20% off all GPT ๐ŸŽ‰ 30% off DeepSeekLearn more

Google: Gemini 2.5 Flash

Chat
google/gemini-2.5-flash

Gemini 2.5 Flash is Google's fast, cost-efficient model in the Gemini 2.5 family, released on 2025-06-17. It pairs toggleable reasoning with full multimodal input โ€” images, audio, video, and PDFs โ€” so a single endpoint covers everything from quick classification to document analysis. It also supports function calling, prompt caching, and web search, delivering Gemini 2.5 quality at a fraction of the Pro tier's cost. Context window: 1M tokens, output: 64K. Available via OpenAI and Gemini protocols through Ofox.

Context Window
1M
Max Output Tokens
66K
Released
2025-06-17
Capabilities
VisionFunction CallingReasoningPrompt CachingWeb SearchAudio InputVideo InputPDF Input
Available Providers
Vertex
Supported Protocols
openaigemini

Providers

Vertexprovider.type: "google_vertex"
Input Tokens
$0.3/M
Output Tokens
$2.5/M
Cache Read
$0.03/M
Cache Write
$1/M
Audio Input
$1/M
Cached Audio
$0.1/M
Web Search
$0.035/R
Protocols
openai/v1/chat/completions
gemini

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.io/gemini"},
)
response = client.models.generate_content(
model="google/gemini-2.5-flash",
contents="Hello!",
)
print(response.text)

Uptime & Status

Benchmarks

LMArena โ†—Evaluated as gemini-2.5-flash

Google: Gemini 2.5 Flash scores 1410 in the Overall category of the LMArena text leaderboard (style control), ranking #115 of 374 models based on 124,376 human preference votes (updated 2026-07-12).

Benchmark scores for gemini-2.5-flash on LMArena
CategoryArena Score95% CIRankVotes
Overall1408โ€“1413#115 of 374124,376
Hard Prompts1416โ€“1423#125 of 37463,791
Coding1419โ€“1428#153 of 36925,879
Math1399โ€“1412#114 of 3627,871
Creative Writing1391โ€“1402#82 of 37217,318
Instruction Following1397โ€“1405#112 of 37433,903
Chinese1436โ€“1452#108 of 3446,418

Source: LMArena ยท CC BY 4.0 ยท Updated 2026-07-12 ยท Methodology โ†— ยท 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 2.5 Flash on Ofox.ai costs $0.3/M per million input tokens and $2.5/M per million output tokens. Pay-as-you-go, no monthly fees.