Model type · Fast, low-latency

Fast free LLM API

Free models for quick, low-stakes calls: titles, labels, one-liners. Latency-first routing with a short timeout so failover starts fast.

Call it with one model id

Point any OpenAI-compatible client at your local Ficelle endpoint and ask for ficelle/auto-fast. Quick, low-stakes calls: titles, summaries, one-liners.

python

from openai import OpenAI

client = OpenAI(base_url="http://127.0.0.1:8646/v1", api_key="ficelle-local")

reply = client.chat.completions.create(
    model="ficelle/auto-fast",
    messages=[{"role": "user", "content": "..."}],
)

What a model needs to be routed here

Free pricing: a model with any price is never eligible, and paid fallback is hardcoded off.
Tool calling support.
At least 64,000 tokens of context by default.
Structured output support.

Good for

Ticket and intent classification
Conversation titles and short summaries
Routing decisions inside an agent graph

Measured, not promised

100% quality-safe vs gpt-5 on classification and triage, in Ficelle's 76-task benchmark. Long-form polished writing is the honest exception, where the paid model still wins. Read the method and raw numbers.

Worth knowing

The only profile whose promise is latency: a silent provider is cut off after a short inactivity budget instead of the global one, so the next model gets its turn sooner.
Read-inactivity budget for this profile: 30 seconds before Ficelle gives up on a silent provider and fails over.

Where the models come from

The pool is built from the free models of the providers you configure. The open core ships OpenRouter and Nous; Pro maintains the broader provider pack. Whether a given provider has a model eligible for this type changes as catalogs change, so Ficelle decides at routing time, not this page.

Questions

Is ficelle/auto-fast free?

Yes. The profile only routes to models with free pricing, and paid fallback is hardcoded off, so a routed request cannot incur a paid-model charge. You bring your own provider keys; the open core is free, and Pro adds a maintained provider pool.

What happens when the model behind ficelle/auto-fast fails?

Ficelle marks it as cooling down or quarantined depending on the failure, tries the next eligible free model in the same pool, and probes the failed one until it recovers. Your client keeps calling the same id.

Which clients can call ficelle/auto-fast?

Anything that speaks the OpenAI API: the OpenAI SDKs, Cursor, Codex, Continue, Open WebUI, LangChain, CrewAI or plain curl, pointed at http://127.0.0.1:8646/v1. Claude Code connects through Ficelle's native Anthropic Messages endpoint. Hermes and OpenClaw use packaged connectors.