Gemini 3.5 Flash-Lite API

google/gemini-3.5-flash-lite

The cheapest Gemini text tier — built for high-volume agentic tasks, translation and simple data processing over an OpenAI-compatible endpoint.

Context window: 1M tokens
Max output: 65.5K tokens
Input: $0.3 / 1M tokens
Output: $2.5 / 1M tokens
Cached input: $0.03 / 1M tokens
Modalities: text → text
Features: tool callingjson modestreaming

Connect Sign in to chat

OpenAPI

Connect to Gemini 3.5 Flash-Lite

Gemini 3.5 Flash-Lite is served through an OpenAI-compatible chat completions API. Point any OpenAI SDK or OpenAI-compatible tool at the base URL below with a ModelRunner API key — no polling, the reply comes back in the response (or streams).

base_url: https://queue.modelrunner.run/google/gemini-3.5-flash-lite
model: google/gemini-3.5-flash-lite
auth: Authorization: Bearer <MODELRUNNER_API_KEY>get a key

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://queue.modelrunner.run/google/gemini-3.5-flash-lite",
    api_key=os.environ["MODELRUNNER_API_KEY"],
)

completion = client.chat.completions.create(
    model="google/gemini-3.5-flash-lite",
    messages=[
      {
        "role": "user",
        "content": "Explain what an API rate limit is in two sentences."
      }
    ],
)
print(completion.choices[0].message.content)

# Streaming: add stream=True and iterate the chunks
# for chunk in client.chat.completions.create(..., stream=True):
#     print(chunk.choices[0].delta.content or "", end="")

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://queue.modelrunner.run/google/gemini-3.5-flash-lite",
  apiKey: process.env.MODELRUNNER_API_KEY,
});

const completion = await client.chat.completions.create({
  model: "google/gemini-3.5-flash-lite",
  messages: [
    {
      "role": "user",
      "content": "Explain what an API rate limit is in two sentences."
    }
  ],
});
const reply = completion.choices[0].message.content;

// Streaming: pass stream: true and iterate the chunks
// for await (const chunk of await client.chat.completions.create({ ..., stream: true })) {
//   process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
// }

# One synchronous call — the reply is in the response body (no polling)
curl https://queue.modelrunner.run/google/gemini-3.5-flash-lite/chat/completions \
  -H "Authorization: Bearer $MODELRUNNER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "messages": [
      {
        "role": "user",
        "content": "Explain what an API rate limit is in two sentences."
      }
    ]
  }'

# Streaming (Server-Sent Events, ends with "data: [DONE]")
curl -N https://queue.modelrunner.run/google/gemini-3.5-flash-lite/chat/completions \
  -H "Authorization: Bearer $MODELRUNNER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "messages": [
      {
        "role": "user",
        "content": "Explain what an API rate limit is in two sentences."
      }
    ],
    "stream": true
  }'

Works withCline · Continue · Claude Code · LangChain · Vercel AI SDK · LiteLLM · Aider

Cline → Settings → API Configuration (or the CLI line below)

API Provider:  OpenAI Compatible
Base URL:      https://queue.modelrunner.run/google/gemini-3.5-flash-lite
API Key:       <your ModelRunner API key>
Model ID:      google/gemini-3.5-flash-lite

# Cline CLI equivalent
cline auth --provider openai --baseurl https://queue.modelrunner.run/google/gemini-3.5-flash-lite --modelid google/gemini-3.5-flash-lite --apikey <your ModelRunner API key>

~/.continue/config.yaml (the IDE extension and the `cn` CLI read the same file)

models:
  - name: Gemini 3.5 Flash-Lite (ModelRunner)
    provider: openai
    model: google/gemini-3.5-flash-lite
    apiBase: https://queue.modelrunner.run/google/gemini-3.5-flash-lite
    apiKey: <your ModelRunner API key>
    roles: [chat, edit]

shell environment (or the env block of ~/.claude/settings.json)

export ANTHROPIC_BASE_URL=https://queue.modelrunner.run/google/gemini-3.5-flash-lite
export ANTHROPIC_AUTH_TOKEN=<your ModelRunner API key>
export ANTHROPIC_MODEL=google/gemini-3.5-flash-lite
# optional: send Claude Code's background/sub-agent calls to the same model
export ANTHROPIC_DEFAULT_HAIKU_MODEL=google/gemini-3.5-flash-lite
export CLAUDE_CODE_SUBAGENT_MODEL=google/gemini-3.5-flash-lite
claude

import os
from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    base_url="https://queue.modelrunner.run/google/gemini-3.5-flash-lite",
    api_key=os.environ["MODELRUNNER_API_KEY"],
    model="google/gemini-3.5-flash-lite",
)
llm.invoke("Explain what an API rate limit is in two sentences.")

