## Basic tool info Model name: wiro/vlm-image-to-text Model description: It is an image-to-text tool for running different vision language models. Model cover: https://cdn.wiro.ai/uploads/models/wiro-vlm-image-to-text-cover.png Model categories: - tool - image-to-text - quick-showcase Run Task Endpoint (POST): https://api.wiro.ai/v1/Run/wiro/vlm-image-to-text Get Task Detail Endpoint (POST): https://api.wiro.ai/v1/Task/Detail ## Model Inputs: - name: selectedModel label: select-model help: select-model-help type: select default: "562" options: - value: "1608" label: moondream3-preview/detect description: Moondream3 is a cutting-edge vision-language model that delivers advanced visual reasoning with built-in object detection, pointing, and OCR capabilities—bringing fast, cost-effective, and scalable inference to real-world applications. triggerwords: [] generatesettings: [] categories: ["bf16","model","checkpoint-folder","persistent","image-to-text"] image: https://cdn.wiro.ai/uploads/models/moondream3-preview-detect-cover.webp samples: ["https://cdn.wiro.ai/uploads/models/moondream3-preview-detect-sample-1.txt","https://cdn.wiro.ai/uploads/models/moondream3-preview-detect-sample-2.txt","https://cdn.wiro.ai/uploads/models/moondream3-preview-detect-sample-3.txt"] marketplace: 1 inspire: [{"inputImage":"https://cdn.wiro.ai/uploads/sampleinputs/moondream-detect-input-1.png","prompt":"Speed limit"},{"inputImage":"https://cdn.wiro.ai/uploads/sampleinputs/moondream-detect-input-2.png","prompt":"Empty parking lot"},{"inputImage":"https://cdn.wiro.ai/uploads/sampleinputs/moondream-detect-input-3.png","prompt":"Needle"}] parameters: [{"title":"","subtitle":"","items":[{"advanced":false,"type":"combinefileinput","class":"is-12","required":false,"rows":"4","id":"inputImage","placeholder":"Input Image","label":"Input Image","defaultvalue":"https://cdn.wiro.ai/uploads/sampleinputs/moondream-detect-input-1.png","value":"https://cdn.wiro.ai/uploads/sampleinputs/moondream-detect-input-1.png","minvalue":"","maxvalue":"","incrementby":"","optionsLoad":"","options":[],"note":"Provide an image file or an image URL.","maxinputlenght":1},{"advanced":false,"type":"textarea","class":"is-12","required":true,"rows":"4","id":"prompt","placeholder":"prompt","label":"prompt","defaultvalue":"Speed limit","value":"Speed limit","minvalue":"","maxvalue":"","incrementby":"","optionsLoad":"","options":[],"note":"prompt-help"}]}] - value: "1607" label: moondream3-preview/point description: Moondream3 is a cutting-edge vision-language model that delivers advanced visual reasoning with built-in object detection, pointing, and OCR capabilities—bringing fast, cost-effective, and scalable inference to real-world applications. triggerwords: [] generatesettings: [] categories: ["bf16","model","checkpoint-folder","persistent","image-to-text"] image: https://cdn.wiro.ai/uploads/models/moondream3-preview-point-cover.webp samples: ["https://cdn.wiro.ai/uploads/models/moondream3-preview-point-sample-1.txt","https://cdn.wiro.ai/uploads/models/moondream3-preview-point-sample-3.txt"] marketplace: 1 inspire: [{"inputImage":"https://cdn.wiro.ai/uploads/sampleinputs/moondream-point-input-1.png","prompt":"empty parking slot"},{"inputImage":"https://cdn.wiro.ai/uploads/sampleinputs/moondream-point-input-3.png","prompt":"blue car"}] parameters: [{"title":"","subtitle":"","items":[{"advanced":false,"type":"combinefileinput","class":"is-12","required":false,"rows":"4","id":"inputImage","placeholder":"Input Image","label":"Input