Ziva Baby

Select Ziva Baby in the model picker for hosted chat with no customer charge. Hosted access still follows your account’s subscription and trial rules. Where Hobby hosted allowances are available, Baby has a daily message limit shown in your account; paid plans have no Baby daily message cap. Tool calls and automatic compaction within a turn do not spend another daily message. The daily reset is at midnight UTC.

Choosing a model

Baby usually selects Nemotron 3.5 Lightning Free. It can also select GPT-6 Luna or Reflection Beam Free. Cat Jam is another name for Beam. A turn keeps the same model, including its tool calls and retries. Baby may choose a different model when you start a new turn, even in an existing chat.

Update the plugin and restart Godot if the picker shows outdated capabilities. Select a concrete model if you need to choose its supported settings.

Images and limits

Supported images are analyzed separately and the resulting description is supplied to Baby. Baby’s chat model does not receive those image pixels. Selecting a model directly uses that model’s own capabilities.

If a conversation is too large, compact it or start a new chat. Shorten a single oversized message before trying again. Manual compaction counts as a new turn; automatic compaction does not.

Feedback and measurements

Use the thumbs under a reply to give feedback, change your vote or remove it. Copies of a reply in forks share the same vote; newly generated replies have their own votes.

The thumbs are disabled while Loading saved feedback. If you see Feedback unavailable, check your connection, sign in to the account that gave the feedback, and reopen the chat. This message does not mean your vote was cleared. Feedback does not change your plan, charges or message allowance.

Votes are linked to your account and the original reply. Saving feedback sends the vote, reply identifiers and usage summaries, not the reply text. Loading saved feedback sends reply and model identifiers with available original-turn attribution, not the conversation or reply text. The normal chat request still follows the provider policies below.

Privacy

Baby can use different providers with different data policies. Do not assume Baby is zero-data-retention or that prompts are excluded from training. Nemotron’s free provider may retain prompts and responses for model improvement. NVIDIA’s published access terms restrict confidential information unless an applicable agreement permits it. Reflection’s free route does not advertise zero retention or an unconditional no-training guarantee. Reflection’s policy says content is not used for general model training by default, but allows flagged content and safety signals to be retained and used for safety training and evaluation. Ordinary content can be retained for up to 30 days; flagged content can be kept longer. Luna’s route has different protections, but those do not apply to all Baby chats. Avoid confidential material unless the applicable provider terms permit your use.

Provider references:

Errors

Baby does not silently substitute a paid model when a request fails. Follow the displayed error and update or restart the plugin when asked. For an image an older plugin cannot analyze, select a model that supports images.

If an error persists, report it with the correlation ID and what you were doing. Do not include private project content in a public report.