Gemini 2.5 Flash Lite

google/gemini-2.5-flash-lite
VisionAudioToolsJSONReasoning
by Google · 2025-07-22

Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance...

ctx1M tokens
Max output65K
Inputtext + image + file + audio + video
Outputtext
p50 TTFT1.34 s
INPUT$0.10/ 1M tokens
OUTPUT$0.40/ 1M tokens
p50 TTFT1.34 s7d
p95 TTFT8.52 s7d
TRAFFIC11.3Mtokens / 7d

Google Gemini 2.5 Flash Lite is a smaller, faster, and more affordable variant of the Gemini 2.5 Flash model from Google. It is designed to handle a wide range of multimodal inputs—including text,…

What is Google Gemini 2.5 Flash Lite?

Who should use this model?

What input modalities does it support?

How does it compare to other Google models?

Code samples

Call from any SDK

OpenAI-compatible — keep the SDK you already use

  • OpenAI SDKhttps://api.orcarouter.ai/v1
  • Gemini SDKhttps://api.orcarouter.ai
import os

from openai import OpenAI

client = OpenAI(
    base_url="https://api.orcarouter.ai/v1",
    api_key=os.environ["ORCAROUTER_API_KEY"],
)

response = client.chat.completions.create(
    model="google/gemini-2.5-flash-lite",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Supported parameters

  • include_reasoning
  • max_tokens
  • reasoning
  • response_format
  • seed
  • stop
  • structured_outputs
  • temperature
  • tool_choice
  • tools
  • top_p

Pricing

Input / 1M tokens$0.100
Output / 1M tokens$0.400
Cache read / 1M$0.010
CurrencyUSD

Cost calculator

Tokens / month10MM
Input share70%%
Estimated / month $1.90 · With prompt caching $1.59

Estimate based on list price

Token & cost estimator

Input tokens: 20Cost per request: $0.000202

Estimate only — actual token counts depend on the provider's tokenizer.

Performance

p50 TTFT
1.34 s
Output speed
541 tok/s
p95 TTFT
8.52 s
Error rate
0.44%

Public benchmarks

7.4
AA Coding
Better than 1% of models compared
#125 of 126
6.7
AA Intelligence
Better than 3% of models compared
#122 of 128
35.3
AA Math
Better than 12% of models compared
#71 of 81
AIME
50.0
AIME 2025
35.3
GPQA Diamond
47.4
Humanity's Last Exam
3.7
IFBench
31.5
LiveCodeBench
40.0
Long-Context Recall
32.0
MATH-500
92.6
MMLU-Pro
72.4
SciCode
17.7
TerminalBench Hard
2.3
τ²-Bench
19.0
Source: artificialanalysis.ai

Community buzz

What developers are saying this week

Hacker News0 mentions · 7ddown 1 vs the previous week

How it compares

Gemini 2.5 Flash LiteGemini 3.1 Pro PreviewGemini 3.1 Pro Preview Custom ToolsGemini 3 Flash Preview
Input $/M$0.10$2.00$4.00$0.50
Output $/M$0.40$12.00$18.00$3.00
Context1.0M1.0M1.0M1.0M
Quality2/1010/1010/109/10
Compare side-by-sideCompare side-by-sideCompare side-by-sideCompare side-by-side

FAQ

What is the cost per token for Gemini 2.5 Flash Lite on OrcaRouter?
Input tokens cost $0.10 per 1 million tokens, output tokens cost $0.40 per 1 million tokens. OrcaRouter bills at the provider rate with zero markup.
What is the context window size?
The context window is 1,048,576 tokens (1 million tokens), and the maximum output is 65,536 tokens.
What are the model's main strengths?
Strengths include low cost, high speed, strong math reasoning (92.6 on MATH-500), a very large context window, and multimodal support for text, images, files, audio, and video.
How does it compare to Gemini 2.5 Flash?
Gemini 2.5 Flash Lite is cheaper and faster but likely has slightly lower performance on complex reasoning, creative writing, and code generation compared to the full Flash model.
Does OrcaRouter store or share my data when using this model?
The provided facts do not specify OrcaRouter's data handling policies. Typically, API providers may process data only to fulfill requests. Check OrcaRouter's privacy policy for details.
How do I call this model via an OpenAI-compatible API?
Use base URL https://api.orcarouter.ai/v1 with model id "google/gemini-2.5-flash-lite" in your OpenAI client library. Include your OrcaRouter API key in the Authorization header.
Can I use multimodal inputs like images and audio?
Yes, the model accepts text, image, file, audio, and video inputs. You can include them as content parts in the user message using the standard OpenAI multimodal format.
What is the expected latency?
The model is designed for low latency, especially compared to larger models. Exact times depend on input/output length and server load. No specific latency figures are provided.
What programming languages and frameworks are supported?
Any language that supports HTTP requests and the OpenAI API format (Python, JavaScript, Go, Java, etc.) can be used. The official OpenAI Python library works seamlessly.
Does OrcaRouter offer any caching or discounts for high volume?
No caching or volume discount information was provided. Pricing is per token at provider rates without markup. Contact OrcaRouter for enterprise inquiries.

Embed this badge

Google: Gemini 2.5 Flash Lite$0.10/M in1339ms p50via OrcaRouter
HTML <a href="https://www.orcarouter.ai/models/google/gemini-2.5-flash-lite" target="_blank"> <img src="https://www.orcarouter.ai/embed/google/gemini-2.5-flash-lite.svg" alt="Google: Gemini 2.5 Flash Lite on OrcaRouter" /> </a>
Markdown [![Google: Gemini 2.5 Flash Lite](https://www.orcarouter.ai/embed/google/gemini-2.5-flash-lite.svg)](https://www.orcarouter.ai/models/google/gemini-2.5-flash-lite)

Model card as data

GET /api/public/models/google/gemini-2.5-flash-liteOpen
Machine-readable:/llms.txt/llms-full.txt