Model Tracker

Gemini 1.5 Flash-8B

Gemini 1.5 Flash-8B is an AI model made by Google. It is retired. Its context window is 1,048,576 tokens. Its longest answer is 8,192 tokens.

In inglese

Released: Not confirmed: two readings disagree: 2024-08-27 and 2024-10-03
Status: Retired — ai.google.dev, read 16 October 2026
Retired: Not confirmed: two readings disagree: 2025-09-29 and 2025-09-24
Takes: Not confirmed: two readings disagree: text, image, audio, video and text, image, audio, video, code
Returns: Text — ai.google.dev, read 16 October 2026
Open weights: Not confirmed: The cited maker pages do not state whether this model's weights are open or downloadable.
Licence: Not confirmed: The cited maker pages do not name a licence for this model.
Context window: 1,048,576 tokens — ai.google.dev, read 16 October 2026
Longest answer: 8,192 tokens — ai.google.dev, read 16 October 2026
Knowledge cutoff: Not confirmed: The cited maker pages do not state a knowledge cutoff for this model.
API price, input: Not confirmed: The current maker pricing page does not list a standard input price for this shut-down model; no historical price is used.
API price, output: Not confirmed: The current maker pricing page does not list a standard output price for this shut-down model; no historical price is used.
Where: Not confirmed: two readings disagree: api, app and api
Parameters: Not confirmed: The cited maker pages do not publish a parameter count; the “8B” in the model name is not treated as confirmation.
Model card: https://ai.google.dev/gemini-api/docs/models/gemini — ai.google.dev, read 16 October 2026

Benchmarks

Measured by others, not by the maker: each score with the name the measurer gives the model and the setting it ran, its day and its licence.

GPQA Diamond, gemini-1.5-flash-8b-001: 33.0% (± 2.4), run 12 March 2025
OTIS Mock AIME 2024–2025, gemini-1.5-flash-8b-001: 4.6% (± 2.0), run 25 February 2025

Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks, CC BY 4.0: Epoch AI’s own runs and its Capabilities Index. Data · CC BY 4.0

The context window of Gemini 1.5 Flash-8B is 1,048,576 tokens, as Google prints it.