Skip to content
GoogleChat

Gemini 2.5 Flash Preview 05-20 (thinking)

gemini-2.5-flash-preview-05-20:thinking

Gemini 2.5 Flash Preview (May 2025) is Google's high-performance general model built for advanced reasoning, coding, math, and science. It includes built-in “thinking” features to deliver more accurate, context-aware answers.

Context
1.0M tokens
Max output
Unknown
Endpoint

Get API KeyCompare

Pricing

Input$0.075 / 1M
Output$1.75 / 1M
Cache Write (5m)$0.075 / 1MDefault rate
Cache Write (1h)$0.075 / 1MDefault rate
Cache Read$0.075 / 1MDefault rate
Web SearchNo surcharge

Quick Start

Select an endpoint and copy a working example for this model.

Endpoint
python
from openai import OpenAI client = OpenAI(    api_key="YOUR_API_KEY",    base_url="https://api.apertis.ai/v1") response = client.chat.completions.create(    model="gemini-2.5-flash-preview-05-20:thinking",    messages=[        {"role": "user", "content": "Hello!"}    ],    max_tokens=1024,    temperature=0.7) print(response.choices[0].message.content) # Optional: Enable context compression to reduce token usage# response = client.chat.completions.create(#     model="gemini-2.5-flash-preview-05-20:thinking",#     messages=[{"role": "user", "content": "Hello!"}],#     extra_body={"compression": {"enabled": True, "model": "gpt-4.1-mini"}}# )

Supported Parameters

API docs
Common7 params
modelmessagesmax_tokenstemperaturetop_pstreamtools
Extended4 params
reasoning_effortstream_optionsthinkingextra_body

Cursor IDE Model IDs

Use these namespaced identifiers in Cursor IDE to avoid conflicts with built-in models.

gemini-2.5-flash-preview-05-20:thinking

Questions about Gemini 2.5 Flash Preview 05-20 (thinking)

How much does Gemini 2.5 Flash Preview 05-20 (thinking) cost on Apertis?

Gemini 2.5 Flash Preview 05-20 (thinking) costs $0.075 per 1M input tokens and $1.75 per 1M output tokens on Apertis.

What is Gemini 2.5 Flash Preview 05-20 (thinking)'s context window?

Gemini 2.5 Flash Preview 05-20 (thinking) has a context window of 1.0M tokens.

Which company develops Gemini 2.5 Flash Preview 05-20 (thinking)?

Gemini 2.5 Flash Preview 05-20 (thinking) is developed by Google.

Which model ID do I use to call Gemini 2.5 Flash Preview 05-20 (thinking)?

Use the model ID gemini-2.5-flash-preview-05-20:thinking to call Gemini 2.5 Flash Preview 05-20 (thinking).

Compare with Other Models

See how this model compares to others from the same provider.