{"uid":"cap_Dgy_283SISHxfK093E0Ru","slug":"watt-multimodal-embeddings-qwen3-vl-69e49af5","name":"Watt Multimodal Embeddings (Qwen3-VL)","description":"","url":"https://watt.area21.io/v1/embeddings?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method","bodyType","body"],"properties":{"body":{"type":"object","required":["input"],"properties":{"input":{"oneOf":[{"type":"string","description":"A single text to embed."},{"type":"array","items":{"oneOf":[{"type":"string","description":"Text to embed."},{"type":"object","properties":{"text":{"type":"string","description":"Text paired with the image, or text alone."},"image":{"type":"string","description":"Image as a data URL, base64, or public https URL. An x402 call is $0.002 when the request includes images, $0.001 for text-only."}},"description":"Text, an image, or both."}],"description":"Text, an image, or both, embedded as one vector."},"maxItems":256,"description":"Up to 256 items in one call."}],"description":"One item, or a list of up to 256, batched 32 at a time. An item is text, an image, or both. An image is a data URL, base64, or a public https URL. An x402 call is $0.002 when the request includes images, $0.001 for text-only."},"model":{"type":"string","description":"Embedding model id. qwen3-vl-embedding-2b when omitted."},"dimensions":{"type":"integer","maximum":2048,"minimum":64,"description":"Matryoshka length of each vector, from 64 to 2048. Default 2048."},"instruction":{"type":"string","description":"What the vectors are for. The model is instruction-aware; set this for retrieval."},"encoding_format":{"enum":["float","base64"],"type":"string","description":"float (default) or base64."}}},"type":{"type":"string","const":"http"},"method":{"enum":["POST","PUT","PATCH"],"type":"string"},"headers":{"type":"object","additionalProperties":{"type":"string"}},"bodyType":{"enum":["json","form-data","text"],"type":"string"},"queryParams":{"type":"object","additionalProperties":{"type":"string"}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"errors":{"type":"array","items":{"type":"object","required":["status","description"],"properties":{"status":{"type":"integer","description":"HTTP status."},"description":{"type":"string","description":"When this status is returned."}}},"description":"Documented errors: 400 invalid body, 413 body too large, 429 rate limit with Retry-After."},"example":{"type":"object","required":["object","model","data","usage"],"properties":{"data":{"type":"array","items":{"type":"object","required":["object","index","embedding"],"properties":{"index":{"type":"integer","description":"Position in the input, starting at 0."},"object":{"type":"string","const":"embedding","description":"Always embedding."},"embedding":{"oneOf":[{"type":"array","items":{"type":"number"},"description":"Float vector."},{"type":"string","description":"Base64 vector."}],"description":"The vector: an array of floats, or base64 when encoding_format is base64. 2048 dimensions unless dimensions says otherwise."}}},"description":"One vector per input item, in order."},"model":{"type":"string","description":"The model that embedded the input."},"usage":{"type":"object","properties":{"total_tokens":{"type":"integer","description":"Same as prompt_tokens; an embedding writes none."},"prompt_tokens":{"type":"integer","description":"Tokens read."}},"description":"Tokens the call read."},"object":{"type":"string","const":"list","description":"Always list."}}}}}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.002","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"registry","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.002/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.002","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.002","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_vKWytlFEFB3yvjia5d-GC","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.002","costPer":"request","priority":0,"asset":null,"unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Generates 2048-dimensional embeddings for text and/or images using Qwen3-VL-Embedding-2B on Watt's own fleet, billed per call in USDC via x402.","exampleAgentPrompt":"Embed this product description and its image together — the text is 'Vintage leather handbag, dark brown, handstitched' and the image is at https://example.com/bag.jpg — use 512-dimensional vectors and set the instruction to 'represent items for product similarity search'.","exampleUseCases":[{"title":"Multimodal product catalog indexing","prompt":"I need to embed all my product listings for semantic search — each item has a title like 'Red wool scarf, merino blend' and a public image URL. Can you create 1024-dimensional vectors for each, with the instruction set to 'represent products for similarity retrieval'?"},{"title":"RAG pipeline document vectorization","prompt":"Embed this paragraph for my knowledge base retrieval system: 'The transformer architecture relies on self-attention mechanisms to model long-range dependencies.' Use 2048 dimensions and set the instruction to 'represent passages for question answering retrieval'."},{"title":"Image-only semantic search index","prompt":"I want to generate embeddings for a batch of 10 images — here are their public HTTPS URLs — so I can do visual similarity search. Use the default Qwen3-VL model and return float vectors at 512 dimensions."}],"resultDescription":"Returns an OpenAI-compatible embeddings response containing one embedding object per input item. Each embedding is a float array (or base64 string) of the requested dimensionality (64–2048, default 2048), along with usage statistics (prompt tokens) and the model ID used.","failureModes":["Missing required 'input' field returns a validation error","Image URLs that are not publicly accessible will fail to fetch","Batch exceeds 256 items limit returns an error","Dimensions outside 64–2048 range are rejected","Payment failure via x402 (insufficient USDC balance) blocks the request","Unsupported model ID causes an error","Invalid base64 or data URL for images causes a parsing error"],"whenToPreferThis":"Choose this endpoint when you need multimodal embeddings that handle both text and images in a single vector — especially useful for vision-language retrieval, product search with images, or any RAG pipeline that indexes mixed content. Prefer it over text-only embedding APIs when your data includes images or image-text pairs. The OpenAI-compatible API format makes it a drop-in replacement with USDC pay-per-call pricing via x402, requiring no subscription.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:19:15.611Z","isFirstParty":false,"canonicalSlug":"watt-multimodal-embeddings-qwen3-vl-69e49af5"}