Gemini 3.8 Flash runs at 70% off on API Token Router.
Google: Gemini 3.8 Flash
Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.
Modalities
Price (in / out)
70% off$0.2228 / $1.1138$0.75 / $3.75per 1M
Context
1M
Released
Sep 2, 2026
Call the Gemini 3.8 Flash API
Model ID gemini-3.8-flash · replace <API_TOKEN_ROUTER_API_KEY> with your API key
OpenAI-compatible
curl https://apitokenrouter.com/v1/chat/completions \
-H "Authorization: Bearer <API_TOKEN_ROUTER_API_KEY>" \
-H "Content-Type: application/json" \
-d '{"model":"gemini-3.8-flash","messages":[{"role":"user","content":"Hello"}]}'Gemini native
curl "https://apitokenrouter.com/v1beta/models/gemini-3.8-flash:generateContent" \
-H "Authorization: Bearer <API_TOKEN_ROUTER_API_KEY>" \
-H "Content-Type: application/json" \
-d '{"contents":[{"parts":[{"text":"Hello"}]}]}'Providers
API Token Router routes by health and cost within the discount range and provider list you configured. When one returns an error we fall through to the next best — you don't pick a provider in the request. Configure discount range
Need a specific set of providers?
| Provider | Context | Input | Output | Cache | Latency | Throughput | Uptime | No training |
|---|---|---|---|---|---|---|---|---|
| Google AI | 1M | $0.75$0.2228 | $3.75$1.1138 | $0.075$0.0223 | — | — | — | No training |
| Google Vertex | 1M | $0.75$0.2228 | $3.75$1.1138 | $0.075$0.0223 | — | — | — | No training |
Uptime
API Token Router continuously probes every provider and falls through to the next best one on error.
Uptime (24h)
—
Uptime (3d)
—
Uptime, last 3 days
—
Uptime, last 24 hours
One line per upstream provider, taking the best success rate among that provider's channels. The API Token Router line counts only the final attempt of each request — the end-to-end result after all fallbacks.
AVAILABILITY · LAST 24H · API Token Router GATEWAY
Data security
API Token Router does not use your data to train models.
For the full data-security policy, learn more.
Need to pick your own providers? .
Quickstart
from google import genai
from google.genai import types
client = genai.Client(
api_key="<API_TOKEN_ROUTER_API_KEY>",
http_options=types.HttpOptions(base_url="https://apitokenrouter.com"),
)
response = client.models.generate_content(
model="gemini-3.8-flash",
contents="Hello",
)
print(response.text)Endpoint: https://apitokenrouter.com
About Gemini 3.8 Flash
Gemini 3.8 Flash is a Google model. On API Token Router its model ID is gemini-3.8-flash, and the same API Token Router API key works for it and every other model. Setup steps are in the API docs.
- Model ID
gemini-3.8-flash- Provider
- Context window
- 1M tokens
- Official list price
- $0.75 input / $3.75 output per 1M tokens
- Released
- Sep 2, 2026
More Google models
Similar-priced models
Use the Gemini 3.8 Flash API
Point the base URL at API Token Router and use gemini-3.8-flash as the model name; nothing else changes. Python example:
from google import genai
from google.genai import types
client = genai.Client(
api_key="<API_TOKEN_ROUTER_API_KEY>",
http_options=types.HttpOptions(base_url="https://apitokenrouter.com"),
)
response = client.models.generate_content(
model="gemini-3.8-flash",
contents="Hello",
)
print(response.text)Use Gemini 3.8 Flash in OpenCode
OpenCode
OpenCode → Settings → Providers → Custom provider
Provider ID: apitokenrouter
Base URL: https://apitokenrouter.com/v1
API key: <your API Token Router API key>
Model ID: gemini-3.8-flashGemini 3.8 Flash guides
- Gemini 3.8 Flash API: Pricing, Limits, Model ID and How to Call It
- Gemini 4 Hydrogen API Is Out: gemini-4-hydrogen Price, Four Thinking Levels and How to Call It
- Gemini 4 Hydrogen vs Carbon vs Argon: Price, Capability and Which to Pick
- Using Gemini 4 Hydrogen Without a Google Account or a Credit Card
- Gemini 4 Carbon API Is Live: Model ID, Price, Benchmarks and How It Differs From Argon
- Gemini Krypton Release Date: What We Know So Far
Gemini 3.8 Flash FAQ
- What is the Gemini 3.8 Flash API model ID?
- The model ID is gemini-3.8-flash. The OpenAI-compatible base URL is https://apitokenrouter.com/v1.
- How do I get a Gemini 3.8 Flash API key?
- You don't need a Google account. Sign up for API Token Router, create a key (sk-…) under API Keys in the dashboard, top up from $5, and call gemini-3.8-flash — the same key also works for every other model. Create an API key.
- How large is the Gemini 3.8 Flash context window?
- Gemini 3.8 Flash has a 1M-token context window.
- How much does the Gemini 3.8 Flash API cost?
- The official list price of Gemini 3.8 Flash is $0.75 input / $3.75 output per 1M tokens. API Token Router bills per use with no monthly fee; see the price table on this page for the current discounted price.
- How do I pay for the Gemini 3.8 Flash API?
- New accounts start with a $0 balance. Top up from $5 by card in the API Token Router dashboard, then usage is deducted per request, with no subscription. Top up.
- Can I use Gemini 3.8 Flash from Russia?
- Yes. API Token Router works from Russia without a VPN, and the Russian version of the site lets you pay in rubles with SBP, SberPay, T-Bank or YooMoney. Gemini 3.8 Flash на русском.
- Can I use Gemini 3.8 Flash in Cursor, Cline or Cherry Studio?
- Yes. Choose the OpenAI-compatible provider, set the base URL to https://apitokenrouter.com/v1, use your API Token Router API key, and enter gemini-3.8-flash as the model name.
- Can I pay for the Gemini 3.8 Flash API with USDT?
- Yes. In the top-up dialog, click "Pay with crypto" and send USDT, USDC or ETH from Binance, OKX or any wallet. The minimum is $5 and no browser extension is needed. Step by step: how to pay for the API with USDT.