AI model
google/gemini-3.5-flash-lite
Google: Gemini 3.5 Flash Lite is a 1,048,576-token model served on Composite at $0.188 per million tokens in and $1.56 per million tokens out. Ranked #39 of 179 models by traffic on Composite over the last 30 days, taking 0.24% of tokens and 0.16% of requests. Measured on Composite, 100.0% of its last 75 requests on Composite succeeded, the typical first token arrives in 8214 ms, output runs at about 314.3 tokens per second.
Try in Playground| Model ID | google/gemini-3.5-flash-lite |
|---|---|
| Provider | |
| Context window | 1,048,576 tokens |
| Accepts | text, image, video, file, audio |
| Returns | text |
| Input price | $0.188 per million tokens |
| Output price | $1.56 per million tokens |
| Prompt caching | Supported — cached input is billed at the provider's cache rate, on credits and plans alike |
| Image input | $1.9e-7 per image |
| Audio input | $1.9e-7 per second |
| Reasoning tokens | $1.56 per million tokens |
| Web search | $0.0175 per result |
| Thinking | Always on for this model |
| Moderated | No |
| Cost on a monthly plan | About 2.5 plan credits per typical call (8k in, 1k out) |
| Routing endpoints | 2 (base plus 1 routing variant) |
Make a Composite API key and type google/gemini-3.5-flash-lite as the model name. JanitorAI takes the full URL https://composite.lucidity.sh/v1/chat/completions; SillyTavern, ChubAI, Agnai and RisuAI take https://composite.lucidity.sh/v1. It runs on credits, a plan, or your own provider key.
JanitorAI setup · SillyTavern setup · Best Janitor AI proxies compared
#39 of 179
0.24% of tokens and 0.16% of requests over 30 days.
100.0%
Across the last 75 requests Composite served for this model.
8214 ms
Median across the same sample.
314.3 tok/s
Median generation rate after the first token.
50.0%
Share of prompt tokens served from the provider's cache over 7 days.
The same model behind 1 alternative endpoint. Call the id directly to pin a route; the base id above picks for you.
| Route | Model ID | Provider | Price |
|---|---|---|---|
| cheapThink | google/gemini-3.5-flash-lite:cheapThink |
$0.188 per million tokens input · $1.56 per million tokens output |
$0.188 per million tokens input · $1.56 per million tokens output
Credits pay the provider’s price plus 25%; cache hits cost less.
On a monthly plan, a typical call (8k tokens in, 1k out) uses about 2.5 plan credits, at the provider's own price.
Gemini models combine large context windows with fast throughput, which keeps response times low even in busy group chats.
With a 1,048,576-token context window, it can hold a long-running roleplay or a full lorebook in memory without losing earlier plot details, so it suits multi-session campaigns and character cards with heavy backstory.
It is priced low enough for high-volume daily roleplay without the per-message cost adding up quickly.
Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.
Supplied by Google, not written by Composite.
Composite Gemini Router · Google: Gemini 3.8 Flash (Drafted) · Google: Gemini 3.7 Flash (Drafted)