> ## Documentation Index
> Fetch the complete documentation index at: https://jigsaw-13.mintlify.app/llms.txt
> Use this file to discover all available pages before exploring further.

# Product Updates

> JigsawStack updates and announcements

<Update label="March 9, 2026" description="API Fixes and Updates" tags={["APIs","Interfaze","Translation Widget", "Playground", "Docs"]}>
  ### APIs

  * **AI Scraper**
    * Hardened AI Scraper for reliability under heavy usage.

  * **VOCR**
    * Improved handling for long-running file processing; requests exceeding limits now return 400 instead of failing silently.

  * **WEB SEARCH**
    * Fixed hallucination issue causing cost explosion

  ### Interfaze

  * **Pricing**
    * Reduced pricing to \$1.50/M input and \$3.50/M output tokens
  * **Playground**
    * Revamped the Playground for a better experience

  ### Translation Widget ( v1.1.4 )

  * Added Request Throttling
  * Added a new param which allows user to enable/disable font scaling.

  ### Deprecated APIs

  * Deprecated the following APIs: Image Generation, Image Translation, Embedding v1, Spell Check, Spam Detection, and Prompt Engine
</Update>

<Update label="24th Feb, 2026" description="API Fixes and Updates" tags={["APIs"]}>
  ### APIs

  * **AI Scraper**
    * Reduced response time significantly
  * **Object Detection**
    * Improved quality of GUI-based object detection
  * **STT**
    * Improved handling of invalid URLs

  ### INTERFAZE

  * Introduced rate limits
    * 50 requests per second
</Update>

<Update label="18th Feb, 2026" description="API Fixes and Updates" tags={["APIs", "SDKs", "INTERFAZE"]}>
  ### APIs

  * Fixed an issue with rate-limit enforcement for certain users/projects.
  * **AI Scraper**
    * Introduced `scroll` parameter - when enabled, automatically scrolls through the entire page to return full-page results. Defaults to `false`.
  * **STT**
    * Fixed timestamp millisecond precision.
  * OBJECT DETECTION
    * Fixed an issue with handling invalid URLs causing 500 HTTP errors
    * Improved API reliability with better validation checks.
  * STT
    * Language code and confidence are now grouped together instead of being two separate fields.

  ### Interfaze

  * Improved Structued output generation for general and visual based tasks
</Update>

<Update label="11th Feb, 2026" description="API Fixes and Updates" tags={["APIs"]}>
  ### APIs

  * Introduced rate limits to the API
    * Free — 50 req/min
    * Pro — 100 req/min
    * Custom — available on request via support
  * **DeepResearch**
    * Fixed several issues that caused API requests to fail.
  * **vOCR**
    * Fixed an issue where API requests failed when large files were passed.
  * **AI Scraper**
    * Improved API reliability with better validation checks.
  * **STT**
    * Language code and confidence are now grouped together instead of being two separate fields.

  ### Interfaze

  * Fixed a validation error when `developer` was used as the message role.
  * Fixed a validation error when `z.array()` was passed as the top-level schema wrapper.
  * Reduced pricing to:
    * \$3 per 1M input tokens
    * \$10 per 1M output tokens
</Update>

<Update label="12th Jan, 2026" description="API Fixes and Updates" tags={["APIs"]}>
  ### APIs

  * **Translate**
    * Fixed few issues that caused API Requests to fail when long texts were passed
  * **AI Scraper**
    * Improved API response time and performance

  ### INTERFAZE

  * Significantly reduced content generation time and improved response latency
</Update>

<Update label="22nd Dec, 2025" description="API Fixes and Updates" tags={["APIs"]}>
  ### APIs

  * **WEB SEARCH**
    * Improved social search in the Web Search API - you can now get better results when searching platforms like Twitter, LinkedIn, portfolios, and similar sources.
  * **AI Scraper**
    * Fixed an issue where the service was taking longer than expected while processing `element_prompts`.
</Update>

<Update label="14th Dec, 2025" description="API Fixes and Updates" tags={["INTERFAZE", "APIs"]}>
  ### APIs

  * **VOCR**
    * Fixed an issue where requests failed due to file access or download errors.
    * Resolved a timeout issue that occurred when fine\_grained was set to true.