import { createOpenAICompatible } from "@ai-sdk/openai-compatible";
import { generateText } from "ai";

const modelrunner = createOpenAICompatible({
  name: "modelrunner",
  baseURL: "https://queue.modelrunner.run/google/gemini-3.5-flash-lite",
  apiKey: process.env.MODELRUNNER_API_KEY,
});

const { text } = await generateText({
  model: modelrunner("google/gemini-3.5-flash-lite"),
  prompt: "Explain what an API rate limit is in two sentences.",
});

import os
import litellm

response = litellm.completion(
    model="openai/google/gemini-3.5-flash-lite",           # "openai/" = OpenAI-compatible route
    api_base="https://queue.modelrunner.run/google/gemini-3.5-flash-lite",
    api_key=os.environ["MODELRUNNER_API_KEY"],
    messages=[{"role": "user", "content": "Explain what an API rate limit is in two sentences."}],
)
print(response.choices[0].message.content)

terminal

export OPENAI_API_BASE=https://queue.modelrunner.run/google/gemini-3.5-flash-lite
export OPENAI_API_KEY=<your ModelRunner API key>
aider --model openai/google/gemini-3.5-flash-lite

Streaming via SSE (stream: true; ends with data: [DONE]) · Non-streaming calls time out at ~290 s — stream long generations · 10 MB request body · Errors use the OpenAI error envelope · Optional metadata object for your own tags, never sent to the model · Many models, one provider entry: base_url https://queue.modelrunner.run/v1 (GET /v1/models lists ids; model field required)

From an MCP client (Claude Desktop, Cursor, Claude Code): connect the ModelRunner MCP server once and its run_model tool runs Gemini 3.5 Flash-Lite with a messages input — the reply comes back in the same call.

Machine-readable: OpenAPI schema · llms.txt

Example conversation

A real run of Gemini 3.5 Flash-Lite on ModelRunner · charged $0.0006 · 104 in / 159 out tokens

Extract the order details as JSON with keys order_id, customer, items (array of {name, qty, unit_price}), and total. Text: Order #A-8842 for Dana Whitfield: 3x cold brew concentrate at 12.50 each, 1x ceramic pour-over at 34.00, 2x filter pack at 6.25. Charged 105.00 to card ending 4417.

{ "order_id": "A-8842", "customer": "Dana Whitfield", "items": [ { "name": "cold brew concentrate", "qty": 3, "unit_price": 12.50 }, { "name": "ceramic pour-over", "qty": 1, "unit_price": 34.00 }, { "name": "filter pack", "qty": 2, "unit_price": 6.25 } ], "total": 105.00 }

Pricing

This model is billed per token, at separate rates for what you send and what it produces.

Input tokens

$0.3

per 1M tokens

Cached input tokens

$0.03

per 1M tokens

Output tokens

$2.5

per 1M tokens

If a run reports no token usage, it bills a flat $0.01.

Cost estimator

Estimate from the rates above — your bill is the model's reported usage × rate, exact to 6 decimals.

Requests per day/ dayInput tokens per requesttokensOutput tokens per requesttokens

Per request$0.00185

Per day$1.851,000 requests

Compare tiers and related models

Model	Input / 1M	Output / 1M	Context	Max output	Features
Gemini 3.5 Flash-Litegoogle/gemini-3.5-flash-lite	$0.3	$2.5	1M	65.5K	tool calling, json mode
Gemini 3.5 Flashgoogle/gemini-3.5-flash	$1.5	$9	1M	65.5K	reasoning, tool calling, json mode
Gemini 3.7 Flashgoogle/gemini-3.7-flash	$0.75	$3.75	1M	65.5K	reasoning, tool calling, json mode
DeepSeek V4 Prodeepseek/v4	$2.4	$4.8	1M	393.2K	reasoning, tool calling, json mode
GLM-5.2z-ai/glm-5.2	$1.4	$4.4	1M	131.1K	reasoning, tool calling, json mode
GLM-5.2 Fast Previewz-ai/glm-5.2-fast-preview	$2.8	$8.8	1M	131.1K	reasoning, tool calling, json mode
Qwen3.8-Maxalibaba/qwen3.8-max	$2	$6	1M	131.1K	reasoning, tool calling, json mode

Request parameters

The body follows OpenAI’s chat completions shape. Fields below are the ones this model documents; anything else the platform does not interpret is forwarded to the model unchanged, and the model is the authority on what it accepts.

Request parameters of Gemini 3.5 Flash-Lite
Name	Type	Required	Description
messages	array	yes	OpenAI-style conversation history. Each item is an object with a `role` (`system`, `user`, `assistant` or `tool`) and `content`.
stream	boolean	no	Return the reply as a Server-Sent Events stream of deltas terminated by `data: [DONE]`. Default: false.
max_tokens	integer	no	Upper bound on generated tokens.
tools	array	no	OpenAI-format tool definitions the model may call.
tool_choice	—	no	`auto`, `none`, `required`, or a specific tool.
response_format	object	no	Set `{"type":"json_object"}` for JSON mode.
stop	—	no	Up to 4 stop sequences.
seed	integer	no	Best-effort determinism hint.

