Model type · Coding assistants

Free coding LLM API

Free models for coding assistants, restricted to a certified coding pool. Fails loudly instead of silently swapping in an uncertified model.

Call it with one model id

Point any OpenAI-compatible client at your local Ficelle endpoint and ask for ficelle/auto-coding. Coding assistants: Claude Code, Codex, Continue, Cursor and scripts. Claude Code's Sonnet tier maps here by default.

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-coding",
    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.
Only models in the release's bundled, certified coding pool.
Only provider deployments that pass local availability checks.

Good for

Codex CLI and Continue sessions
Cursor with a custom OpenAI base URL
Scripted refactors and code review bots

Worth knowing

It may return 503 no_certified_coding_model while other profiles work: Ficelle will not silently substitute a model that is merely tool-capable.
Public leaderboards only decide what Ficelle evaluates next, never whether a model is routed.

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.

Popular free models built for this

Models whose developers build them for this kind of work, and where they are free today. Whether ficelle/auto-coding routes to one on your install is still decided per request.

Qwen3.8 27B

Questions

Is ficelle/auto-coding 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-coding 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-coding?

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.