  * **Embeddings**
    * Fixed a bug that caused embeddings to timeout unexpectedly.

  * **AI Scraper**
    * Improved reliability when scraping large websites.
    * Updated cookie handling to improve stability and security.

  ### INTERFAZE

  * Made major UI improvements to the Playground for a smoother experience.
  * Updated pre-context handling: it is now fetched conditionally based on the presence of specific headers.
</Update>

<Update label="8th Dec, 2025" description="API Fixes and Updates" tags={["INTERFAZE", "APIs", "SDKs"]}>
  ### APIs

  * **Web Search**

    * Upgraded web search to handle general search queries much faster & better.
    * Fixed an issue where geo search failed on large JSON responses.

  * **HTML to Any**
    * Fixed a bug where html-to-any requests intermittently failed.

  ### DEEP RESEARCH ( v0.1.4 )

  * Updated model intelligence using human evaluation signals.
  * Added repair text logic to stabilize recovery from failed structured outputs.

  ### INTERFAZE

  * Improved Interfaze search to deliver faster and more relevant responses.
</Update>

<Update label="1st Dec, 2025" description="API Fixes and Updates" tags={["INTERFAZE", "APIs", "SDKs"]}>
  ### SDKs

  * **Javascript ( v0.4.0 )**
    * Added optional file\_store\_key to TranslateImageParams for more flexible file handling.
    * Added optional steps to PredictionParams to support customizable prediction flows.
    * Added optional dimensions, instruction, and query to EmbeddingV2Params for enhanced embedding control.
    * Added optional name to PromptCreateParams for more flexible prompt definition.
    * Added fine\_grained option to VOCRParams for high-fidelity bounding box extraction.
    * Expanded element\_prompts in AIScrapeParams to accept a dictionary for richer element extraction.

  * **Python ( v0.4.0 )**
    * Added optional dimensions, instruction, and query to EmbeddingV2Params to support advanced embedding configurations.
    * Made steps optional in PredictionParams, with improved documentation for valid ranges and defaults.
    * Added optional name to PromptEngineCreateParams for clearer prompt identification.
    * Added optional max\_results to SearchParams, including request-side logic to honor the parameter.
    * Added optional fine\_grained to VOCRParams to enable high-fidelity, word-level bounding boxes.

  ### APIs

  * **AI Scraper**
    * Improved ad-blocking logic to reduce noise and improve DOM parsing reliability.

  * **Summary**
    * Fixed unusual timeouts while processing requests with urls.

  * **Web Search**
    * Enhanced geolocation searches in web search.

  ### DEEP RESEARCH

  * Fixed a schema validation bug in reasoning-plan generation.

  ### INTERFAZE

  * Resolved a bug that blocked user-defined overrides of the internal action layer.
  * Enhanced relevance and accuracy of financial data search results.
</Update>

<Update label="Nov 24th, 2025" description="API Fixes and Updates" tags={["INTERFAZE", "APIs"]}>
  ### APIs

  * **AI Scraper**
    * Improved AI Scraper reliability, performance, and schema validation.

  * **Web Search**
    * Improved web search results for Twitter-related queries.

  * **Deep-Research**
    * Ensured Deep Research API responses consistently include their underlying sources.

  * **Embedding-v2**
    * Added support for configurable embedding dimensions, with 4096 as the default for `v2/embedding`.

  * **Classification**
    * Fixed unusual timeout issues with image-classification.

  * **VOCR**
    * Enhanced VOCR word-level bounding boxes when using the `fine_grained` flag for more complete coverage.

  ### DeepResearch (open-source)

  * Migrated DeepResearch to OpenRouter for stable performance.
  * Reduced end-to-end latency, making long runs noticeably faster.
</Update>

<Update label="Nov 18th, 2025" description="API Fixes and Updates" tags={["INTERFAZE", "APIs"]}>
  ### APIs

  * **Prediction**
    * Resolved intermittent timeout issues.

  * **Speech-to-Text**
    * Fixed a bug that caused Javanese audio requests to fail.
    * Fixed an issue where m4a files failed to transcribe.

