Gemini 2.5 Flash-Lite

Text

Gemini 2.5 Flash-Lite; 1M context, thinking off by default; OpenAI-compatible Chat Completions

Input $0.10 / 1M tokens | Output $0.40 / 1M tokens Gemini 2.5 Flash-Lite API reference →

Model health Insufficient data

runapi.ai

# Base URL
https://runapi.ai

# Endpoints
POST /v1/chat/completions
POST /v1/responses
POST /v1/messages
POST /v1beta/models/gemini-2.5-flash-lite:generateContent
POST /v1beta/models/gemini-2.5-flash-lite:streamGenerateContent

curl https://runapi.ai/v1/chat/completions \
  -H "Authorization: Bearer $RUNAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "gemini-2.5-flash-lite",
  "messages": [
    {
      "role": "user",
      "content": "Analyze this codebase and suggest three performance improvements with before/after examples."
    }
  ]
}'

from openai import OpenAI

client = OpenAI(
    base_url="https://runapi.ai/v1",
    api_key="your-runapi-key"
)

response = client.chat.completions.create(
    model="gemini-2.5-flash-lite",
    messages=[{"role": "user", "content": "Analyze this codebase and suggest three performance improvements with before/after examples."}]
)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://runapi.ai/v1",
  apiKey: "your-runapi-key"
});

const response = await client.chat.completions.create({
  model: "gemini-2.5-flash-lite",
  messages: [{ role: "user", content: "Analyze this codebase and suggest three performance improvements with before/after examples." }]
});

https://runapi.ai 5 endpoints

11 versions available

OVERVIEW

What Gemini 2.5 Flash-Lite is built for

Gemini 2.5 Flash-Lite is the Flash-Lite tier of Google's Gemini 2.5 generation, aimed at high-volume classification, extraction, and other low-latency work. It reached general availability on July 22, 2025, with a knowledge cutoff of January 2025. The context window is 1,048,576 tokens and output goes up to 65,536 tokens.

Thinking is off by default, and Google documents an optional thinking mode for harder prompts. Google supports function calling and structured outputs on the model.

Google's model accepts text, image, video, audio, and PDF input. On RunAPI, send text through the OpenAI-compatible Chat Completions endpoint (/v1/chat/completions); RunAPI accepts text input only for this model. Google recommends Gemini 3.5 Flash-Lite for new projects, and RunAPI lists it as gemini-3.5-flash-lite.

Model ID

gemini-2.5-flash-lite

Released

July 22, 2025 (general availability)

Knowledge cutoff

January 2025

Context window

1,048,576 tokens

Max output

65,536 tokens

Thinking

Optional, off by default

Endpoint on RunAPI

OpenAI Chat Completions, text input

Playground

Try Gemini 2.5 Flash-Lite

Pick any model and generate in seconds.

Specifications

Provider	Google
Model ID	gemini-2.5-flash-lite
Modality	Text
Task types	Synchronous
API endpoint	/v1/chat/completions
	/v1/responses

	/v1/messages
	/v1beta/models/gemini-2.5-flash-lite:generateContent
	/v1beta/models/gemini-2.5-flash-lite:streamGenerateContent
Billing unit	1K tokens
Catalog status	Operational

HOW IT WORKS

Use This Model in 3 Steps

Get Your Key

Sign up for free and create an API key for gemini-2.5-flash-lite from the dashboard.
Send a Request

POST to /v1/chat/completions with the gemini-2.5-flash-lite model slug and your parameters.
Get Results

Read the completed gemini-2.5-flash-lite response directly from the endpoint.

What this model offers

Endpoint coverage

Exposes 1 public endpoint(s): chat_completion.

Usage-based billing

Metered by 1K tokens with no subscription requirement.

Gemini 2.5 Flash-Lite Pricing

Endpoint

Price

chat_completion

Input: $0.10 / 1M tokens Output: $0.40 / 1M tokens

Cache read: $0.01 / 1M tokens

API REFERENCE

Endpoint Specification

Endpoint: POST /v1/chat/completions
Model ID: gemini-2.5-flash-lite
Task Types: chat_completion

Request parameters

No request parameters are published for this endpoint.

USE CASES

Customer support

Answer customer questions from a private knowledge base, reducing ticket volume.

Document analysis

Draft contract summaries and flag key clauses for attorney review.

Code generation

Auto-generate unit tests, code reviews, and refactoring suggestions in CI.

Trusted by developers

API Calls / Day

100.0%

Success Rate

1.8s

Avg Generation

Verified customer feedback is not available for this model yet.

FAQ

Frequently asked questions about Gemini 2.5 Flash-Lite

Should I use Gemini 2.5 Flash-Lite or Gemini 3.5 Flash-Lite?

Google recommends Gemini 3.5 Flash-Lite or Gemini 3.8 Flash for new work. Choose gemini-2.5-flash-lite when an existing workload, prompt set, or evaluation was built on it. Both models are on RunAPI under the same API key.

Can I still use Gemini 2.5 Flash-Lite?

Yes. Google has announced no shutdown date for it, although Google's own API now limits 2.5 model access to users who used them before. On RunAPI, gemini-2.5-flash-lite is available to every account.

Can I call Gemini 2.5 Flash-Lite with the OpenAI SDK?

Yes. Point the OpenAI SDK at https://runapi.ai/v1 with your RunAPI API key and send Chat Completions requests with model set to gemini-2.5-flash-lite. Tools use the standard OpenAI tools format.

Does Gemini 2.5 Flash-Lite think before answering?

Not by default. Google ships it with thinking off for high-volume, low-latency work and documents an optional thinking mode.

How do I select gemini-2.5-flash-lite?

Pass the model ID shown in the quickstart.

What's the rate limit on this variant?

Per-key rate limits scale with your usage tier. The pricing page shows current limits. If you need higher throughput, contact support to discuss tier upgrades.

Can I switch variants later?

Yes. Variant is a parameter in the request. Switch by changing the model ID — no code changes, no re-authentication, no separate billing setup. All variants share the same API key and request shape.

Does it stream?

Where streaming is available, RunAPI streams end-to-end. LLM models support token-level streaming. Media models use async task polling or webhook callbacks for result delivery.

Where do I report quality issues?

Open an issue on the public GitHub repo or email support at [email protected]. Include the task ID and model ID so the team can investigate the specific generation.

Do I need a separate provider account?

No. Your RunAPI API key is enough to access this variant and every other model in the catalog. You do not need accounts with the underlying provider.

Building with a team?

We're here to help with enterprise setup, integrations, and technical questions.