Image","defaultvalue":"https://cdn.wiro.ai/uploads/sampleinputs/moondream-point-input-1.png","value":"https://cdn.wiro.ai/uploads/sampleinputs/moondream-point-input-1.png","minvalue":"","maxvalue":"","incrementby":"","optionsLoad":"","options":[],"note":"Provide an image file or an image URL.","maxinputlenght":1},{"advanced":false,"type":"textarea","class":"is-12","required":true,"rows":"4","id":"prompt","placeholder":"prompt","label":"prompt","defaultvalue":"empty parking slot","value":"empty parking slot","minvalue":"","maxvalue":"","incrementby":"","optionsLoad":"","options":[],"note":"prompt-help"}]}] - value: "1606" label: moondream3-preview/caption description: Moondream3 is a cutting-edge vision-language model that delivers advanced visual reasoning with built-in object detection, pointing, and OCR capabilities—bringing fast, cost-effective, and scalable inference to real-world applications. triggerwords: [] generatesettings: [] categories: ["bf16","model","checkpoint-folder","persistent","image-to-text"] image: https://cdn.wiro.ai/uploads/models/moondream3-preview-caption-cover.webp samples: ["https://cdn.wiro.ai/uploads/models/moondream3-preview-caption-sample-1.txt","https://cdn.wiro.ai/uploads/models/moondream3-preview-caption-sample-2.txt","https://cdn.wiro.ai/uploads/models/moondream3-preview-caption-sample-3.txt"] marketplace: 1 inspire: [{"inputImage":"https://cdn.wiro.ai/uploads/sampleinputs/moondream-caption-input-1.png"},{"inputImage":"https://cdn.wiro.ai/uploads/sampleinputs/moondream-caption-input-2.png"},{"inputImage":"https://cdn.wiro.ai/uploads/sampleinputs/moondream-caption-input-3.png"}] parameters: [{"title":"","subtitle":"","items":[{"advanced":false,"type":"combinefileinput","class":"is-12","required":false,"rows":"4","id":"inputImage","placeholder":"Input Image","label":"Input Image","defaultvalue":"https://cdn.wiro.ai/uploads/sampleinputs/moondream-caption-input-1.png","value":"https://cdn.wiro.ai/uploads/sampleinputs/moondream-caption-input-1.png","minvalue":"","maxvalue":"","incrementby":"","optionsLoad":"","options":[],"note":"Provide an image file or an image URL.","maxinputlenght":1},{"advanced":false,"type":"selectwithcover","class":"is-12","required":false,"rows":"0","id":"length","placeholder":"Length","label":"Length","defaultvalue":"normal","value":"normal","minvalue":"","maxvalue":"","incrementby":"","optionsLoad":"","options":[{"value":"short","text":"Short"},{"value":"normal","text":"Normal"},{"value":"long","text":"Long"}],"note":""},{"advanced":true,"type":"float","class":"is-12","required":false,"rows":"0","id":"temperature","placeholder":"Temperature","label":"Temperature","defaultvalue":"0.7","value":"0.7","minvalue":"0","maxvalue":"5","incrementby":"0.01","optionsLoad":"","options":[],"note":"Adjusts randomness of outputs, greater than 1 is random and 0 is deterministic, 0.7 is a good starting value.","quick":false},{"advanced":true,"type":"float","class":"is-12","required":false,"rows":"0","id":"top_p","placeholder":"Top P","label":"Top P","defaultvalue":"0.95","value":"0.95","minvalue":"0","maxvalue":"1","incrementby":"0.01","optionsLoad":"","options":[],"note":"When decoding text, samples from the top p percentage of most likely tokens; lower to ignore less likely tokens.","quick":false}]}] - value: "1605" label: moondream3-preview/query description: Moondream3 is a cutting-edge vision-language model that delivers advanced visual reasoning with built-in object detection, pointing, and OCR capabilities—bringing