AI Agent StoreFireworks · Renamed routing service verified
Nexus Auto
Let Fireworks choose a model for each turn of coding work. If you need one fixed model, check whether your plan supports pinning it.
First reviewed 2026-10-23 · Checked 2026-11-03. A provider launch date and public per-token prices are not verified.
We still need comparable independent tests. You can compare the confirmed features and limits below, but we cannot yet give this version an Agent Fit or Practical Value rating. Test it on your own tasks before switching; results for another version or thinking setting may not apply.
What you can use today
Token prices measure the small pieces of text the model reads or produces. Capacity is the amount the service accepts in a request; check the limits below for any fallback to another model. A dash means the rate is unverified.
Exact provider API ID: auto. Replaces FireRouter. Open models bill to Fireworks; Anthropic and OpenAI turns use your connected credentials. The response model field identifies what answered. Without a closed-provider credential, that provider is left out of automatic selection.
With a Fireworks key alone, auto uses open models. Connected Anthropic/OpenAI credentials add those providers. The current guide limits pinning a specific model to Enterprise; confirm your plan before relying on fixed selection.
Limits and reasoning behavior depend on the serving model; a common exact maximum is not verified.
No single token price or guaranteed saving. Compare the total bill for completed tasks, including retries and the model selected for each turn. Allow for retries and any tool fees. Models that think before answering may also charge for that work.
Provider release and specifications ↗
Check availability and plans ↗
Test it before switching
Give each model the same examples, tools and definition of success. Record correct outcomes, response time, retries and total cost. A cheaper token price does not guarantee a cheaper completed task.
Compare caching and long-context costs ↗