HyperAI
Command Palette
Search for a command to run...
gemini-2.5-flash
Detailed information about gemini-2.5-flash AI model
At a glance
Modalities
Context window
1,048,576
Pricing
$0.30$2.50
Capabilities
Tool Calling
Connect the model to external tools and systems.
Structured outputs
Return responses in a specific, organized format.
Reasoning
The model thinks before responding.
Benchmarks
| Benchmark | Score | Link |
|---|---|---|
swe-bench / bash-only | 28.73% | ai.google.dev |
swe-bench / Verified | 28.73% | mini-swe-agent.com |
Pricing Details
Input
Tokens
$0.30/1M tokens
Cache read
$0.03/1M tokens
Cache write
$0.08/1M tokens
Image
$0.00/1K tokens
Audio
$0.00/1K tokens
Audio cache
$0.00/1K tokens
Output
Tokens
$2.50/1M tokens
Reasoning
$2.50/1M tokens
Other Costs
Web search
$0.014
Model Owner
Available Providers
Google
google/gemini-2.5-flash
Released on 6/17/2025
Want to try more models?
Deploy on HyperAI with one click and experience model performance instantly.