fast, cost-effective, and scalable inference to real-world applications. triggerwords: [] generatesettings: [] categories: ["bf16","model","checkpoint-folder","persistent","image-to-text"] image: https://cdn.wiro.ai/uploads/models/moondream3-preview-query-cover.webp samples: ["https://cdn.wiro.ai/uploads/models/moondream3-preview-query-sample-1.txt","https://cdn.wiro.ai/uploads/models/moondream3-preview-query-sample-2.txt","https://cdn.wiro.ai/uploads/models/moondream3-preview-query-sample-3.txt"] marketplace: 1 inspire: [{"inputImage":"https://cdn.wiro.ai/uploads/sampleinputs/moondream-query-input-1.png","prompt":"List all the accessories in json format under 'accessories' key"},{"inputImage":"https://cdn.wiro.ai/uploads/sampleinputs/moondream-query-input-2.png","prompt":"List all the ingredients in the image"},{"inputImage":"https://cdn.wiro.ai/uploads/sampleinputs/moondream-query-input-3.png","prompt":"List the balls"}] parameters: [{"title":"","subtitle":"","items":[{"advanced":false,"type":"combinefileinput","class":"is-12","required":false,"rows":"4","id":"inputImage","placeholder":"Input Image","label":"Input Image","defaultvalue":"https://cdn.wiro.ai/uploads/sampleinputs/moondream-query-input-1.png","value":"https://cdn.wiro.ai/uploads/sampleinputs/moondream-query-input-1.png","minvalue":"","maxvalue":"","incrementby":"","optionsLoad":"","options":[],"note":"Provide an image file or an image URL.","maxinputlenght":1},{"advanced":false,"type":"textarea","class":"is-12","required":true,"rows":"4","id":"prompt","placeholder":"prompt","label":"prompt","defaultvalue":"List all the accessories in json format under 'accessories' key","value":"List all the accessories in json format under 'accessories' key","minvalue":"","maxvalue":"","incrementby":"","optionsLoad":"","options":[],"note":"prompt-help"},{"advanced":false,"type":"checkbox","class":"is-12","required":false,"rows":"0","id":"reasoning","placeholder":"Reasoning","label":"Reasoning","defaultvalue":"--reasoning","value":"--reasoning","minvalue":"","maxvalue":"","incrementby":"","optionsLoad":"","options":[],"note":"Whether to include detailed reasoning. Default value: true"},{"advanced":true,"type":"float","class":"is-12","required":false,"rows":"0","id":"temperature","placeholder":"Temperature","label":"Temperature","defaultvalue":"0.7","value":"0.7","minvalue":"0","maxvalue":"5","incrementby":"0.01","optionsLoad":"","options":[],"note":"Adjusts randomness of outputs, greater than 1 is random and 0 is deterministic, 0.7 is a good starting value.","quick":false},{"advanced":true,"type":"float","class":"is-12","required":false,"rows":"0","id":"top_p","placeholder":"Top P","label":"Top P","defaultvalue":"0.95","value":"0.95","minvalue":"0","maxvalue":"1","incrementby":"0.01","optionsLoad":"","options":[],"note":"When decoding text, samples from the top p percentage of most likely tokens; lower to ignore less likely tokens.","quick":false}]}] - value: "663" label: Salesforce/blip2-flan-t5-xl description: BLIP-2 creates captions or detailed descriptions for images. This is BLIP-2 model, leveraging Flan T5-xl. triggerwords: [] generatesettings: [] categories: ["model","image-to-text","checkpoint-folder"] image: https://cdn.wiro.ai/uploads/models/salesforce-blip2-flan-t5-xl-cover.webp samples: ["https://cdn.wiro.ai/uploads/models/salesforce-blip2-flan-t5-xl-sample-1.webp","https://cdn.wiro.ai/uploads/models/salesforce-blip2-flan-t5-xl-sample-2.webp","https://cdn.wiro.ai/uploads/models/salesforce-blip2-flan-t5-xl-sample-3.txt","https://cdn.wiro.ai/uploads/models/salesforce-blip2-flan-t5-xl-sample-4.txt"] marketplace: 