Chub AI alternatives
Chub AI (chub.ai) is a library of character cards with its own chat front end and paid inference. The alternatives split two ways: another place to chat with characters, or keeping your cards and bringing your own model. Both are below, with what MagmaRouter carries for the second.
What Chub AI is
Chub (chub.ai) hosts a large library of character cards and sells its own inference, and many users bring an external API key instead because it is cheaper per message and keeps the model choice in their hands.
Other options people compare with Chub AI
| Option | What it is |
|---|---|
| Janitor AI | Hosted character platform with a large public card library. Has its own free model and also takes an OpenAI-compatible proxy key. |
| SillyTavern | Free, open-source front end you run yourself: character cards, lorebooks, group chats, and a connection to almost any API, including any OpenAI-compatible one. No model of its own. |
| RisuAI | Open-source front end that runs in the browser or as a desktop app, with character cards, lorebooks and its own scripting. Bring your own API key. |
| Agnaistic (Agnai) | Open-source roleplay front end, used at agnai.chat or self-hosted, with multi-character chats and memory books. Connects to the backend you configure. |
| Character.AI | The best-known hosted character app. Its own models, a content filter on every reply, and no way to bring your own key. |
| SpicyChat | Hosted character platform on a freemium structure, with the larger models and longer memory on paid tiers. |
| Backyard AI | Desktop app that runs characters against local models on your own machine. Nothing leaves the device; the model has to fit it. |
Cards from chub.ai download in the standard character card format, so SillyTavern, RisuAI and Agnaistic all import them. Moving front end does not mean losing your characters.
What MagmaRouter carries instead
MagmaRouter sells 6 uncensored models on one OpenAI-compatible endpoint, every one able to call tools. Ordered for this particular job rather than by a single ranking: MiMo V2.6 Flash Xploded leads because it carries the longest window of the set at 1.05M, which is what keeps a long session coherent.
| Model | Context | In | Out | Tools |
|---|---|---|---|---|
| MiMo V2.6 Flash Xploded mimo-v2.6-flash-xploded |
1.05M | $1.00 | $2.00 | Yes |
| DeepSeek V4.1 Flash Xploded deepseek-v4.1-flash-xploded |
1.05M | $0.30 | $1.50 | Yes |
| Qwen3.8 27B Xploded qwen3.8-27b-xploded |
1.05M | $1.50 | $5.00 | Yes |
| GLM 5.3 Flash Xploded glm-5.3-flash-xploded |
1.05M | $0.30 | $1.00 | Yes |
Using Chub AI with MagmaRouter
Chub AI takes an OpenAI-compatible key, so you can keep it and change only the model behind it.
In Chub AI's API settings, pick the OpenAI-compatible option (front ends call it custom, OpenAI-compatible, reverse proxy or proxy) and fill in these values:
| Base URL | https://api.magmarouter.com/v1 |
|---|---|
| Full endpoint, if it asks for one | https://api.magmarouter.com/v1/chat/completions |
| API key | Your MagmaRouter key, sk-mr-... |
| Model | An id from the table above, for example glm-5.3-xploded |
Switching takes one base URL
Anything that speaks the OpenAI chat completions format works unchanged. Point it here, use a MagmaRouter key, and name the model from the table.
curl https://api.magmarouter.com/v1/chat/completions \ -H "Authorization: Bearer sk-mr-..." \ -H "Content-Type: application/json" \ -d '{ "model": "mimo-v2.6-flash-xploded", "messages": [{"role": "user", "content": "Hello"}] }'
FAQ
Is MagmaRouter actually uncensored, or does it just say so?
MagmaRouter does not moderate requests. It prices the call, holds the money against your key cap and passes the request to the model. What comes back is whatever that model does: an uncensored build refuses far less than a frontier model but can still decline, and only an abliterated build has the refusal direction removed outright. Neither tag is a promise that any given answer will arrive.
What does it cost compared with Chub AI?
You pay per token at the rates in the table above, with no subscription. $1.00 in and $2.00 out per million tokens for MiMo V2.6 Flash Xploded.
Can I cap what a key is allowed to spend?
Yes, and the cap is enforced before the request goes upstream rather than reconciled afterwards. The reply cannot physically cost more than the hold placed before it was sent.
Will it work with my existing client?
If the client takes an OpenAI-compatible base URL, yes: point it at https://api.magmarouter.com/v1 with a MagmaRouter key. Claude Code and the Anthropic SDKs use the Anthropic format, which is served too.