Short answer
Gemini 3.8 Flash (gemini-3.8-flash) is the Flash model Google made generally available on September 2, 2026, described as its most capable Flash model for long software-engineering tasks and agents. Google's price is $0.75 per million input tokens and $3.75 per million output tokens (thinking tokens count as output) until December 31, 2026, and doubles on January 1, 2027. On TeamoRouter it is available under the same model ID for $0.22 input / $1.09 output at the time of writing, about 29% of the list price.
Specs at a glance
From Google's model page:
| Gemini 3.8 Flash | |
|---|---|
| Model ID | gemini-3.8-flash |
| Generally available | September 2, 2026 |
| Input | Text, images, video, audio, PDF |
| Output | Text |
| Input limit | 1,048,576 tokens |
| Output limit | 65,536 tokens |
| Thinking | low, medium, high (minimal returns an error) |
| Function calling, structured outputs, caching | Supported |
Gemini 3.7 Flash is retired. Since October 8, 2026, Google routes requests for gemini-3.7-flash to gemini-3.8-flash. Update the model name in your code.
Pricing
Google's paid tier, per 1 million tokens:
| Until Dec 31, 2026 | From Jan 1, 2027 | |
|---|---|---|
| Input | $0.75 | $1.50 |
| Output (incl. thinking) | $3.75 | $7.50 |
| Cached input | $0.075 | $0.15 |
Compared with TeamoRouter at the time of writing:
| Per 1M tokens | Google (2026) | TeamoRouter |
|---|---|---|
| Input | $0.75 | ≈ $0.22 |
| Cached input | $0.075 | ≈ $0.022 |
| Output | $3.75 | ≈ $1.09 |
TeamoRouter's price follows Google's price list, so expect it to change when Google's does in January. The current numbers are always on the pricing page.
Call it through TeamoRouter
from openai import OpenAI
client = OpenAI(base_url="https://api.teamorouter.com/v1", api_key="YOUR_KEY")
resp = client.chat.completions.create(
model="gemini-3.8-flash",
messages=[{"role": "user", "content": "Summarize the changes in this diff: ..."}],
)
print(resp.choices[0].message.content)
The Gemini-native request format works with the same key; see the examples in Gemini 4 Argon API. Full reference: API integration.
Flash or Argon
Gemini 3.8 Flash is the cheap, fast option for high-volume work and agents that make many calls. For the hardest problems, Google's flagship is Gemini 4 Argon (gemini-4-argon, $2 / $10 list). Both run on the same TeamoRouter key, so you can route easy steps to Flash and hard ones to Argon.
Paying for usage
No subscription: you top up a balance from $5 and pay only for the tokens you use, by card or with USDT, USDC or ETH from any exchange app (how to pay with crypto).
FAQ
Is Gemini 3.8 Flash getting more expensive? Yes. Google's list price doubles on January 1, 2027.
I still use gemini-3.7-flash. What happens? Google routes those requests to Gemini 3.8 Flash since October 8, 2026. Switch the model name to gemini-3.8-flash.
Do thinking tokens cost extra? They are billed as output tokens.
Can it read PDFs and video? Yes: text, images, video, audio and PDF in, text out.