1 parameters: [{"title":"","subtitle":"","items":[{"advanced":false,"type":"combinefileinput","class":"is-12","required":true,"rows":"4","id":"inputImage","placeholder":"Input Image","label":"Input Image","defaultvalue":"https://cdn.wiro.ai/uploads/sampleinputs/dinosaur.png","value":"https://cdn.wiro.ai/uploads/sampleinputs/dinosaur.png","minvalue":"","maxvalue":"","incrementby":"","optionsLoad":"","options":[],"note":"Provide an image file or an image URL.","maxinputlenght":1},{"advanced":false,"type":"textarea","class":"is-12","required":false,"rows":"4","id":"prompt","placeholder":"prompt","label":"prompt","defaultvalue":"What is a dinosaur holding?","value":"What is a dinosaur holding?","minvalue":"","maxvalue":"","incrementby":"","optionsLoad":"","options":[],"note":"prompt-help"},{"advanced":true,"type":"number","class":"is-12","required":false,"rows":"0","id":"tokens","placeholder":"tokens","label":"tokens","defaultvalue":"30","value":"30","minvalue":"1","maxvalue":"500","incrementby":"1","optionsLoad":"","options":[],"note":"inferencesteps-help"}]}] - value: "662" label: Salesforce/blip-image-captioning-large description: BLIP is a model that is able to perform various multi-modal tasks including visual question answering and image captioning. This is the blip image captioning large model. triggerwords: [] generatesettings: [] categories: ["model","image-to-text","checkpoint-folder"] image: https://cdn.wiro.ai/uploads/models/salesforce-blip-image-captioning-large-cover.webp samples: ["https://cdn.wiro.ai/uploads/models/salesforce-blip-image-captioning-large-sample-4.webp","https://cdn.wiro.ai/uploads/models/salesforce-blip-image-captioning-large-sample-5.webp","https://cdn.wiro.ai/uploads/models/salesforce-blip-image-captioning-large-sample-6.txt","https://cdn.wiro.ai/uploads/models/salesforce-blip-image-captioning-large-sample-7.txt"] marketplace: 1 parameters: [{"title":"","subtitle":"","items":[{"advanced":false,"type":"combinefileinput","class":"is-12","required":true,"rows":"4","id":"inputImage","placeholder":"Input Image","label":"Input Image","defaultvalue":"https://cdn.wiro.ai/uploads/sampleinputs/dinosaur.png","value":"https://cdn.wiro.ai/uploads/sampleinputs/dinosaur.png","minvalue":"","maxvalue":"","incrementby":"","optionsLoad":"","options":[],"note":"Provide an image file or an image URL.","maxinputlenght":1},{"advanced":false,"type":"textarea","class":"is-12","required":false,"rows":"4","id":"prompt","placeholder":"prompt","label":"prompt","defaultvalue":"There is a ","value":"There is a ","minvalue":"","maxvalue":"","incrementby":"","optionsLoad":"","options":[],"note":"prompt-help"},{"advanced":true,"type":"number","class":"is-12","required":false,"rows":"0","id":"tokens","placeholder":"tokens","label":"tokens","defaultvalue":"30","value":"30","minvalue":"1","maxvalue":"500","incrementby":"1","optionsLoad":"","options":[],"note":"inferencesteps-help"}]}] - value: "661" label: Salesforce/blip-image-captioning-base description: BLIP is a model that is able to perform various multi-modal tasks including visual question answering and image captioning. This is the blip image captioning base model. triggerwords: [] generatesettings: [] categories: ["model","image-to-text","checkpoint-folder","quick-showcase"] image: https://cdn.wiro.ai/uploads/models/Salesforce-blip-image-captioning-base-cover.png samples: ["https://cdn.wiro.ai/uploads/models/Salesforce-blip-image-captioning-base-sample-1.jpg","https://cdn.wiro.ai/uploads/models/Salesforce-blip-image-captioning-base-sample-4.txt","https://cdn.wiro.ai/uploads/models/Salesforce-blip-image-captioning-base-sample-3.jpg","https://cdn.wiro.ai/uploads/models/Salesforce-blip-image-captioning-base-sample-5.txt"] marketplace: 1 parameters: [{"title":"","subtitle":"","items":[{"advanced":false,"type":"fileinput","class":"is-12","required":false,"rows":"4","id":"inputImage","placeholder":"input-image","label":"input-image","defaultvalue":"https://cdn.wiro.ai/uploads/sampleinputs/dinosaur.png","value":"https://cdn.wiro.ai/uploads/sampleinputs/dinosaur.png","quick":true,"minvalue":"","maxvalue":"","incrementby":"","optionsLoad":"","options":[],"note":"input-image-help"},{"advanced":false,"type":"text","class":"is-12","required":false,"rows":"0","id":"inputImageUrl","placeholder":"input-image-url","label":"input-image-url","defaultvalue":"","value":"","minvalue":"","maxvalue":"","incrementby":"","optionsLoad":"","options":[],"note":"input-image-url-help"},{"advanced":false,"type":"textarea","class":"is-12","required":false,"rows":"4","id":"prompt","placeholder":"prompt","label":"prompt","defaultvalue":"There is a dinosaur","quick":true,"value":"There is a ","minvalue":"","maxvalue":"","incrementby":"","optionsLoad":"","options":[],"note":"prompt-help"},{"advanced":true,"type":"number","class":"is-12","required":false,"rows":"0","id":"tokens","placeholder":"tokens","label":"tokens","defaultvalue":"30","value":"30","minvalue":"1","maxvalue":"500","incrementby":"1","optionsLoad":"","options":[],"note":"inferencesteps-help"}]}] - value: "562" label: llava-hf/llava-v1.6-mistral-7b-hf description: LLaVA is a tool that generates descriptions for a given image. triggerwords: [] generatesettings: [] categories: ["model","llava-hf","image-to-text","checkpoint-folder"] image: https://cdn.wiro.ai/uploads/models/llava-hf-llava-v1-6-mistral-7b-hf-cover.webp samples: ["https://cdn.wiro.ai/uploads/models/llava-hf-llava-v1-6-mistral-7b-hf-sample-5.webp","https://cdn.wiro.ai/uploads/models/llava-hf-llava-v1-6-mistral-7b-hf-sample-6.webp","https://cdn.wiro.ai/uploads/models/llava-hf-llava-v1-6-mistral-7b-hf-sample-7.txt","https://cdn.wiro.ai/uploads/models/llava-hf-llava-v1-6-mistral-7b-hf-sample-8.txt"] marketplace: 1 parameters: [{"title":"","subtitle":"","items":[{"advanced":false,"type":"combinefileinput","class":"is-12","required":true,"rows":"4","id":"inputImage","placeholder":"Input Image","label":"Input Image","defaultvalue":"https://cdn.wiro.ai/uploads/sampleinputs/eiffel.jpeg","value":"https://cdn.wiro.ai/uploads/sampleinputs/eiffel.jpeg","minvalue":"","maxvalue":"","incrementby":"","optionsLoad":"","options":[],"note":"Provide an image file or an image URL.","maxinputlenght":1},{"advanced":false,"type":"textarea","class":"is-12","required":false,"rows":"4","id":"prompt","placeholder":"prompt","label":"prompt","defaultvalue":"What is shown in this image?","value":"What is shown in this image?","minvalue":"","maxvalue":"","incrementby":"","optionsLoad":"","options":[],"note":"prompt-help"},{"advanced":true,"type":"number","class":"is-12","required":false,"rows":"0","id":"tokens","placeholder":"tokens","label":"tokens","defaultvalue":"120","value":"120","minvalue":"1","maxvalue":"500","incrementby":"1","optionsLoad":"","options":[],"note":"inferencesteps-help"}]}] - value: "559" label: Salesforce/blip2-opt-2.7b description: BLIP-2 creates captions or detailed descriptions for