Response

An OpenAI ChatCompletion object: id, object, created, model, choices[] and usage. The id is chatcmpl-<requestId>, and the same request appears in your dashboard.

About Gemini 3.5 Flash-Lite

Gemini 3.5 Flash-Lite is the most cost-efficient model in the Gemini text family, intended for work you do a lot of rather than work that is hard: classification, translation, extraction, tagging, routing and other high-volume data processing.

Best for

High-volume classification, tagging and routing at the lowest cost per token
Bulk translation and text normalisation pipelines
Cheap extraction of structured JSON from messy text
A low-cost default tier behind an OpenAI-compatible base URL

Notesshow the full description ›

It is built to sit behind pipelines that call an LLM on every row, every message or every support ticket, where the per-call cost compounds fast — roughly a fifth the cost of Gemini 3.5 Flash per token. Thinking is minimal by default, which is what makes it fast and cheap on classification and extraction.

## Choose another model when - A single call needs more reasoning depth than volume — step up to Gemini 3.5 Flash, or to Gemini 3.7 Flash for multi-step reasoning - Your input includes images, audio or video — this endpoint is text-only

## Tips - Custom `temperature` / `top_p` values are not supported on this generation and are ignored - For structured extraction, set `response_format: {"type": "json_object"}` and name the keys you want in the prompt

Behaviour & limits

Context window: 1M tokens (input + output)
Max output: 65.5K tokens per reply
Structured calls: OpenAI-format tools + tool_choice · response_format JSON mode
Transport: OpenAI-compatible chat completions · SSE streaming · ~290 s non-stream ceiling · 10 MB body

FAQ

How do I connect to Gemini 3.5 Flash-Lite through the API?

Gemini 3.5 Flash-Lite is served by an OpenAI-compatible chat completions endpoint. Point any OpenAI SDK or OpenAI-compatible tool at base_url https://queue.modelrunner.run/google/gemini-3.5-flash-lite with a ModelRunner API key (Authorization: Bearer <key>) and model google/gemini-3.5-flash-lite; the SDK appends /chat/completions itself. The call is synchronous — the reply comes back in the response body, or streams as Server-Sent Events with "stream": true. Do not submit it to the asynchronous queue path, which returns HTTP 400 for this model.

How much does Gemini 3.5 Flash-Lite cost?

Gemini 3.5 Flash-Lite is billed per token from the usage the model reports: $0.3 per 1M input tokens, $0.03 per 1M cached input tokens, $2.5 per 1M output tokens. There is no per-request minimum — a short call bills a fraction of a cent, exact to six decimals.

What is Gemini 3.5 Flash-Lite's context window?

Gemini 3.5 Flash-Lite supports a 1M-token context window and up to 65.5K output tokens per reply.

Can I use Gemini 3.5 Flash-Lite in GitHub Copilot or another tool that requires a /models endpoint?

Yes. Custom-provider flows that probe GET {base_url}/models before first use (GitHub Copilot's BYOK flow does) work with either base URL: https://queue.modelrunner.run/google/gemini-3.5-flash-lite self-describes at https://queue.modelrunner.run/google/gemini-3.5-flash-lite/models, and the platform base https://queue.modelrunner.run/v1 covers every public chat model with one provider entry — GET /v1/models lists the ids and the request's model field selects google/gemini-3.5-flash-lite.

Does Gemini 3.5 Flash-Lite support streaming?

Yes. Set "stream": true and the reply arrives as Server-Sent Events (data: frames ending with data: [DONE]); stream_options: {"include_usage": true} adds a final usage frame. Non-streaming calls are cut off at about 290 seconds, so stream long generations.

Does Gemini 3.5 Flash-Lite support tool calling or JSON mode?

Gemini 3.5 Flash-Lite supports function calling via an OpenAI-format tools array with tool_choice and JSON mode via response_format {"type": "json_object"}. Both are passed through to the model in the standard OpenAI chat completions shape, so existing client code works unchanged.

What happens if my ModelRunner balance runs out while calling Gemini 3.5 Flash-Lite?

The request is refused with HTTP 429 and an OpenAI-style error whose code is insufficient_quota — the convention OpenAI SDKs already understand — and nothing is charged. Top up in the dashboard and retry. (Disconnecting from a stream after output has started is not a refund — the platform finishes the upstream call and bills its exact usage.)

Gemini 3.5 Flash-Lite API

Connect to Gemini 3.5 Flash-Lite

Example conversation

Model Pricing

Pricing

Cost estimator

Compare tiers and related models

Request parameters

Response

About Gemini 3.5 Flash-Lite

Best for

Behaviour & limits

FAQ