Ficelle
Gemini 3.8 Flash free tier: limits, terms and failover
Gemini 3.8 Flash has a free tier on the Gemini API: a 1M-token context, tools and structured output. What the free tier allows, its terms, and how to fail over.
Checked against Google's and each provider's official pages
Where Gemini 3.8 Flash is free
Google's Gemini API has a free tier for Gemini 3.8 Flash, with limits set per project and data terms that differ from the paid tier.
| Provider | Model id | Free-tier terms |
|---|---|---|
| Gemini | gemini-3.8-flash |
Free tier with per-project limits shown in AI Studio, not published. Batch, Flex and Google Search grounding are not free. |
Listed, but not free
-
OpenRouter
(
google/gemini-3.8-flash): paid only; there is no :free variant.
What Gemini 3.8 Flash is
Gemini 3.8 Flash is Google's newest Flash model, based on Gemini 3.7 Flash and aimed at long-horizon software engineering, autonomous agents and enterprise workflows. It is a proprietary model, served only through Google.
- Context window
- 1,048,576 tokens in, 65,536 out
- Input
- Text, image, video, audio, PDF
- Output
- Text
- Tools
- Function calling and structured outputs
- Reasoning
- Thinking at low, medium or high
- Parameters
- Not disclosed by Google
Before you rely on it
- Free-tier prompts and responses may be used to improve Google products and read by human reviewers; do not send sensitive data.
- Apps offered to users in the EEA, Switzerland or the UK must use paid services, per the Gemini API terms.
- Older Flash models (3.7, 3.6, 3.5 and 3.5 Flash-Lite) are on the free tier too, each with its own limits.
Use Gemini 3.8 Flash with automatic failover
A single free tier runs out. Ficelle puts the free models of every provider you
configure behind one local OpenAI-compatible endpoint. Call a routing profile and
Gemini 3.8 Flash is one of the models it can pick; when it rate-limits or fails, the next
eligible free model answers. To pin Gemini 3.8 Flash alone, call the id that
ficelle models lists for it, knowing a pinned model has no failover.
from openai import OpenAI
client = OpenAI(base_url="http://127.0.0.1:8646/v1", api_key="ficelle-local")
# A routing profile keeps failover: Gemini 3.8 Flash is one of the free
# models it can pick, and the next eligible one answers if it fails.
client.chat.completions.create(
model="ficelle/auto-tools",
messages=[{"role": "user", "content": "..."}],
)Routing profiles that fit what Gemini 3.8 Flash is built for:
- Tool calling
ficelle/auto-tools - JSON & structured output
ficelle/auto-json - Long context
ficelle/auto-long - Multimodal
ficelle/auto-multimodal
Whether a profile routes to Gemini 3.8 Flash on your install depends on your providers' live catalogs and Ficelle's eligibility checks, decided at request time.
Questions
Is Gemini 3.8 Flash free to use?
Google's Gemini API has a free tier for Gemini 3.8 Flash, with limits set per project and data terms that differ from the paid tier. When we checked on 28 September 2026, Gemini served it at no charge, each under its own free-tier limits.
Where can I use the Gemini 3.8 Flash API for free?
Gemini as gemini-3.8-flash. Free catalogs change often, so check the provider's own page before you rely on one.
What is Gemini 3.8 Flash?
Gemini 3.8 Flash is Google's newest Flash model, based on Gemini 3.7 Flash and aimed at long-horizon software engineering, autonomous agents and enterprise workflows. It is a proprietary model, served only through Google.
Can I call Gemini 3.8 Flash through Ficelle?
Yes, when one of your configured providers serves it for free. Run ficelle models to see the ids your install can route to. Calling that id pins the one model, with no failover; calling a routing profile such as ficelle/auto-tools keeps failover, so another free model answers when Gemini 3.8 Flash is rate-limited.
Sources
Official pages this guide rests on, read on 28 September 2026:
