AI model gateway

Choose the right model.
Use FreeModel.online

Free models first. Automatic failover. No per-provider signup.

FreeModel is an AI model gateway that gives you a single API key for dozens of model providers, routes each task to the best available model, tries free models first, and falls back automatically when a provider fails or runs out of quota.

477 models callable today
6 modalities
2 API formats
$0 to start
One request entering FreeModel and fanning out to many model providers
One node highlighted among many

Free models are tried first

Among the models that fit the task, ones with remaining free quota go first.

How routing works →
A broken path with a second path continuing around it

A dead provider is not your outage

A rate limit or an exhausted quota moves the request to the next candidate.

Failover detail →
A single key with lines radiating to many nodes

One key, one address, one bill

Five providers no longer means five accounts and five billing pages.

Set it up →

Models

Browse all 477 →
auto/best-codingcombination route auto/best-reasoningcombination route Text & codelargest group Image & videofor generation and vision Embeddingsfor search and RAG

The live list is public and needs no key: GET /v1/models · which ones are free →

Pricing

Full price table →
Bring your own keys Free You pay your providers directly. FreeModel adds nothing.
Platform key Pay per call Buy points, spend them at the listed per-model price. Free quota costs nothing.

Quickstart

All setup guides →
# Anthropic-compatible clients: Claude Code, and others
export ANTHROPIC_BASE_URL="https://freemodel.online/api/gateway"
export ANTHROPIC_API_KEY="sk-your-key"

# OpenAI-compatible clients: Codex CLI, Cursor, Cline, SDKs
export OPENAI_BASE_URL="https://freemodel.online/v1"

Aiglade

What it is →

A desktop app that runs several AI agents at once on Windows, with no setup. It ships pointing at FreeModel, so you never register with a provider or paste a key.

Windows Desktop installer Windows 10 or later Download ↓ Android Mobile app Drives the same task queue over your local network Download ↓

Both are free. No account needed to install.

Questions

All questions →
Is FreeModel actually free?
Some models carry a free quota and routing prefers them. When no free model fits the task, the request goes to a paid one at the listed price.
Do I have to hand over my provider keys?
No. Use the platform key, or bring your own for the providers you already pay.
What happens when a provider goes down?
The request moves to the next candidate, and the routing log records which one served it.
Can I see the models without signing up?
Yes. /v1/models is public and needs no key.

Why a gateway is worth one extra hop

The full sequence →

A direct connection to one provider is the shortest path, and it is also the most fragile one. Everything that can change on the provider's side — a quota running out, a key being rotated, a model being retired, a price moving — arrives in your application as a failure, and each of those failures has a different cause and a different fix. A gateway exists to absorb that class of event before your code sees it, and to record what happened, so the next occurrence is a lookup rather than an investigation.

FreeModel adds exactly one hop and takes those events out of your error path. Of the 477 listed models, 66% accept text or multimodal input and 34% generate images, so a text workload is comparing inside the larger half of the catalogue. Among the 317 text models, 95% have tool calling enabled and 73% support reasoning, which is why an agent can be pointed at almost any of them without checking capabilities first; 29% accept image input, so a request carrying a screenshot narrows the pool without emptying it. The router filters that pool to what the request actually needs, spends free quota wherever any remains, and moves on when a provider refuses.

What you give up is knowing which model answered. A route name is a statement of intent, not a model id, and only 8% of the listed models are combination routes — the 38 entries that take this trade explicitly. If you need to reproduce a result exactly, or to name a model for compliance reasons, send a specific id instead and let the gateway do nothing but forward it.

Four steps from nothing to a first request

  1. Step 1 — Get a key. Open the console and create one. No provider account and no payment method is needed to start.
  2. Step 2 — Point a client at the gateway. For an Anthropic-shaped client, set ANTHROPIC_BASE_URL to https://freemodel.online/api/gateway and ANTHROPIC_API_KEY to your key. For an OpenAI-shaped client, set OPENAI_BASE_URL to https://freemodel.online/v1.
  3. Step 3 — Send a route name instead of a model id. auto/best-coding for code, auto/best-reasoning for reasoning, auto/best-free when the request must not cost anything.
  4. Step 4 — Read the routing log in the console. It names the provider that actually served the call and lists the candidates that were skipped, with a reason for each.

FreeModel FAQ

All questions →
Why not call the provider directly?
For a single provider you already trust, that is the simpler setup and FreeModel adds nothing to it. A gateway earns its hop when more than one model is in play: the capability filter, the free-quota preference, the failover path and the routing log all live inside that hop, and none of them is something you have to build or maintain.
Does the gateway change my code?
No. Clients keep speaking the OpenAI or Anthropic request shape. You change where the client points — ANTHROPIC_BASE_URL or OPENAI_BASE_URL — and which model name you send. Everything above that line stays as it was, and switching back is the same edit in reverse.
What does a route name actually guarantee?
It guarantees what the router optimises for, not which model answers. auto/best-coding picks the best available model for code this minute, and may pick a different one next month. When you need the identical model every time, send a specific id and the router gets out of the way.
What happens if every candidate fails?
The request returns an error rather than looping quietly, and the routing log lists each candidate that was tried together with the reason it was skipped. In practice the fallback list is long enough that reaching its end usually means the request itself was malformed, not that the market was down.