Gemini

Google: Gemini 3.1 Flash Lite

Chat
google/gemini-3.1-flash-lite
CompareGet Started

Gemini 3.1 Flash Lite is Google's high-efficiency multimodal model, released on 2026-05-07 as the GA version of the earlier preview and optimized for low-latency, high-volume workloads. It exposes full thinking levels — minimal, low, medium and high — so you can tune the cost/performance trade-off, and it is priced at half the cost of Gemini 3 Flash. Capabilities include vision, audio, video and PDF input, tool use, prompt caching and web search. Context window: 1M tokens, output: 64K. Available via OpenAI and Gemini protocols.

Context Window
1M
Max Output Tokens
64K
Released
2026-05-07
Capabilities
VisionFunction CallingReasoningPrompt CachingWeb SearchAudio InputVideo InputPDF Input
Available Providers
GoogleCloudVertex
Supported Protocols
OpenAIopenaiGeminigemini

Providers

GoogleCloudVertex
Input Tokens
$0.25/M
Output Tokens
$1.5/M
Cache Read
$0.025/M
Cache Write
$1/M
Audio Input
$0.5/M
Cache Write (1 hour)
$1/M
Cached Audio
$0.05/M
Web Search
$0.014/R
Protocols
OpenAIopenai/v1/chat/completions
Geminigemini

Code Examples

from google import genai
client = genai.Client(
api_key="YOUR_OFOX_API_KEY",
http_options={"api_version": "v1beta", "base_url": "https://api.ofox.run/gemini"},
)
response = client.models.generate_content(
model="google/gemini-3.1-flash-lite",
contents="Hello!",
)
print(response.text)

Uptime & Status

Benchmarks

LMArenaEvaluated as gemini-3.1-flash-lite-preview

Google: Gemini 3.1 Flash Lite scores 1432 in the Overall category of the LMArena text leaderboard (style control), ranking #77 of 374 models based on 60,926 human preference votes (updated 2026-07-12).

Benchmark scores for gemini-3.1-flash-lite-preview on LMArena
CategoryArena Score95% CIRankVotes
Overall143214281435#77 of 37460,926
Hard Prompts144414391449#91 of 37439,139
Coding145714511463#111 of 36916,852
Math143814281449#62 of 3623,430
Creative Writing141214051420#62 of 3729,869
Instruction Following140614011412#101 of 37419,934
Chinese147814661489#68 of 3443,283

Source: LMArena · CC BY 4.0 · Updated 2026-07-12 · Methodology · Ranks compare models within each category of the LMArena text leaderboard (style control). Scores come from third-party human preference evaluations, not from OFOX.

Frequently Asked Questions

Google: Gemini 3.1 Flash Lite on Ofox.ai costs $0.25/M per million input tokens and $1.5/M per million output tokens. Pay-as-you-go, no monthly fees.