Skip to main content
FireRouter is a managed routing service for any LLM workload. Request a FireRouter model through the Fireworks inference API, and FireRouter scores each turn to select a model from the configured set. By default, it routes between a Fireworks open model and a closed-source model. The result is lower cost on simpler requests without giving up closed-source quality on harder ones.
FireRouter is in research preview. APIs, routing behavior, and the models in the routing pair may change. This documentation is updated to reflect the current configuration.

​
When to use FireRouter

Use FireRouter when you want automatic cost optimization without picking a different model per request:
  • You want closed-source quality (for example Claude Opus) on hard prompts but do not need it on every call.
  • Many of your requests are straightforward (summaries, formatting, simple Q&A) and can be served by a Fireworks open model.
  • You want to select the models available to the router without choosing a target for every request.
  • For the default configuration, you are able to send both a Fireworks API key and a provider API key on each request.

​
How it works

FireRouter evaluates each new user request. The default firerouter configuration picks one of two paths: FireRouter uses a bring-your-own-key (BYOK) model:
  • Your Fireworks API key authenticates to FireRouter and pays for calls to Fireworks models.
  • A third-party provider API key pays for calls to that provider’s models.
FireRouter never stores your provider keys server-side. You send them on each request.

​
FireConnect

The easiest way to use FireRouter in coding harnesses is FireConnect. As of FireConnect v0.9.0, select FireRouter like any other model:
See FireConnect Models for how firerouter fits next to other short IDs, and Harness support for which harnesses support FireRouter. Per-harness details (Claude slot flags, Codex Anthropic env, routing preference) live on each harness page. Upgrade FireConnect before enabling FireRouter on an older install. See Upgrade FireConnect. Pass --anthropic-api-key sk-ant-... on on, or store a key once with fireconnect configure --anthropic-api-key sk-ant-.... The default firerouter requires an Anthropic key because Claude Opus 5 is its primary model; FireRouter fails closed instead of silently restricting the route to GLM. See Authentication. Cursor and Deep Agents need workspace BYOK for FireRouter (no local Anthropic key).

​
Endpoint

FireRouter is available through the Fireworks inference API:
Common API paths:

​
Model ID

FireRouter is a first-party model on the Fireworks provider. Use firerouter in the model field:
These longer forms are also accepted:
For LiteLLM, use the full router path in litellm_params.model. FireRouter decides the target model for each request based on request complexity. The model ID selects the set of models FireRouter can route to.

​
Current routing pair

The short firerouter model ID currently routes between: These models are subject to change as FireRouter is updated. This page reflects the current configuration. Because the default pass-through target is Claude Opus 5, supply an Anthropic API key to use that path. See Authentication.

​
Choose different models

Use a slash-delimited FireRouter slug to change the models available to the router. The first model is the primary; the remaining models are alternatives that FireRouter ranks for each request. Each member must be an exact deployed model ID or a unique model alias, and a slug can contain up to eight distinct models. Examples: Set the selected slug in the model field just as you would use firerouter. FireRouter still chooses the target for each request. The primary model’s credential is required. A later model is eligible only when its credential is present. Use x-anthropic-api-key for Claude models and x-openai-api-key for OpenAI models. See Authentication.

​
Client integrations

​
What FireRouter is not

  • Not a deployment router. FireRouter is different from deployment routers, which load-balance traffic across your own Fireworks deployments.

​
Next steps

FireConnect

Enable FireRouter with one command

Quickstart

Make your first API call

Claude Code (manual)

Edit settings.json for FireRouter in Claude Code

Authentication

BYOK headers and API key requirements

Routing preferences

Tune the quality vs. savings dial

LiteLLM

Add FireRouter to LiteLLM Proxy