiple boxes for the same class if there are multiple regions\n\nExample valid response:\n{\"farmland\": [[10, 20, 50, 60]], \"built-up\": [[60, 10, 90, 40]], \"meadow\": [], \"forest\": [[5, 70, 30, 95]], \"water\": [[70, 50, 95, 80]]}\n\nNow analyze the provided image and return only the JSON object with bounding boxes.\n"}, {"type": "input_image", "image_url": "openai://file-HrQccCvoagvC3ZbEg6jzFk"}]}], "response_format": {"type": "json"}}}
{"custom_id": "Jamalpur_13851_33345_14364_33858.png", "method": "POST", "url": "/v1/responses", "body": {"model": "gpt-4.1", "input": [{"role": "user", "content": [{"type": "input_text", "text": "You are analyzing a satellite/aerial image.\n\nImage dimensions:\n- Width: 513 pixels\n- Height: 513 pixels\n\nYou are analyzing a satellite/aerial image. Examine the image carefully and identify all regions that match these land cover types: farmland, built-up, meadow, forest, and water.\n\nFor each land cover type, provide bounding box coordinates for EVERY distinct region you can identify in the image.\n\nCRITICAL: You must respond with ONLY a JSON object. Do not include any explanatory text, markdown formatting, or code blocks. Your entire response should be valid JSON that can be parsed directly.\n\nReturn this exact JSON structure:\n{\n    \"farmland\": [[x1, y1, x2, y2], [x1, y1, x2, y2], ...],\n    \"built-up\": [[x1, y1, x2, y2], [x1, y1, x2, y2], ...],\n    \"meadow\": [[x1, y1, x2, y2], [x1, y1, x2, y2], ...],\n    \"forest\": [[x1, y1, x2, y2], [x1, y1, x2, y2], ...],\n    \"water\": [[x1, y1, x2, y2], [x1, y1, x2, y2], ...]\n}\n\nCoordinate format:\n- x1, y1: top-left corner (percentages 0-100)\n- x2, y2: bottom-right corner (percentages 0-100)\n- Use empty array [] if a class is not visible\n- Include multiple boxes for the same class if there are multiple regions\n\nExample valid response:\n{\"farmland\": [[10, 20, 50, 60]], \"built-up\": [[60, 10, 90, 40]], \"meadow\": [], \"forest\": [[5, 70, 30, 95]], \"water\": [[70, 50, 95, 80]]}\n\nNow analyze the provided image and return only the JSON object with bounding boxes.\n"}, {"type": "input_image", "image_url": "openai://file-RdszzUoBQX5YNhKvjPcwkz"}]}], "response_format": {"type": "json"}}}
{"custom_id": "Bandarban_6669_1026_7182_1539.png", "method": "POST", "url": "/v1/responses", "body": {"model": "gpt-4.1", "input": [{"role": "user", "content": [{"type": "input_text", "text": "You are analyzing a satellite/aerial image.\n\nImage dimensions:\n- Width: 513 pixels\n- Height: 513 pixels\n\nYou are analyzing a satellite/aerial image. Examine the image carefully and identify all regions that match these land cover types: farmland, built-up, meadow, forest, and water.\n\nFor each land cover type, provide bounding box coordinates for EVERY distinct region you can identify in the image.\n\nCRITICAL: You must respond with ONLY a JSON object. Do not include any explanatory text, markdown formatting, or code blocks. Your entire response should be valid JSON that can be parsed directly.\n\nReturn this exact JSON structure:\n{\n    \"farmland\": [[x1, y1, x2, y2], [x1, y1, x2, y2], ...],\n    \"built-up\": [[x1, y1, x2, y2], [x1, y1, x2, y2], ...],\n    \"meadow\": [[x1, y1, x2, y2], [x1, y1, x2, y2], ...],\n    \"forest\": [[x1, y1, x2, y2], [x1, y1, x2, y2], ...],\n    \"water\": [[x1, y1, x2, y2], [x1, y1, x2, y2], ...]\n}\n\nCoordinate format:\n- x1, y1: top-left corner (percentages 0-100)\n- x2, y2: bottom-right corner (percentages 0-100)\n- Use empty array [] if a class is not visible\n- Include multiple boxes for the same class if there are multiple regions\n\nExample valid response:\n{\"farmland\": [[10, 20, 50, 60]], \"built-up\": [[60, 10, 90, 40]], \"meadow\": [], \"forest\": [[5, 70, 30, 95]], \"water\": [[70, 50, 95, 80]]}\n\nNow analyze the provided image and return only the JSON object with bounding boxes.\n"}, {"type": "input_image", "image_url": "openai://file-R48gSpe4qe7xuYD4trpiwp"}]}], "response_format": {"type": "json"}}}
