Gemini 2.5 Flash

google/gemini-2.5-flash

Gemini 2.5 Flash is the workhorse model of Google's Gemini 2.5 family, a thinking model released as stable in June 2025. Google positions it for large-scale processing, low-latency and high-volume tasks that require reasoning, and agentic use cases, with text, image, video and audio input. It sits between 2.5 Flash-Lite and 2.5 Pro in the same generation and remains a stable model with no announced shutdown date.

Input price
$0.30USD / 1M tokens
Output price
$2.50USD / 1M tokens
Cache read
$0.03USD / 1M tokens
Context window
1M
Max output
65.5K

Specifications

CapabilitiesChatVisionReasoningStructured outputFunction callingAudio input
Input
Text, image, audio
Output
Text
Available

Questions

FAQ

How do I call Google Gemini 2.5 Flash through SandBase?

Create a SandBase API key, then send requests with the model ID "google/gemini-2.5-flash" to Chat Completions API (/v1/chat/completions) at https://api.sandbase.ai. The request examples on this page show the exact payload.

How much does Google Gemini 2.5 Flash cost?

$0.30 per 1M input tokens and $2.50 per 1M output tokens, billed per request from your SandBase balance. Discounts, when available, are shown in the pricing on this page.

What is the context window of Google Gemini 2.5 Flash?

1M tokens of context, with up to 65.5K output tokens per response.

Which features does Google Gemini 2.5 Flash support?

Google Gemini 2.5 Flash supports vision (image input), reasoning, function calling, structured output. See Specifications above for the full list.

Do I need a separate Google account?

No. One SandBase API key and balance gives you access to Google Gemini 2.5 Flash and the other models in the catalog; you do not need to sign up with Google separately.