  * **VOCR**
    * Improved error propagation for clearer, more actionable error details.

  * **Translate**
    * Fixed a bug where valid requests were incorrectly blocked.

  * **Log ID**
    * Each request now comes with a Log ID to make support and debugging easier.

  ### INTERFAZE

  * Fixed a bug where URLs returned were placeholders.
  * Improved error propagation for clearer debugging.
</Update>

<Update label="Nov 11th, 2025" description="API Fixes and Updates" tags={["INTERFAZE", "APIs"]}>
  ### APIs

  * **Prediction**
    * Fixed timeout issues to improve reliability and response consistency.

  * **Speech-to-Text**
    * Improved speaker label accuracy and diarization for better multi-speaker transcription.
    * Fixed an issue preventing STT from accessing certain URLs.

  * **Web Search**
    * Refined handling of various edge cases to ensure more accurate results.
    * Expanded Historical Finance Index, now available for querying.

  ### INTERFAZE

  * Improved language detection accuracy for enhanced contextual understanding.
  * Added support for Feature Context and Thinking chunks during streaming for deeper insights.
  * Updated Playground UI to visualize these chunks, along with new documentation for developers.
</Update>

<Update label="Nov 4th, 2025" description="API Fixes and Updates" tags={["SDKs", "INTERFAZE", "APIs"]}>
  ### APIs

  * **Web Search:**
    * Enhanced AI Overview for richer, more accurate summaries
    * Improved historical finance data retrieval
  * **VOCR**:
    * Fixed issues with random spikes in latency.
  * **Speech to Text (STT)**:
    * Fixed timeout issues for smoother response handling
  * **Summary**:
    * Fixed timeout issues for smoother response handling
  * **Prompt Engine**:
    * Resolved timeout issues and improved reliability
  * **Speech to Text**:
    * We’ve improved our multilingual diarization service to reduce speaker confusion
  * **Translate**:
    * Fixed and improved input language detection accuracy
  * **Classification**
    * Upgraded multilingual models for higher-quality results across languages

  ### SDKs

  * Dropped Python support for versions 3.8 and below

  ### INTERFAZE

  * Enhanced the model’s vision capabilities
  * Added support to generate structured JSON with AI directly in the Playground
  * Improved error handling pipeline for better response consistency
</Update>

<Update label="October 16, 2025" description="API Fixes and Updates" tags={["SDKs", "DOCs", "APIs", "Others"]}>
  ### APIs

  * **VOCR:**
    * Fixed the issue where the lines and section output of ocr format was different when there is a prompt and no prompt. Fixed to standardize the format
    * Added confidence score for the words detected in the ocr format
  * **Web Search**: Improved the speed and quality of the web search model significantly
  * **Speech to Text (STT)**:
    * Updated suppport for longer than 5+ hour audio clips with diariazation
    * Fixed input validation for empty audio files
  * **Image Translate**:
    * Fixed input validation for the image translate API
    * Fixed a temporary outage caused by a recent deployment that affected image generation requests
  * **AI Scraper**: Fixed issue of large broad element selection for scraping. Now supports things like "body" or "main" as the element prompts.

  ### SDKs

  * **VOCR** Added confidence score for the words detected in the ocr format

  ### DOCS

  * Updated JigsawStack [Google Sheets integration](/docs/integration/google-sheets)
  * Added confidence score for words detected in the [VOCR](/docs/api-reference/ai/vocr) API

  ### Others

  * Updated our Postman Collection to include the most up to date APIs and features
</Update>

<Update label="September 29, 2025" description="API Fixes and Updates" tags={["DOCS", "Fixes", "APIs"]}>
  ### Fixes

  * Fixed **Embedding v1** API where sometimes the model would fail inconsistently
  * Fixed **Classification** API where the model would fail inconsistently for certain images
  * Fixed **AI Scraper** where the model would fail for pdf with large amount of pages