images. triggerwords: [] generatesettings: [] categories: ["model","image-to-text","checkpoint-folder"] image: https://cdn.wiro.ai/uploads/models/wiro-blip-2-cover.png samples: ["https://cdn.wiro.ai/uploads/models/Salesforce-blip2-opt-2.7b-sample-9.jpg","https://cdn.wiro.ai/uploads/models/Salesforce-blip2-opt-2.7b-sample-10.jpg","https://cdn.wiro.ai/uploads/models/Salesforce-blip2-opt-2.7b-sample-11.txt","https://cdn.wiro.ai/uploads/models/Salesforce-blip2-opt-2.7b-sample-12.txt"] marketplace: 1 parameters: [{"title":"","subtitle":"","items":[{"advanced":false,"type":"fileinput","class":"is-12","required":false,"rows":"4","id":"inputImage","placeholder":"input-image","label":"input-image","defaultvalue":"https://cdn.wiro.ai/uploads/sampleinputs/dinosaur.png","value":"https://cdn.wiro.ai/uploads/sampleinputs/dinosaur.png","minvalue":"","maxvalue":"","incrementby":"","optionsLoad":"","options":[],"note":"input-image-help"},{"advanced":false,"type":"text","class":"is-12","required":false,"rows":"0","id":"inputImageUrl","placeholder":"input-image-url","label":"input-image-url","defaultvalue":"","value":"","minvalue":"","maxvalue":"","incrementby":"","optionsLoad":"","options":[],"note":"input-image-url-help"},{"advanced":false,"type":"textarea","class":"is-12","required":false,"rows":"4","id":"prompt","placeholder":"prompt","label":"prompt","defaultvalue":"What is a dinosaur holding?","value":"What is a dinosaur holding?","minvalue":"","maxvalue":"","incrementby":"","optionsLoad":"","options":[],"note":"prompt-help"},{"advanced":true,"type":"number","class":"is-12","required":false,"rows":"0","id":"tokens","placeholder":"tokens","label":"tokens","defaultvalue":"30","value":"30","minvalue":"1","maxvalue":"500","incrementby":"1","optionsLoad":"","options":[],"note":"inferencesteps-help"}]}] - name: selectedModelPrivate label: select-model-private help: select-model-private-help type: select default: "" options: - name: inputImageUrl label: input-image-url help: input-image-url-help type: text default: - name: prompt label: prompt help: type: textarea default: What is in the image? - name: tokens label: tokens help: inferencesteps-help type: number default: 30 ## Model Parameter Inspires: - prompt: What is shown in the image? - prompt: Can you describe the given image? - prompt: What is dinosaur holding? - prompt: What objects are present in the image? - prompt: What is the background of the image? ## Integration Header Prepare ```bash # Sign up Wiro dashboard and create project export YOUR_API_KEY="{{useSelectedProjectAPIKey}}"; export YOUR_API_SECRET="XXXXXXXXX"; # unix time or any random integer value export NONCE=$(date +%s); # hmac-SHA256 (YOUR_API_SECRET+Nonce) with YOUR_API_KEY export SIGNATURE="$(echo -n "${YOUR_API_SECRET}${NONCE}" | openssl dgst -sha256 -hmac "${YOUR_API_KEY}" | awk '{print $NF}')"; ``` ## Run Command - Make HTTP Post Request ```bash curl -X POST "https://api.wiro.ai/v1/Run/wiro/vlm-image-to-text" -H "Content-Type: multipart/form-data" -H "x-api-key: ${YOUR_API_KEY}" -H "x-nonce: ${NONCE}" -H "x-signature: ${SIGNATURE}" -d '{ "selectedModel": "562", "selectedModelPrivate": "", "inputImageUrl": "input-portrait-2.jpg", "prompt": "What is in the image?", "tokens": 30, "callbackUrl": "You can provide a callback URL; Wiro will send a POST request to it when the task is completed." }'; ``` ## Run Command - Response ```json { "errors": [], "taskid": "2221", "socketaccesstoken": "eDcCm5yyUfIvMFspTwww49OUfgXkQt", "result": true } ``` ## Get Task Detail - Make HTTP Post Request with Task ID ```bash curl -X POST "https://api.wiro.ai/v1/Task/Detail" -H "Content-Type: multipart/form-data" -H "x-api-key: ${YOUR_API_KEY}" -H "x-nonce: ${NONCE}" -H "x-signature: ${SIGNATURE}" -d '{ "taskid": "2221" }'; ``` ## Get Task Detail - Make HTTP Post Request with Socket Access Token ```bash curl -X POST "https://api.wiro.ai/v1/Task/Detail" -H "Content-Type: multipart/form-data" -H "x-api-key: ${YOUR_API_KEY}" -H "x-nonce: ${NONCE}" -H "x-signature: ${SIGNATURE}" -d '{ "tasktoken": "eDcCm5yyUfIvMFspTwww49OUfgXkQt" }'; ``` ## Get Task Detail - Response ```json { "total": "1", "errors": [], "tasklist": [ { "id": "2221", "uuid": "15bce51f-442f-4f44-a71d-13c6374a62bd", "socketaccesstoken": "eDcCm5yyUfIvMFspTwww49OUfgXkQt", "parameters": {}, "debugoutput": "", "debugerror": "", "starttime": "1734513809", "endtime": "1734513813", "elapsedseconds": "6.0000", "status": "task_postprocess_end", "createtime": "1734513807", "canceltime": "0", "assigntime": "1734513807", "accepttime": "1734513807", "preprocessstarttime": "1734513807", "preprocessendtime": "1734513807", "postprocessstarttime": "1734513813", "postprocessendtime": "1734513814", "totalcost": "0.003510000000", "chargedcost": "0.002808000000", "discountamount": "0.000702000000", "outputs": [ { "id": "6bc392c93856dfce3a7d1b4261e15af3", "name": "0.png", "contenttype": "image/png", "parentid": "6c1833f39da71e6175bf292b18779baf", "uuid": "15bce51f-442f-4f44-a71d-13c6374a62bd", "size": "202472", "addedtime": "1734513812", "modifiedtime": "1734513812", "accesskey": "dFKlMApaSgMeHKsJyaDeKrefcHahUK", "url": "https://cdn1.wiro.ai/6a6af820-c5050aee-40bd7b83-a2e186c6-7f61f7da-3894e49c-fc0eeb66-9b500fe2/0.png" } ], "size": "202472" } ], "result": true } ``` totalcost is the list price. chargedcost is the amount actually billed after any discount (a store fee is included on store runs); discountamount is the discount. chargedcost is null until the charge is recorded (shortly after task_postprocess_end) and "0" for a failed or cancelled task. ## Kill Task - Make HTTP Post Request with Task ID ```bash curl -X POST "https://api.wiro.ai/v1/Task/Kill" -H "Content-Type: multipart/form-data" -H "x-api-key: ${YOUR_API_KEY}" -H "x-nonce: ${NONCE}" -H "x-signature: ${SIGNATURE}" -d '{ "taskid": "534574" }'; ``` ## Kill Task - Make HTTP Post Request with Socket Access Token ```bash curl -X POST "https://api.wiro.ai/v1/Task/Kill" -H "Content-Type: multipart/form-data" -H "x-api-key: ${YOUR_API_KEY}" -H "x-nonce: ${NONCE}" -H "x-signature: ${SIGNATURE}" -d '{ "socketaccesstoken": "ZpYote30on42O4jjHXNiKmrWAZqbRE" }'; ``` ## Kill Task - Response ```json { "errors": [], "tasklist": [ { "id": "534574", "uuid": "15bce51f-442f-4f44-a71d-13c6374a62bd", "name": "", "socketaccesstoken": "ZpYote30on42O4jjHXNiKmrWAZqbRE", "parameters": { "inputImage": "https://api.wiro.ai/v1/File/mCmUXgZLG1FNjjjwmbtPFr2LVJA112/inputImage-6060136.png" }, "debugoutput": "", "debugerror": "", "starttime": "1734513809", "endtime": "1734513813", "elapsedseconds": "6.0000", "status": "task_cancel", "cps": "0.000585000000", "totalcost": "0.003510000000", "guestid": null, "projectid": "699", "modelid": "598", "description": "", "basemodelid": "0", "runtype": "model", "modelfolderid": "", "modelfileid": "", "callbackurl": "", "marketplaceid": null, "createtime": "1734513807", "canceltime": "0", "assigntime": "1734513807", "accepttime": "1734513807", "preprocessstarttime": "1734513807", "preprocessendtime": "1734513807", "postprocessstarttime": "1734513813", "postprocessendtime": "1734513814", "pexit": "0", "categories": "["tool","image-to-image","quick-showcase","compare-landscape"]", "outputs": [ { "id": "6bc392c93856dfce3a7d1b4261e15af3", "name": "0.png", "contenttype": "image/png", "parentid": "6c1833f39da71e6175bf292b18779baf", "uuid": "15bce51f-442f-4f44-a71d-13c6374a62bd", "size": "202472", "addedtime": "1734513812", "modifiedtime": "1734513812", "accesskey": "dFKlMApaSgMeHKsJyaDeKrefcHahUK", "foldercount": "0", "filecount": "0", "ispublic": 0, "expiretime": null, "url": "https://cdn1.wiro.ai/6a6af820-c5050aee-40bd7b83-a2e186c6-7f61f7da-3894e49c-fc0eeb66-9b500fe2/0.png" } ], "size": "202472" } ], "result": true } ``` ## Cancel Task - Make HTTP Post Request (For tasks on queue) ```bash curl -X POST "https://api.wiro.ai/v1/Task/Cancel" -H "Content-Type: multipart/form-data" -H "x-api-key: ${YOUR_API_KEY}" -H "x-nonce: ${NONCE}" -H "x-signature: ${SIGNATURE}" -d '{ "taskid": "634574" }'; ``` ## Cancel Task - Response ```json { "errors": [], "tasklist": [ { "id": "634574", "uuid": "15bce51f-442f-4f44-a71d-13c6374a62bd", "name": "", "socketaccesstoken": "ZpYote30on42O4jjHXNiKmrWAZqbRE", "parameters": { "inputImage": "https://api.wiro.ai/v1/File/mCmUXgZLG1FNjjjwmbtPFr2LVJA112/inputImage-6060136.png" }, "debugoutput": "", "debugerror": "", "starttime": "1734513809", "endtime": "1734513813", "elapsedseconds": "6.0000", "status": "task_cancel", "cps": "0.000585000000", "totalcost": "0.003510000000", "guestid": null, "projectid": "699", "modelid": "598", "description": "", "basemodelid": "0", "runtype": "model", "modelfolderid": "", "modelfileid": "", "callbackurl": "", "marketplaceid": null, "createtime": "1734513807", "canceltime": "0", "assigntime": "1734513807", "accepttime": "1734513807", "preprocessstarttime": "1734513807", "preprocessendtime": "1734513807", "postprocessstarttime": "1734513813", "postprocessendtime": "1734513814", "pexit": "0", "categories": "["tool","image-to-image","quick-showcase","compare-landscape"]", "outputs": [ { "id": "6bc392c93856dfce3a7d1b4261e15af3", "name": "0.png", "contenttype": "image/png", "parentid": "6c1833f39da71e6175bf292b18779baf", "uuid": "15bce51f-442f-4f44-a71d-13c6374a62bd", "size": "202472", "addedtime": "1734513812", "modifiedtime": "1734513812", "accesskey": "dFKlMApaSgMeHKsJyaDeKrefcHahUK", "foldercount": "0", "filecount": "0", "ispublic": 0, "expiretime": null, "url": "https://cdn1.wiro.ai/6a6af820-c5050aee-40bd7b83-a2e186c6-7f61f7da-3894e49c-fc0eeb66-9b500fe2/0.png" } ], "size": "202472" } ], "result": true } ``` ## Task Status Information This section defines the possible task status values returned by the API when polling for task completion. ### Completed Task Statuses (Polling can stop) These indicate that the task has reached a terminal state — either success or failure. Once any of these is received, polling should stop. - task_postprocess_end : Task completed successfully and post-processing is done. - task_cancel : Task was cancelled by the user or system. ### Running Task Statuses (Continue polling) These statuses indicate that the task is still in progress. Polling should continue if one of these is returned. - task_queue : Task is waiting in the queue. - task_accept : Task has been accepted for processing. - task_assign : Task is being assigned to a worker. - task_preprocess_start : Preprocessing is starting. - task_preprocess_end : Preprocessing is complete. - task_start : Task execution has started. - task_output : Output is being generated.