Which URL and key do I put in my app?

Use the base URL https://api.freetheai.org/v1 and an API key from Dashboard > API keys. Apps that ask for the full URL, like JanitorAI, need https://api.freetheai.org/v1/chat/completions. Copy model IDs exactly as they appear on the Models page. Step-by-step guides for 24 apps are at freetheai.org/setup.

Which model should I use for roleplay?

On the Models page, pick Roleplay under Good for. It lists the models that suit roleplay, ranked by what roleplay apps use most. The dog/ and lion/ models are for general questions and writing, not roleplay.

Why are my replies cut off, or why does my app say "No response"?

Raise your app's max tokens (response length), or set it to 0 to use the model's full output length, and turn on streaming. Some models think before they answer, so long chats can take a while; if your app gives up waiting, retry or pick a faster model.

Which email can I sign up with?

Use an address from a major provider such as Gmail, Yahoo, or Outlook. Some privacy-focused and temporary email services are not accepted. Verify your email from the link we send before using the API.

How do I turn the model's thinking off?

On Dashboard > API keys, open scope & settings under your key, turn on "Turn thinking off", and save. Models that think first then answer straight away, with nothing to change in your app. If you see a second "thinking" part inside the reply text, your app's preset is asking the model to write its thoughts; turn that option off in the preset.

The models you want. The price you choose.

One API key for 146 models from many providers. Compare prices and pay per token from one wallet.

Get started Browse 146 models

curl https://api.freetheai.org/v1/chat/completions \

-H "Authorization: Bearer $FREETHEAI_API_KEY" \

-H "Content-Type: application/json" \

-d '{

"model": "glm-5.3",

"stream": true,

"messages": [

{ "role": "user", "content": "Hi" }

]

}'

200 OKstreamingglm-5.3

"Hi! What should we build today?"

146Models

475Requests yesterday

5,420Active users, last 30 days

147Countries

Deposit crypto

Fund your FreeTheAI wallet with crypto. One balance pays for every model on the marketplace.

Call any model

OpenAI, Anthropic, Google, and more through one API. Access comes from independent sellers, not the original companies.

Choose the right route

Select cheapest or fastest routing. Each request uses one reviewed route with server-owned pricing and access checks.

Works with the app you already use

Paste one address and your key. Every guide was tested in the app itself.

Roleplay apps
5 guides
Every click, step by step, in the JanitorAI guide
Works in
JanitorAI, SillyTavern, Chub AI, RisuAI, Tavo
Open the guides
Chat apps
9 guides
Every click, step by step, in the Open WebUI guide
Works in
Open WebUI, LibreChat, LobeHub (LobeChat), Chatbox, Cherry Studio, NextChat, TypingMind, AnythingLLM, Page Assist
Open the guides
Coding tools
10 guides
Every click, step by step, in the Claude Code guide
Works in
Claude Code, Codex CLI, OpenCode, Kilo Code, Cline, Continue, Aider, Zed, VS Code Copilot Chat, Hermes Agent
Open the guides

Models you can call right now

185 models through one key. Prices are per million tokens.

Browse all models

Pay only for what you use

Add funds once and each request bills the tokens it used at the price listed for it. No subscription.

Three formats, one API

OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages use one account and one server-controlled marketplace.

One wallet, fair billing
Sellers list per-call or per-token pricing. Every transaction is crypto, settled from your balance.
Priced by the market
Approved independent providers offer reviewed capacity at different prices and service levels. FreeTheAI owns the catalog, routing, billing, and support.
Server-owned route selection
Choose the cheapest or fastest reviewed route for each request. Authorization, pricing, and billing are checked before dispatch.
Sellers earn in crypto
Offer approved independent capacity, set per-call or per-token pricing, and receive manual crypto payouts after completed usage.

Frequently asked questions

See all questions

Use the base URL https://api.freetheai.org/v1 and an API key from Dashboard > API keys.
Apps that ask for the full URL, like JanitorAI, need https://api.freetheai.org/v1/chat/completions.
Copy model IDs exactly as they appear on the Models page.
Step-by-step guides for 24 apps are at freetheai.org/setup.

On the Models page, pick Roleplay under Good for.
It lists the models that suit roleplay, ranked by what roleplay apps use most.
The dog/ and lion/ models are for general questions and writing, not roleplay.

Raise your app's max tokens (response length), or set it to 0 to use the model's full output length, and turn on streaming.
Some models think before they answer, so long chats can take a while; if your app gives up waiting, retry or pick a faster model.

Use an address from a major provider such as Gmail, Yahoo, or Outlook.
Some privacy-focused and temporary email services are not accepted.
Verify your email from the link we send before using the API.

On Dashboard > API keys, open scope & settings under your key, turn on "Turn thinking off", and save.
Models that think first then answer straight away, with nothing to change in your app.
If you see a second "thinking" part inside the reply text, your app's preset is asking the model to write its thoughts; turn that option off in the preset.

The models you want. The price you choose.

How it works

Deposit crypto

Call any model

Choose the right route

Works with the app you already use

Roleplay apps

Chat apps

Coding tools

Models you can call right now

The providers you already know

Listed on

Why FreeTheAI

Pay only for what you use

Three formats, one API

One wallet, fair billing

Priced by the market

Server-owned route selection

Sellers earn in crypto

Frequently asked questions