  ### APIs

  * **Speech to Text (STT):** Added confidnece score for the language detected. Available if language parameter is not provided or set to “auto”.
  * **Object to Detection:**: Improved the speed of the object detection model
  * Improved the speed of APIs that involves processing binary data. This includes:
    * Object Detection
    * Speech to Text (STT)
    * Embedding v1
    * Embedding v2
    * Image Translation
    * vOCR
    * NSFW
    * File Upload

  ### DOCS

  * Introduced JigsawStack [Google Sheets integration](/docs/integration/google-sheets)
  * Added confidence score for the language detected in the [STT](/docs/api-reference/ai/speech-to-text) API
  * Added warning for the deprecated [Image Generation](/docs/api-reference/ai/image-generation) API
</Update>

<Update label="September 19, 2025" description="Python v0.3.7, JavaScript v0.3.6" tags={["DOCS", "Fixes", "SDKs"]}>
  ### Fixes

  * Updated **Object Detection** API to accept "object" parameter as an alternative to "object\_detection"
  * Fixed **Object Detection** API for pure GUI images
  * Improved **Speech to Text (STT)** webhook error handling with 400 status code for empty files
  * Enhanced **Object Detection** tag generation for more accurate and relevant results

  ### SDKs

  * Updated **Object Detection** now supports "object" parameter as an alternative to "object\_detection"
  * Updated **Speech to Text (STT)** to return `language_detected` and `confidence` in the response

  ### DOCS

  * Added documentation for [Embedding v2](/docs/api-reference/ai/embedding-v2) parameters: `instructions` and `query`
  * Added documentation for [Object Detection](/docs/api-reference/ai/object-detection) parameters: `return_masks`
  * Fixed CURL example for [File Uploads](/docs/api-reference/store/file/add)
  * Fixed C# examples on all APIs
  * Updated [Speech to Text (STT)](/docs/api-reference/ai/speech-to-text) documentation to include parameters: `chunk_duration`, `language_detected`, and `confidence`
</Update>

<Update label="September 15, 2025" description="v0.3.4 - v0.3.5" tags={["SDKs", "Fixes", "DOCS"]}>
  ### Fixes

  * Added support for **NSFW** API when images are not available
  * Added support for **HTML to Any** now works with all HTML tags as input
  * Fixed **File Upload** now works with Embedding v2
  * Fixed **VOCR** for PDF in certain edge cases
  * Fixed **AI Scraper** returning invalid JSON for empty element\_prompts
  * Decrease latency for **AI Scraper**

  ### DOCS

  * Updated File Uploads documentation [Handling Files](/docs/api-reference/handling-files)
  * Renamed embeddingV2 method to embedding\_v2 for consistency

  ### SDKs

  * Updated the way multipart/form-data are handled for APIs involved with file uploads
  * Renamed embeddingV2 method to embedding\_v2 for consistency

  #### Python

  * Fixed blob inputs for **Object Detection** where previously features params was not respected
  * Fixed blob inputs for **VOCR** where page range was not respected
  * Established CI/CD pipeline for Python SDK
  * Updated to pass **x-jigsaw-no-request-log** through headers. [Security](/docs/security)

  #### JavaScript

  * Fixed blob inputs for **Object Detection** where previously features params was not respected
  * Fixed blob inputs for **VOCR** where page range was not respected
</Update>

<Update label="September 8, 2025" description="Python v0.3.3, JavaScript v0.3.3" tags={["SDKs", "Features", "API", "Fixes", "DOCS"]}>
  ### Features

  **Embedding v2** is a new, flexible, and more powerful embedding model.

  * params: `speaker_fingerprint` a boolean value to switch on/off speaker identification.
  * response: `speaker_embeddings` a list of embeddings for the speaker.

  ### Fixes

  * fixed **Speech to Text (STT)** webhook
  * fixed **file upload** overwrites error

  ### API

  * added **embedding v2** API

  ### SDKs

  * additional type safety for all APIs
  * added **embedding v2**
  * added **deep research**
  * removed **Text to Speech (TTS)** from SDKs
  * brought back **prompt engine**

  ### DOCS

  * changelog introduction
  * examples for all SDKs supported
  * [Vercel Integration](/docs/integration/vercel) and Marketplace
  * [Handling Files](/docs/api-reference/handling-files) documentation
</Update>