WEB SEARCH

Built‑in Web Search for Every Model

Backboard gives you fast, production‑ready web search that works with any model you call through our API. No separate search provider, no tool‑calling support required, and no extra charge.

WEB SEARCH

Built‑in Web Search for Every Model

Backboard gives you fast, production‑ready web search that works with any model you call through our API. No separate search provider, no tool‑calling support required, and no extra charge.

WEB SEARCH

Why engineers use Backboard web search

From zero-infra search to adaptive context budgeting — all built into one stateful API call.

WEB SEARCH

Why engineers use Backboard web search

From zero-infra search to adaptive context budgeting — all built into one stateful API call.

WEB SEARCH

Why engineers use Backboard web search

From zero-infra search to adaptive context budgeting — all built into one stateful API call.

Does web search work with every model in the catalog?

Yes. Web search is implemented at the Backboard platform level, not as a tool call, so it works with any of the 17,000+ models you route through our API — including models that don't support function calling or tool schemas.

Is there a per-query cost for web search?

No. Web search is included in the Backboard platform at no additional charge. You pay for model usage and memory operations — not for search queries.

How does Backboard handle web results inside a limited context window?

Adaptive Context Management automatically budgets your context window. Web results are ranked by relevance and fit alongside your state, memory, RAG results, and system prompt — without overflowing the model's limit.

Do I need to wire a separate search provider?

No. You don't need to choose, integrate, or manage a third-party search API. Just set the web_search flag in your existing Backboard call and the platform handles querying, result selection, and formatting.

Can I combine web search with RAG and memory in the same call?

Yes. All Backboard features — routing, memory, RAG, web search, state management, and Adaptive Context — are available in a single API call. Backboard orchestrates them together and manages the context budget automatically.

What kinds of queries benefit most from web search?

Time-sensitive queries are the biggest win: recent model releases, benchmark results, news, pricing changes, and documentation updates that fall outside a model's training cutoff. It also helps with fact-checking model outputs against current public information.

Web search without extra infra

What is Backboard web search?

Backboard web search lets your apps pull in fresh, high‑quality information from the internet on demand. Instead of wiring a separate search API and teaching each model how to call it, you:

Web search without extra infra

What is Backboard web search?

Backboard web search lets your apps pull in fresh, high‑quality information from the internet on demand. Instead of wiring a separate search API and teaching each model how to call it, you:

Turn web search on with a simple flag

Add web_search: true to any existing Backboard message call. No new client, no separate endpoint, no configuration required — one flag and you're live.

Let Backboard handle querying, result ranking, and formatting

Backboard queries the web, selects the most relevant results, and formats them into context automatically. You never touch the search provider or parse raw results.

Feed the results into any model, even if it does not support tool calling

Web search is implemented at the platform level, not as a tool call. It works with all 17,000+ models — including those that don't support function calling or tool schemas.

HOW IT WORKS

How Backboard web search works

You enable web search as part of the same msg call you already use:

1. Your app sends a user message

Your app sends a message to Backboard with web_search: true set. Backboard loads any active session state, memory, and RAG context as usual.

1. Your app sends a user message

Your app sends a message to Backboard with web_search: true set. Backboard loads any active session state, memory, and RAG context as usual.

2. You set web_search: true in the tools/options

Backboard identifies the search intent in the message, queries the web, scores and selects the top relevant snippets, and formats them for injection.

2. You set web_search: true in the tools/options

Backboard identifies the search intent in the message, queries the web, scores and selects the top relevant snippets, and formats them for injection.

3. Backboard runs a web search, selects relevant snippets, and injects them into the model context

Web results are injected into the model context alongside your system prompt, session state, memory, and RAG results. No manual formatting required.

3. Backboard runs a web search, selects relevant snippets, and injects them into the model context

Web results are injected into the model context alongside your system prompt, session state, memory, and RAG results. No manual formatting required.

4. Adaptive Context Management fits web results alongside state, memory, and RAG

Adaptive Context Management automatically trims and prioritizes all sources — state, memory, RAG, and web — to fit within the target model's token window before forwarding the request.

4. Adaptive Context Management fits web results alongside state, memory, and RAG

Adaptive Context Management automatically trims and prioritizes all sources — state, memory, RAG, and web — to fit within the target model's token window before forwarding the request.

USE CASES

Web search patterns you can implement

Common patterns teams build once they have live web results available on every model call.

News‑aware assistants

Agents and assistants that answer questions about current events, market moves, or recent releases — grounded in live web results, not training data.

Hybrid knowledge bots

Combine RAG over internal docs with live web search for external coverage. One call returns answers grounded in both your proprietary content and the open web.

Research workflows

Multi-step agents that pull fresh source material on demand — benchmark data, pricing, papers, documentation — without leaving the Backboard API.

Safety and validation

Use web search to fact-check model-generated outputs against current public information before returning them to users. Reduce hallucination risk at the source.

COMPARISON

Why not just bolt on a search API?

Doing it yourself means choosing infra, stitching systems, and managing context budgets manually. Backboard handles all of it.

Doing it yourself usually means:

Choosing and integrating a third‑party search provider

Designing result formatting for each model

Handling rate limits, errors, and different relevance formats

Backboard gives you:

Web search integrated into the same unified, stateful API

Free usage as part of the platform — no per‑query fees or separate search bill.

Automatic context budgeting alongside routing, memory, and RAG

You toggle a flag instead of building another subsystem. Backboard fits web results into the context window automatically, alongside everything else.

PLATFORM

Included in Backboard, not a separate product

Web search is a first‑class, free feature of Backboard.

No separate search bill or per‑query line item

Web search is included in the platform. You pay for model usage and memory calls — not search queries.

Works with any model, with or without tool‑calling capabilities

Web search is implemented at the Backboard platform level, so any of the 17,000+ models you route through Backboard can benefit — no function-calling support needed.

Ships alongside routing, memory, RAG, state management, and Adaptive Context

One integration, one platform. All features — routing, memory, RAG, web search, state management, and Adaptive Context Management — are available on every call.

No separate search bill or per‑query line item

Web search is included in the platform. You pay for model usage and memory calls — not search queries.

Works with any model, with or without tool‑calling capabilities

Web search is implemented at the Backboard platform level, so any of the 17,000+ models you route through Backboard can benefit — no function-calling support needed.

Ships alongside routing, memory, RAG, state management, and Adaptive Context

One integration, one platform. All features — routing, memory, RAG, web search, state management, and Adaptive Context Management — are available on every call.

Give every model live access to the web

Wire Backboard once and add reliable web search to your entire AI stack, at no extra cost.

Give every model live access to the web

Wire Backboard once and add reliable web search to your entire AI stack, at no extra cost.

Give every model live access to the web

Wire Backboard once and add reliable web search to your entire AI stack, at no extra cost.