AIHubMixAIHubMix
Models
gemini-2.5-pro-exp-03-25
Compare
Google logo

gemini-2.5-pro-exp-03-25

Google
Google’s latest experimental model, highly unstable, for experience only. It boasts strong reasoning and coding capabilities, able to "think" before responding, enhancing performance and accuracy in complex tasks. It supports multimodal inputs (text, audio, images, video) and a 1 million token context window, suitable for advanced programming, math, and science tasks. This means Gemini 2.5 can handle more complex problems in coding, science and math, and support more context-aware agents.

Pricing

TierPricingCache ReadWeb SearchCache Storage
Input<=200K
$1.25$10
$0.125/M tokens$0.035/request$4.5/h/M tokens
200K<Input
$2.5$15
$0.25/M tokens$0.035/request$4.5/h/M tokens

Input Modalities

  • Text
  • Vision
  • Audio
  • Video

Output Modalities

  • Text

Capabilities

  • Tools
  • Structured outputs
  • Long context

Providers

VertexAI gemini-2.5-pro-exp-03-25
Pricing$1.25$10
Cache Read$0.125/M tokens
Web Search$0.035/request
Cache Storage$4.5/h/M tokens
Pricing$2.5$15
Cache Read$0.25/M tokens
Web Search$0.035/request
Cache Storage$4.5/h/M tokens
Context0
Max output0
Latency8.3S
Throughput122.0TPS
Uptime
0.00% uptime 2 days ago
0.00% uptime yesterday
0.00% uptime today
Google AI Studio gemini-2.5-pro-exp-03-25
Pricing$1.25$10
Cache Read$0.125/M tokens
Web Search$0.035/request
Cache Storage$4.5/h/M tokens
Pricing$2.5$15
Cache Read$0.25/M tokens
Web Search$0.035/request
Cache Storage$4.5/h/M tokens
Context0
Max output0
Latency8.3S
Throughput122.0TPS
Uptime
0.00% uptime 2 days ago
0.00% uptime yesterday
0.00% uptime today

Performance for gemini-2.5-pro-exp-03-25

Uptime is the percentage of requests that succeeded over the past 72 hours. AIHubMix continuously monitors every provider and automatically retries with the next-best provider when one returns an error or responds too slowly; Latency is total round-trip time (lower is better); Throughput is how fast the model writes (tokens per second, higher is better).

Uptime
Loading...
Latency
Loading...
Throughput
Loading...

Try this model

Python
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["AIHUBMIX_API_KEY"],
    base_url="https://aihubmix.com/v1",
)

response = client.chat.completions.create(
    model="gemini-2.5-pro-exp-03-25",
    messages=[
      {
        "role": "user",
        "content": "Hello, how are you?"
      }
    ],
    max_tokens=1024,
    stream=False,
)

print(response.choices[0].message.content)

Frequently asked questions

What is gemini-2.5-pro-exp-03-25?

Google’s latest experimental model, highly unstable, for experience only. It boasts strong reasoning and coding capabilities, able to "think" before responding, enhancing performance and accuracy in complex tasks. It supports multimodal inputs (text, audio, images, video) and a 1 million token context window, suitable for advanced programming, math, and science tasks. This means Gemini 2.5 can handle more complex problems in coding, science and math, and support more context-aware agents.
AIHubMix

© 2023 - 2026 AIHubMix, LLC

Product

Company

Developer

Connect