Google Gemini

Nano Banana 2.1 (gemini-nano-banana-2.1), GA on October 6, 2026, is Google's newest and recommended default image model, updating Nano Banana 2 with better text rendering and character consistency, 1K to 4K output and up to 14 reference images.

Google's current Flash model, GA since September 2026, aimed at long-horizon software engineering and autonomous agents. Reads text, image, video, audio and PDF in a 1M-token context, with 64K output and low, medium or high thinking.

Google's dedicated speech-to-text model, launched August 2026 and improving on Chirp 3, with auto-detection of 85+ languages, word-level timestamps, speaker diarization and custom vocabulary. Takes up to an hour of audio per request; a live variant streams.

Flash model released in August 2026, three weeks after 3.6 Flash, with coding and web-development gains and a March 2026 knowledge cutoff. Deprecated in October 2026; requests now route to its successor, Gemini 3.8 Flash.

Embodied-reasoning model for robots, built on Gemini 3.5 Flash and in public preview since July 2026, replacing Robotics-ER 1.6. Handles spatial reasoning, task-progress tracking from video, tool orchestration and multi-robot coordination over a 128K context.

Google's current Flash-Lite model, GA since July 2026 and the fastest, cheapest member of the 3.5 series, aimed at high-volume extraction and sub-agent work. Takes text, image, video, audio and PDF input across a 1M-token context.

Flash model released in July 2026 as the successor to 3.5 Flash, which now routes to it, with Google citing fewer output tokens per task. Still stable, though Gemini 3.7 and 3.8 Flash have since followed.

Nano Banana 2 Lite (gemini-3.1-flash-lite-image), GA since June 30, 2026, is the fastest and cheapest Gemini image model, targeting sub-2-second latency at 1K resolution only. Google names it the migration path for the original Nano Banana.

Gemini 3.5 Live Translate is a June 2026 Live API preview for continuous speech-to-speech translation across 70+ languages, detecting the source language and keeping the speaker's intonation, pacing and pitch. It remains Google's dedicated live-translation model, with no shutdown announced.

Nano Banana Pro (gemini-3-pro-image), Google's Pro-tier image model, GA since May 2026 after a November 2025 preview. Built for complex layouts with accurate text, Search grounding and up to 4K output; Nano Banana 2.1 is the newer default.

Nano Banana 2 (gemini-3.1-flash-image), the Flash-tier image model previewed in February 2026 and GA in May, outputs 512px to 4K and accepts video as context. Deprecated October 6, 2026 for Nano Banana 2.1, with no shutdown date set.

Verbatim transcription by prompting Gemini 3.5 Flash, the May 2026 Flash model. Google deprecated it on 8 October 2026 and routes its requests to Gemini 3.6 Flash, so transcripts now come from that successor.

Opened the Gemini 3.5 series at Google I/O in May 2026 as a GA Flash model for agents and coding. Deprecated on 8 October 2026; calls to gemini-3.5-flash are now routed to Gemini 3.6 Flash.

Low-cost transcription that prompts Gemini 3.1 Flash-Lite, Google's GA lightweight multimodal model from May 2026, to return verbatim text from audio. Gemini 3.5 Flash-Lite has since taken over the Flash-Lite tier.

Cost-focused Flash-Lite model, GA since May 2026 after a March preview, built for high-frequency lightweight tasks over 1M tokens of multimodal input. Superseded by Gemini 3.5 Flash-Lite; Google lists May 2027 as its earliest shutdown.

Google's first multimodal embedding model, GA in April 2026 after a March preview, mapping text, images, video, audio and PDFs into one vector space. 8,192-token input and 128 to 3,072 dimensions; incompatible with gemini-embedding-001 vectors.

Gemini 3.1 Flash TTS (gemini-3.1-flash-tts-preview), an April 2026 preview, steers delivery with inline audio tags in 70+ languages, handles two speakers and streams. Google now calls it legacy, replaced by Gemini 3.8 Flash-Lite TTS, with shutdown on November 17, 2026.

Veo 3.1 Lite (veo-3.1-lite-generate-preview), launched March 31, 2026, is the lowest-cost Veo tier, generating video with native audio at 720p or 1080p but without 4K or extension. Gemini Omni Flash replaces it on October 22, 2026.

Gemini 3.1 Flash Live, a March 2026 Live API preview for real-time audio-to-audio conversation with thinking, Search grounding and function calling. Legacy since Gemini 3.8 Live reached GA in September 2026; shutdown is set for November 17, 2026.

Transcribes audio by prompting Gemini 3.1 Pro Preview, Google's February 2026 Pro-tier reasoning model, which reads audio natively alongside text, images and video. Still a preview; Gemini 4 Argon now heads Google's lineup.