All models

Gemini 3.5 Flash-Lite

google/gemini-3.5-flash-lite
Google LLMChat

Google's lightest, cheapest Gemini for high-volume simple tasks.

Quick start

# Inspect the price — a plain request returns the 402 challenge:
curl -i https://api.glianalabs.com/v1/chat/completions \
  -H "content-type: application/json" \
  -d '{
    "model": "google/gemini-3.5-flash-lite",
    "messages": [{"role": "user", "content": "<your message>"}]
  }'

# Pay + run in one step with the mppx CLI (create a wallet: npx mppx account create):
npx mppx https://api.glianalabs.com/v1/chat/completions \
  -J '{"model": "google/gemini-3.5-flash-lite", "messages": [{"role": "user", "content": "<your message>"}]}'

Parameters

Input
messages array required

OpenAI-style chat messages: [{ role: "user" | "system" | "assistant" | "tool", content }]. Vision: content may be a parts array with { type: "image_url", image_url: { url } } (public URL — upload via POST /v1/media).

max_tokens integer optional default: 1024

Output-token cap — bounds the pre-charged price ceiling. Default 1024.

stream boolean optional

true → Server-Sent Events in the OpenAI chunk format (on /v1/chat/completions).

temperature number optional

Sampling temperature. Passed through where the provider supports it.

tool_choice string optional

"auto" (default) | "none" | "required" | { type: "function", function: { name } }.

tools array optional

OpenAI-style function tools: [{ type: "function", function: { name, description, parameters } }]. The response returns tool_calls (finish_reason "tool_calls"); send results back as { role: "tool", tool_call_id, content }.

top_p number optional

Nucleus sampling. Passed through where the provider supports it.

Output
Chat completion (OpenAI-compatible)