Verified stable model ID: gemini-3.8-live. Official documentation lists an input token limit of 131,072 and output token limit of 65,536. Those are separate limits; a combined context total is not asserted. Inputs include text, images and audio. In Live session configuration, AUDIO is the supported response modality; enable output_audio_transcription for a text transcript. Supports interleaved reasoning and function calling, but not configurable thinking_level. Free tier is subject to limits. Paid rates per million tokens: input $0.75 text, $3 audio, $1 image/video; output $4.50 text, $12 audio. Tool charges can apply. Sources: https://ai.google.dev/gemini-api/docs/models/gemini-3.8-live; https://ai.google.dev/gemini-api/docs/pricing#gemini-3.8-live. Checked November 6, 2026.
Loading the catalog…