Check everything
Bocha Wanxiang is a multi-modal search API launched by Bocha. It provides developers with multi-modal search capabilities such as text and images. It is an application-oriented
Bochawanxiang
Core parameters and statistics
Bocha Wanxiang is a multi-modal search API launched by Bocha. Understand it in one sentence - if Bocha AI search is for users, Bocha Wanxiang is a "search capability interface" purely for developers, and it extends the search from text to multi-modal: text, pictures, etc. can be retrieved. It meets the demand that "AI applications need to retrieve not only text, but also pictures and other content."
| Projects | Public Information |
|---|---|
| Official positioning | Multimodal search API |
| Producer | Bocha |
| Core Competencies | Text/image and other multi-modal retrieval |
| Service objects | Developer AI applications |
| Product form | API |
| Belonging to Ecology | Bocha Search Ecology |
| Support Platform | API |
| Place of Belonging | China |
| Billing form | Billing by API call |
Product Boundary: It is developer infrastructure and does not directly face ordinary users. The value lies in making multi-modal retrieval into a callable interface, allowing applications to have richer search capabilities.
Capability source: Based on Bocha search capabilities, multi-modal retrieval is expanded and opened to the outside world with a standardized API.
User and market recognition
Gradually build user awareness in the field, and product capabilities are used by content creators and teams to improve work efficiency. Some industry users have incorporated it into their daily workflow. It is recommended to refer to the latest official disclosures for specific user scale and industry adoption rate data.
Cost advantage
As an API service, Bocha Wanxiang's cost logic is "pay per call instead of self-built multi-modal retrieval".
C-side/Individual: For developers, not a C-side product; individual developers can apply for trial with a low threshold.
Developer/API: Provided as a multi-modal search API, billed based on the number of calls, eliminating the high cost of building a self-built multi-modal search system.
Enterprise/Scale: The plan and price of high-frequency calls must be subject to the official real-time page and business communication.
Hidden costs: Multimodal retrieval usually consumes more resources than plain text retrieval. The real cost is related to the call frequency and modal complexity; the hidden benefit is the elimination of huge engineering investment in self-built multimodal search. Evaluation should be based on multi-modal call size calculations for real applications.
Main functions
- Multi-modal search: Supports multi-modal search such as text, pictures, etc.
- Search API: Provides application calls with standard interfaces.
- Cross-modal information acquisition: Provide retrieval support for multi-modal applications.
- Ecological connection: Used in conjunction with Bocha AI search and other capabilities.
Hidden linkage: Its value lies in its synergy with the Bocha search ecosystem - Bocha AI search complements "networked text retrieval", and Bocha Wanxiang complements "multi-modal retrieval". The combination of the two allows developers to equip applications with search capabilities from text to multi-modal within the same ecosystem.
Model and version evolution
Continuous iterative updates, the latest version introduces performance optimization and new features. Historical version information can be viewed on the official release page. There is no complete public version evolution timeline yet. It is recommended to pay attention to the official announcement to understand the rhythm of feature updates.
Technical advantages
Mechanism: Expand multi-modal retrieval on Bocha search capabilities, and unify text and image retrieval into a callable standard API.
Effect: Developers can add cross-modal search capabilities to applications without building a complex multi-modal search system, lowering the threshold for building multi-modal applications.
Applicable scenarios: Developers building multi-modal Q&A, content understanding, and image-text retrieval applications can best benefit from the multi-modal search API.
How to use
- Visit open.bochaai.com to register a developer account.
- Apply for a multimodal search API key.
- Call the API in the application to retrieve text/images, etc.
- Use the search results for multi-modal question answering or content processing.
- Monitor call usage and costs.
The service is in pure API form and is oriented to developers.
Product Pricing
The pricing model is subject to the official real-time page. Usually a freemium or subscription system is used, and basic functions can be used for free. Advanced functions or high-frequency use require paid subscriptions, and users are advised to evaluate the optimal solution based on actual usage.
Application scenarios
- Multimodal Q&A: Provides retrieval for graphic and text Q&A.
- Graphic content understanding: Retrieve relevant multi-modal content.
- Multimodal RAG: Cross-modal retrieval augmentation generation.
- Content Application: Application scenarios that require image retrieval.
Applicable people
- Multimodal App Developers: Cross-modal retrieval is required.
- AI Product Team: Build graphic question and answer and content understanding applications.
- Bocha ecological user: Already using Bocha search and need to expand multi-modality.
Not suitable for the boundary: For applications that only require plain text retrieval, it is more lightweight and economical to use the text search API; users who are not developers and do not integrate applications do not belong to its target group.
Summary and Outlook
Bocha Wanxiang extends the search capabilities from text to multi-modal, and opens it in the form of pure API. Together with Bocha AI search, it forms a search infrastructure from text to multi-modal, responding to the needs of multi-modal AI applications for cross-modal retrieval. It is aimed at developers, and its value depends on the quality and coverage of multi-modal retrieval.
Implementation suggestions: Developers building multi-modal applications can first access Bocha Wanxiang with small traffic to verify the accuracy and response performance of multi-modal retrieval, and then evaluate the cost based on the actual call scale; teams that are already using Bocha text search API can expand multi-modal capabilities within the same ecosystem and manage calls and costs in a unified manner.
Related tools: perplexity, you-com
Version evolution of Bocha Wanxiang
As an API service, capabilities iterate with versions and there is no traditional discrete version number.
Main line context
- Capability release period (~2025): Launch multi-modal search Bocha Wanxiang based on the search API.
- Continuous iteration period: Expand supported modalities, improve multi-modal retrieval quality and coverage.
The official unified version number and precise date have not been disclosed, and the text is marked with the status of the collection time.
Version Info
- Bocha Wanxiang (API version) ：The multi-modal search API continues to iterate, and the coverage modalities and retrieval capabilities are updated with the version; the official unified version number has not been disclosed, and the collection time point status is marked here. There is no official precise date yet.
- Posted by Bocha Wanxiang ：BoCha launched multi-modal search capabilities based on the search API to BoCha; there is no official precise date yet.
User Reviews