About
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.
Pricing
| Input | $1.16 from $0.52 | per 1M prompt tokens |
|---|---|---|
| Output | $5.77 from $2.63 | per 1M generated tokens, reasoning included |
| Cached input | $0.12 | per 1M tokens read back from the prompt cache |
| Cache write | $0.06 | per 1M tokens written to the prompt cache |
| Web search | $0.020 | per request that uses the provider’s built-in search |
50% off right now. The provider is running a promotion, and the developer API bills what the provider actually charged for your call plus our flat markup, so it reaches your bill with nothing to claim. The “from” figure is the cheapest endpoint serving the model; which one answers is the provider’s routing decision, so treat it as a floor. Promotions can end at any time.
What a request costs
| Typical request | Each | Per 1,000 |
|---|---|---|
| Short chat reply1,500 in · 400 out | $0.0040 | $4.04 |
| Question over a long document40,000 in · 800 out | $0.051 | $50.82 |
| Agent tool step20,000 in · 1,200 out | $0.030 | $30.03 |
At the developer-API rate, before any provider promotion or prompt-cache saving. In the app, the model picker shows what a message costs on your plan before you send it.
Benchmarks
Head-to-head rankings
- #5Godot gamesAgent arenaElo 127353% wins
- #6Mobile appsAgent arenaElo 123354% wins
- #8SVGModel arenaElo 129255% wins
- #10ASCII artModel arenaElo 127553% wins
- #11Full stackAgent arenaElo 124448% wins
- #11Web appsAgent arenaElo 123146% wins
- #11UI componentsModel arenaElo 131954% wins
- #13WebsitesModel arenaElo 130350% wins
- #15CodeModel arenaElo 130650% wins
- #17Game devModel arenaElo 130851% wins
Scores from Artificial Analysis; bars are scaled to the best model on our list. Rankings from Design Arena head-to-head votes. Published by OpenRouter alongside its catalogue.
Call it from code
OpenAI-compatible: point any OpenAI SDK at https://api.privateer.pro/v1 and set
model. Keys are created in the app under Settings.
curl https://api.privateer.pro/v1/chat/completions \
-H "Authorization: Bearer $PRIVATEER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "google/gemini-3.8-flash",
"messages": [{ "role": "user", "content": "Hello" }]
}'import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.privateer.pro/v1",
api_key=os.environ["PRIVATEER_API_KEY"],
)
reply = client.chat.completions.create(
model="google/gemini-3.8-flash",
messages=[{"role": "user", "content": "Hello"}],
)
print(reply.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.privateer.pro/v1",
apiKey: process.env.PRIVATEER_API_KEY,
});
const reply = await client.chat.completions.create({
model: "google/gemini-3.8-flash",
messages: [{ role: "user", content: "Hello" }],
});
console.log(reply.choices[0].message.content);Parameters this model accepts
include_reasoningmax_tokensreasoningreasoning_effortresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_p