{"custom_id": "Patuakhali_23085_21033_23598_21546.png", "method": "POST", "url": "/v1/responses", "body": {"model": "gpt-4.1", "input": [{"role": "user", "content": [{"type": "input_text", "text": "You are analyzing a satellite/aerial image.\n\nImage dimensions:\n- Width: 513 pixels\n- Height: 513 pixels\n\nYou are analyzing a satellite/aerial image. Examine the image carefully and identify all regions that match these land cover types: farmland, built-up, meadow, forest, and water.\n\nFor each land cover type, provide bounding box coordinates for EVERY distinct region you can identify in the image.\n\nCRITICAL: You must respond with ONLY a JSON object. Do not include any explanatory text, markdown formatting, or code blocks. Your entire response should be valid JSON that can be parsed directly.\n\nReturn this exact JSON structure:\n{\n    \"farmland\": [[x1, y1, x2, y2], [x1, y1, x2, y2], ...],\n    \"built-up\": [[x1, y1, x2, y2], [x1, y1, x2, y2], ...],\n    \"meadow\": [[x1, y1, x2, y2], [x1, y1, x2, y2], ...],\n    \"forest\": [[x1, y1, x2, y2], [x1, y1, x2, y2], ...],\n    \"water\": [[x1, y1, x2, y2], [x1, y1, x2, y2], ...]\n}\n\nCoordinate format:\n- x1, y1: top-left corner (percentages 0-100)\n- x2, y2: bottom-right corner (percentages 0-100)\n- Use empty array [] if a class is not visible\n- Include multiple boxes for the same class if there are multiple regions\n\nExample valid response:\n{\"farmland\": [[10, 20, 50, 60]], \"built-up\": [[60, 10, 90, 40]], \"meadow\": [], \"forest\": [[5, 70, 30, 95]], \"water\": [[70, 50, 95, 80]]}\n\nNow analyze the provided image and return only the JSON object with bounding boxes.\n"}, {"type": "input_image", "image_url": "openai://file-TUssMoDG5Fp8Nevi38jdxi"}]}], "response_format": {"type": "json"}}}
{"custom_id": "Maulvibazar_17955_15903_18468_16416.png", "method": "POST", "url": "/v1/responses", "body": {"model": "gpt-4.1", "input": [{"role": "user", "content": [{"type": "input_text", "text": "You are analyzing a satellite/aerial image.\n\nImage dimensions:\n- Width: 513 pixels\n- Height: 513 pixels\n\nYou are analyzing a satellite/aerial image. Examine the image carefully and identify all regions that match these land cover types: farmland, built-up, meadow, forest, and water.\n\nFor each land cover type, provide bounding box coordinates for EVERY distinct region you can identify in the image.\n\nCRITICAL: You must respond with ONLY a JSON object. Do not include any explanatory text, markdown formatting, or code blocks. Your entire response should be valid JSON that can be parsed directly.\n\nReturn this exact JSON structure:\n{\n    \"farmland\": [[x1, y1, x2, y2], [x1, y1, x2, y2], ...],\n    \"built-up\": [[x1, y1, x2, y2], [x1, y1, x2, y2], ...],\n    \"meadow\": [[x1, y1, x2, y2], [x1, y1, x2, y2], ...],\n    \"forest\": [[x1, y1, x2, y2], [x1, y1, x2, y2], ...],\n    \"water\": [[x1, y1, x2, y2], [x1, y1, x2, y2], ...]\n}\n\nCoordinate format:\n- x1, y1: top-left corner (percentages 0-100)\n- x2, y2: bottom-right corner (percentages 0-100)\n- Use empty array [] if a class is not visible\n- Include multiple boxes for the same class if there are multiple regions\n\nExample valid response:\n{\"farmland\": [[10, 20, 50, 60]], \"built-up\": [[60, 10, 90, 40]], \"meadow\": [], \"forest\": [[5, 70, 30, 95]], \"water\": [[70, 50, 95, 80]]}\n\nNow analyze the provided image and return only the JSON object with bounding boxes.\n"}, {"type": "input_image", "image_url": "openai://file-KvQv7d16VDbfKJqQMXnWEG"}]}], "response_format": {"type": "json"}}}
{"custom_id": "Rangpur_26163_18468_26676_18981.png", "method": "POST", "url": "/v1/responses", "body": {"model": "gpt-4.1", "input": [{"role": "user", "content": [{"type": "input_text", "text": "You are analyzing a satellite/aerial image.\n\nImage dimensions:\n- Width: 513 pixels\n- Height: 513 pixels\n\nYou are analyzing a satellite/aerial image. Examine the image carefully and identify all regions that match these land cover types: farmland, built-up, meadow, forest, and water.\n\nFor each land cover type, provide bounding box coordinates for EVERY distinct region you can identify in the image.\n\nCRITICAL: You must respond with ONLY a JSON object. Do not include any explanatory text, markdown formatting, or code blocks. Your entire response should be valid JSON that can be parsed directly.\n\nReturn this exact JSON structure:\n{\n    \"farmland\": [[x1, y1, x2, y2], [x1, y1, x2, y2], ...],\n    \"built-up\": [[x1, y1, x2, y2], [x1, y1, x2, y2], ...],\n    \"meadow\": [[x1, y1, x2, y2], [x1, y1, x2, y2], ...],\n    \"forest\": [[x1, y1, x2, y2], [x1, y1, x2, y2], ...],\n    \"water\": [[x1, y1, x2, y2], [x1, y1, x2, y2], ...]\n}\n\nCoordinate format:\n- x1, y1: top-left corner (percentages 0-100)\n- x2, y2: bottom-right corner (percentages 0-100)\n- Use empty array [] if a class is not visible\n- Include multiple boxes for the same class if there are multiple regions\n\nExample valid response:\n{\"farmland\": [[10, 20, 50, 60]], \"built-up\": [[60, 10, 90, 40]], \"meadow\": [], \"forest\": [[5, 70, 30, 95]], \"water\": [[70, 50, 95, 80]]}\n\nNow analyze the provided image and return only the JSON object with bounding boxes.\n"}, {"type": "input_image", "image_url": "openai://file-BXX68vpLuFuVDA9H7F49W1"}]}], "response_format": {"type": "json"}}}