New model: Gemini 3.8 Flash (Google)

Google released Gemini 3.8 Flash on 2026-09-02, a multimodal model supporting text, image, video, audio, and PDF inputs with a 1049k context window and 66k maximum output tokens. The model is available via Google Vertex AI and is listed on models.dev, with no retirement date announced.

GG● Healthy Gemini 3.8 Flash Google · gemini-3.8-flash Released2026-09-02 Retiresno announced date gemini-flashtext+image+video+audio+pdf1049k context66k max out also matches: gemini-3.8-flash google/gemini-3.8-flash provider announcement → https://models.dev/google-vertex/gemini-3.8-flash Does your code call Gemini 3.8 Flash? $ curl -fsSL https://llmstatus.ai/install.sh | bash Then mm status in any repo — it finds every model you use and flags the ones on a clock. No account, nothing uploaded. Get alerted before it retires → /sign-up