gemini

gemini-2.5-flash-preview

completions

Google's best model in terms of price-performance, offering well-rounded capabilities. Gemini 2.5 Flash rate limits are more restricted since it is an experimental / preview model.

Input:$0.15 / 1M tokens
Output:$0.6 / 1M tokens
Context:1M tokens
tools
text
image
audio
video
text

Access gemini-2.5-flash-preview through LangDB AI Gateway

Recommended

Integrate with gemini's gemini-2.5-flash-preview and 250+ other models through a unified API. Monitor usage, control costs, and enhance security.

Unified API
Cost Optimization
Enterprise Security
Get Started Now

Free tier available • No credit card required

Instant Setup
99.9% Uptime
10,000+Monthly Requests
Code Example
Configuration
Base URL
API Keys
Headers
Project ID in header
X-Run-Id
X-Thread-Id
Model Parameters
8 available
max_tokens
response_format
stop
structured_outputs
temperature
012
tool_choice
tools
top_p
011
Additional Configuration
Tools
Guards
User:
Id:
Name:
Tags:
Publicly Shared Threads5
  • gemini
    Python code implementing a full-featured Tetris game using Pygame with classic mechanics, scoring, next piece preview, and game over handling.
    python tetris game
    pygame tetris tutorial
    tetromino game development
    classic tetris python
  • gemini
    Explanation and origin of "ride shotgun," its modern meaning of sitting front passenger, plus example sentence and usage scenario.
    ride shotgun idiom
    ride shotgun origin
    ride shotgun meaning
    ride shotgun usage
  • gemini
    Created a responsive navigation bar that toggles a hamburger menu for screens under 600px using HTML, CSS, and vanilla JavaScript.
    responsive navigation bar
    collapsible hamburger menu
    html css javascript navbar
    mobile friendly navigation
  • gemini
    Solved the bridge-crossing puzzle for A, B, C, D with one flashlight, finding the minimum total time of 17 minutes and optimal crossing steps.
    bridge crossing puzzle
    minimum crossing time
    flashlight bridge problem
    optimal crossing sequence
  • gemini
    Detailed breakdown and count of vowels in the word "encyclopedia," identifying each vowel occurrence and explaining the counting process.
    counting vowels
    vowels in encyclopedia
    vowel identification
    english vowels
Popular Models10
  • deepseek
    DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well on a variety of tasks.
    Input:$0.24 / 1M tokens
    Output:$0.82 / 1M tokens
    Context:163840 tokens
    tools
    text
    text
  • openai
    GPT-4o mini (o for omni) is a fast, affordable small model for focused tasks. It accepts both text and image inputs, and produces text outputs (including Structured Outputs). It is ideal for fine-tuning, and model outputs from a larger model like GPT-4o can be distilled to GPT-4o-mini to produce similar results at lower cost and latency.The knowledge cutoff for GPT-4o-mini models is October, 2023.
    Input:$0.15 / 1M tokens
    Output:$0.6 / 1M tokens
    Context:128K tokens
    tools
    text
    image
    text
  • deepseek
    May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass. Fully open-source model.
    Input:$0.39 / 1M tokens
    Output:$1.63 / 1M tokens
    Context:163840 tokens
    text
    text
  • bytedance
    UI-TARS-1.5 is a multimodal vision-language agent optimized for GUI-based environments, including desktop interfaces, web browsers, mobile systems, and games. Built by ByteDance, it builds upon the UI-TARS framework with reinforcement learning-based reasoning, enabling robust action planning and execution across virtual interfaces. This model achieves state-of-the-art results on a range of interactive and grounding benchmarks, including OSworld, WebVoyager, AndroidWorld, and ScreenSpot. It also demonstrates perfect task completion across diverse Poki games and outperforms prior models in Minecraft agent tasks. UI-TARS-1.5 supports thought decomposition during inference and shows strong scaling across variants, with the 1.5 version notably exceeding the performance of earlier 72B and 7B checkpoints.
    Input:$0.1 / 1M tokens
    Output:$0.2 / 1M tokens
    Context:128K tokens
    text
    image
    text
  • mistralai
    ministral-8b
    mistralai
    Ministral 8B is an 8B parameter model featuring a unique interleaved sliding-window attention pattern for faster, memory-efficient inference. Designed for edge use cases, it supports up to 128k context length and excels in knowledge and reasoning tasks. It outperforms peers in the sub-10B category, making it perfect for low-latency, privacy-first applications.
    Input:$0.1 / 1M tokens
    Output:$0.1 / 1M tokens
    Context:128K tokens
    tools
    text
    text
  • anthropic
    Our high-performance model with exceptional reasoning and efficiency
    Input:$3 / 1M tokens
    Output:$15 / 1M tokens
    Context:200K tokens
    tools
    text
    image
    text
  • anthropic
    claude-opus-4
    anthropic
    Our most capable and intelligent model yet. Claude Opus 4 sets new standards in complex reasoning and advanced coding
    Input:$15 / 1M tokens
    Output:$75 / 1M tokens
    Context:200K tokens
    tools
    text
    image
    text
  • gemini
    Gemini 2.5 Pro is our most advanced reasoning Gemini model, capable of solving complex problems.
    Input:$1.25 / 1M tokens
    Output:$10 / 1M tokens
    Context:1M tokens
    tools
    text
    image
    audio
    video
    text
  • openai
    gpt-4.1
    openai
    GPT-4.1 is OpenAI's flagship model for complex tasks. It is well suited for problem solving across domains.
    Input:$2 / 1M tokens
    Output:$8 / 1M tokens
    Context:1047576 tokens
    tools
    text
    image
    text
  • gemini
    Gemini 2.5 Pro Experimental is Google's state-of-the-art thinking model, capable of reasoning over complex problems in code, math, and STEM, as well as analyzing large datasets, codebases, and documents using long context.
    Input:$1.25 / 1M tokens
    Output:$10 / 1M tokens
    Context:1M tokens
    tools
    text
    image
    audio
    video
    text