Gemini Flash Latest is an auto-updated alias from Google that always points to the newest stable release in the Gemini Flash line, hot-swapped whenever a new Flash version ships. Google gives a two-week notice by email before the model behind the alias changes.
Because it tracks the newest release, its exact capabilities shift over time as Google ships new Flash generations behind the same alias.
| Developer | |
|---|---|
| Model ID | google/gemini-flash-latest |
| Context window | 1,048,576 tokens |
| Max output | 65,536 tokens |
Always current
The alias is hot-swapped to the newest stable Flash release, so requests automatically use Google's latest Flash model without changing the model ID.
Advance notice on changes
Google provides a two-week notice before swapping the model behind the alias for any breaking change.
Measured on the AI/ML API gateway across live traffic. Figures are medians unless stated. Last updated 2026-10-12.
Gemini Flash Latest is documented as suited for long-horizon software engineering, autonomous agents, and complex enterprise workflows. It is also positioned for coding tasks, based on the model documentation for the latest Flash release.
It is suited to interactive apps that need quick answers and complex analysis. The documentation also describes it as useful for document analysis in enterprise and developer settings.
import requests r = requests.post( "https://api.aimlapi.com/v1/chat/completions", headers={"Authorization": "Bearer " + AIMLAPI_KEY}, json={ "model": "google/gemini-flash-latest", "messages": [ { "role": "user", "content": "Hello!" } ] }, ) print(r.json())
const r = await fetch("https://api.aimlapi.com/v1/chat/completions", { method: "POST", headers: { Authorization: `Bearer ${process.env.AIMLAPI_KEY}`, "Content-Type": "application/json", }, body: JSON.stringify({ "model": "google/gemini-flash-latest", "messages": [ { "role": "user", "content": "Hello!" } ] }), }); console.log(await r.json());
curl -X POST https://api.aimlapi.com/v1/chat/completions \ -H "Authorization: Bearer $AIMLAPI_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"google/gemini-flash-latest","messages":[{"role":"user","content":"Hello!"}]}'
OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Input | |
| Output | |
| Cached input |
Gemini Flash Latest has a 1,048,576 tokens context window and can return up to 65,536 tokens.
Gemini Flash Latest takes image, text as input and returns text.
Use google/gemini-flash-latest as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.
Gemini Flash Latest became available on April 27, 2026.
Gemini Flash Latest is priced at input $2.0631 / 1M tokens, output $12.3786 / 1M tokens, cached input $0.20631 / 1M tokens.
Yes, Gemini Flash Latest can stream responses as they are generated.
Yes, Gemini Flash Latest accepts image input alongside text.
Gemini Flash Latest was built by Google.
It is available via the API endpoint https://api.aimlapi.com/v1/chat/completions using the model id google/gemini-flash-latest.
