Gemini 3.5 Flash-Lite

By Google, on GridPup at $0.36 per million input tokens and $3.02 per million output tokens, paid from your GridPup balance per request. No subscription.

Try it in the Playground Get an API key

Price

Made by: Google
Input: $0.36 per million tokens
Output: $3.02 per million tokens
Context: 1.048576M tokens
Can: Tools, Reads images

What it costs, roughly
A 1,000-word answer to a 200-word question	$0.0041
1,000 such answers	$4.12
Summarising a 50-page document (25,000 words) in 500 words	$0.014

Use it from your code

GridPup's API speaks OpenAI's format: use any OpenAI SDK with the base URL https://api.gridpup.com/v1/ai and a GridPup API key with Also use AI models. The answer tells you what it cost. More in the API docs.

from openai import OpenAI

client = OpenAI(base_url="https://api.gridpup.com/v1/ai", api_key="gp_live_…")

r = client.chat.completions.create(
    model="google/gemini-3.5-flash-lite",
    messages=[{"role": "user", "content": "Explain a KV cache in two sentences."}],
)
print(r.choices[0].message.content)
print("cost:", r.usage.cost_usd, "USD")

Questions

How much does Gemini 3.5 Flash-Lite cost?: $0.36 per million input tokens and $3.02 per million output tokens, charged per request from your prepaid balance. You need a small balance to start ($1 for most models); there is no monthly fee.
Who runs it?: Google made Gemini 3.5 Flash-Lite. GridPup serves it through Cloudflare's AI Gateway, so you use it with one GridPup balance instead of an account with Google.
Does it work with the OpenAI SDK?: Yes: set base_url to https://api.gridpup.com/v1/ai and the model to google/gemini-3.5-flash-lite.

Similar chat and reasoning models

GPT-5 miniOpenAI$0.30 per million input tokens
Llama 3.3 70B (fast)Meta$0.35 per million input tokens
Gemini 2.5 FlashGoogle$0.36 per million input tokens
Grok 4.20xAI$1.51 per million input tokens
Grok 4.3xAI$1.51 per million input tokens
Qwen3.8 27BQwen$0.54 per million input tokens

All chat and reasoning models and prices

Loading…