IBM: Granite 4.1 8B is a chat model built by Ibm-Granite. It accepts up to 131K tokens of context per request. Routed through external models — ~100 tokens per message (50% markup over upstream cost).

IBM: Granite 4.1 8B works well for general conversation, writing assistance, brainstorming, code help, and analysis. Try the sample prompts above to see its style.

About 100 tokens per average message. $1 buys 750,000 tokens, so even paid models cost cents per chat. Free accounts get 10,000 signup tokens plus a daily pool.

It depends on the task. /chat/compare/ lets you send the same prompt to IBM: Granite 4.1 8B and any other model side-by-side — comparison is the fastest way to decide.

Yes. Outputs are yours — Free.ai does not claim rights to anything you generate.

131,072 tokens.

Replies stream token-by-token within ~1 second. Total response time depends on length and model size — small models stream faster, frontier models trade speed for depth.

Yes. Signed-in users see every chat in /account/?tab=history. You can also share a one-link copy of any conversation via the Share button.

Free.ai does not train models on your conversations. Self-hosted models stay on our GPUs. Premium models route to the upstream provider for inference.

Yes. POST to /v1/chat/ with model="ibm-granite/granite-4.1-8b" and a messages array. Streaming SSE is supported. Full reference: /api/.

IBM: Granite 4.1 8B is a premium model served by an external provider, so self-hosting is not available. Free.ai exposes it through token-based pricing.

Free accounts get 10,000 signup tokens plus a daily pool. When that runs out, top up starting at $1 (750K tokens) — no subscription required.