LLM routing

Route across 17,000+ models through one API

Backboard gives you a single, portable API to 17,000+ LLMs across providers. Bring your own keys from OpenAI, Anthropic, Google Gemini, Cohere, xAI, OpenRouter, and more. Route by cost, speed, quality, or capability—with built‑in state management and adaptive context handling, no token markup, and access to many free models.

LLM routing

Route across 17,000+ models through one API

Backboard gives you a single, portable API to 17,000+ LLMs across providers. Bring your own keys from OpenAI, Anthropic, Google Gemini, Cohere, xAI, OpenRouter, and more. Route by cost, speed, quality, or capability—with built‑in state management and adaptive context handling, no token markup, and access to many free models.

LLM routing, without the glue code

What is LLM routing on Backboard?

Backboard lets you call 17,000+ models from a single endpoint and change which model you use at any time, without rewriting your app. Instead of hard‑coding every provider's SDK and payload quirks, you:

Integrate one unified API

One endpoint for every model. No provider-specific SDKs, no payload quirks, no conditional logic scattered through your codebase.

Integrate one unified API

One endpoint for every model. No provider-specific SDKs, no payload quirks, no conditional logic scattered through your codebase.

Choose models with a simple string or routing rule

Switch from gpt-4o to claude-3-5-sonnet by changing one value. Routing rules let you express logic in config, not code.

Choose models with a simple string or routing rule

Switch from gpt-4o to claude-3-5-sonnet by changing one value. Routing rules let you express logic in config, not code.

Bring your own keys (BYOK) for providers you already use

Use your existing provider keys for OpenAI, Anthropic, Google Gemini, Cohere, xAI, OpenRouter. Backboard doesn't add markup on tokens.

Bring your own keys (BYOK) for providers you already use

Use your existing provider keys for OpenAI, Anthropic, Google Gemini, Cohere, xAI, OpenRouter. Backboard doesn't add markup on tokens.

Let Backboard handle state, context, tools, and memory consistently

State, context, tools, and memory are managed consistently across every model. Models become interchangeable infrastructure; your orchestration stays the same.

Let Backboard handle state, context, tools, and memory consistently

State, context, tools, and memory are managed consistently across every model. Models become interchangeable infrastructure; your orchestration stays the same.

LLM ROUTING

Why engineers route through Backboard

From benchmark-leading memory to BYOK with no token markup — everything built into one stateful API.

One API, 17,000+ models, many free

Call OpenAI, Anthropic, Google Gemini, Cohere, xAI, open‑source models via OpenRouter, and more through a single integration. Tap into many free and low‑cost models for experimentation and background workloads.

BYOK with no token markup

Use your own API keys for OpenAI, Anthropic, Google Gemini, Cohere, xAI, OpenRouter, and others. Backboard does not add a premium on tokens—your model costs are whatever your provider charges.

Stateful by default

Backboard is built around state. You don't resend full history every call; portable state and memory travel with the conversation.

Adaptive context management built in

Switch between models with different context windows and Backboard automatically fits the conversation. It reserves ~20% of context for raw state and key elements and frees the rest via intelligent summarization, prioritizing system prompts, recent turns, tool calls, RAG, and search.

Configurable memory, RAG, and tools on every route

Attach long‑term memory (lite or pro), RAG, and web search to any model through the same endpoint. You keep one orchestration surface; models become pluggable.

how it works

How LLM routing works

You call a single msg‑style endpoint and pass the model (or routing rule), the state or conversation ID, and optional tools: memory, RAG, web search, custom tools.

1. Resolve model

Backboard resolves the model or routing rule, using your keys where applicable.

1. Resolve model

Backboard resolves the model or routing rule, using your keys where applicable.

2. Apply state

State management is applied automatically so you don't resend everything on every call.

2. Apply state

State management is applied automatically so you don't resend everything on every call.

3. Fit context

Adaptive Context Management fits the conversation into the model's context window, prioritizing system prompts, recent turns, tool calls, RAG, and search.

3. Fit context

Adaptive Context Management fits the conversation into the model's context window, prioritizing system prompts, recent turns, tool calls, RAG, and search.

4. Run and return

Backboard runs tools, returns the response plus telemetry. Change the model string, not your architecture or billing setup.

4. Run and return

Backboard runs tools, returns the response plus telemetry. Change the model string, not your architecture or billing setup.

routing patterns

Routing patterns you can implement

Same state, same memory, same tools—different models for different jobs.

Cost‑aware routing

Default to cheaper or free models; escalate tricky queries to stronger models using your own provider keys. Pay more only when it matters.

Cost‑aware routing

Default to cheaper or free models; escalate tricky queries to stronger models using your own provider keys. Pay more only when it matters.

Latency‑sensitive routing

Fast models for UI interactions; larger models for background jobs—with the same state and memory across both.

Latency‑sensitive routing

Fast models for UI interactions; larger models for background jobs—with the same state and memory across both.

Capability‑based routing

Code models for refactors, long‑context models for docs, multimodal models for images. Route by what the model can do.

Capability‑based routing

Code models for refactors, long‑context models for docs, multimodal models for images. Route by what the model can do.

Provider redundancy

Primary provider with automatic failover to another, all using BYOK, no token markup. Never go down because one provider does.

Provider redundancy

Primary provider with automatic failover to another, all using BYOK, no token markup. Never go down because one provider does.

how it works

Why not just build your own router?

Wiring a couple of models is easy. The hard parts are what Backboard solves.

Wiring a couple of models is easy. The hard parts:

Keeping state and memory consistent across models and providers

Handling different context windows without losing important info

Tracking cost, latency, and usage when logic is scattered

Making RAG, web search, and tools behave the same for every model

Managing multiple keys and pricing models without accidentally overpaying

Backboard gives you:

A unified API for 17,000+ models

BYOK support for major providers with no token markup

Access to many free models for experimentation and background work

Free state management and Adaptive Context Management baked in

Best‑in‑class configurable memory (lite and pro), plus RAG and web search

You integrate once and get world‑leading routing everywhere.

PLATFORM

Included in Backboard, not a separate product

LLM routing is part of the core Backboard API. No separate product, no add-on pricing for routing itself.

PLATFORM

Included in Backboard, not a separate product

LLM routing is part of the core Backboard API. No separate product, no add-on pricing for routing itself.

Pay for model usage directly to providers (via BYOK) and for memory calls/tokens on Backboard

Pay for model usage directly to providers (via BYOK) and for memory calls/tokens on Backboard

Get routing, state management, Adaptive Context, RAG, and web search as part of the platform

Get routing, state management, Adaptive Context, RAG, and web search as part of the platform

Start with free and low‑cost models, then scale to premium models without changing your integration

Start with free and low‑cost models, then scale to premium models without changing your integration

Start routing models like infrastructure

Wire Backboard into one service today and unlock 17,000+ models, BYOK, stateful behavior, adaptive context, and many free models across your stack.

Start routing models like infrastructure

Wire Backboard into one service today and unlock 17,000+ models, BYOK, stateful behavior, adaptive context, and many free models across your stack.

Start routing models like infrastructure

Wire Backboard into one service today and unlock 17,000+ models, BYOK, stateful behavior, adaptive context, and many free models across your stack.

We protect your data.

All systems operational

© 2026 Backboard.io

We protect your data.

All systems operational

© 2026 Backboard.io

We protect your data.

All systems operational

© 2026 Backboard.io

We protect your data.

All systems operational

© 2026 Backboard.io