[bbg2401]

I'm banned from using the free options. At some point they flagged my account as having engaged in model training against their ToS. This despite my account using around £15 worth of tokens over several months, nearly entirely through BYOK providers.

The handful of times I did try a free model is when I used their chat interface to quickly compare a few open weight models with a single prompt. That's the only usage I can think which could have triggered the block on my account. Even still, what's the point in have the simultaneous chat feature if using it veers so quickly into a ToS violation.

Their support is beyond useless in helping understand the situation. I don't think I managed to speak to anyone other than Tony Bot (or whatever it was named).

Edit:

Total usage over 1 year:

Claude Sonnet 4.6 $8.80

Gemini 3.1 Pro Preview $6.71

Claude Opus 4 $6.19

Claude Opus 4.1 $7.49

Gemini 2.5 Pro $10.06

Claude Sonnet 4.5 $12.74

GPT-5 Codex $2.56

Grok 4 $4.39

Gemini 2.5 Flash Image Preview (Nano Banana) $1.88

GPT-5 $7.30

Others $7.99

[mmarian]

Since you're BYOK, have you tried self-hosting LiteLLM? It's what I use for the BYOK option on my service.

[bbg2401]

Good shout, that's what I use.

My usage of OpenRouter was limited to casual throwaway experiments with coding agents and quick, surface-level exploration of new and unfamiliar models in the chat interface.

My comment is just an expression of a festering grudge over the unannounced, unexplained sanction on my account and the lack of transparency and feedback from the non-existent support team. There's no OpenRouter shaped hole in my personal workflow, fortunately.

[drak0n1c]

If you want to avoid bans, Venice is another good option since their focus is uncensored and privacy. They run models themselves alongside offering OpenRouter-style routing for frontier and niche models - but at least they fully anonymize the user and never ban.