Back to Models
google/gemini-2-5-flash
Not Available
Gemini 2.5 Flash
Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in "thinking" capabilities, enabling it to provide responses with greater accuracy and nuanced context handling. Additionally, Gemini 2.5 Flash is configurable through the "max tokens for reasoning" parameter, as described in the documentation (https://openrouter.ai/docs/use-cases/reasoning-tokens#max-tokens-for-reasoning).
6/17/2025
1,048,576 tokens
Specifications
Modalities
Input
file
image
text
audio
video
Output
text
Supported Parameters
include_reasoning
max_tokens
reasoning
response_format
seed
stop
structured_outputs
temperature
tool_choice
tools
top_p
Max Output Tokens
65,535Frequently asked questions
- Is Gemini 2.5 Flash available on FastMetal?
- Not at the moment. GLM 5.3 Flash, from the same lab, is available on the FastMetal API today.
- What is the context window of Gemini 2.5 Flash?
- 1,048,576 tokens, shared between the prompt and the response.