Gemini 2.5 Flash

gemini-2.5-flash · Google

This model has been retired.
Requests return 404 model_retired. All model retirements

Gemini 2.5 Flash is Google’s best model in terms of both performance and cost efficiency, offering a comprehensive set of capabilities. It is the first Flash model to support visible reasoning, allowing insight into the thought process behind its responses. With its strong price–performance ratio, the model is well suited for large-scale processing, low-latency, high-throughput tasks that require reasoning, as well as agent-based application scenarios.

API Pricing

Input$0.3 / 1M tokens
Output$2.499 / 1M tokens
Cache read$0.03 / 1M tokens

Specifications

Context1.05M tokens
Modalitiestext, image, video, audio, PDF
Output modalitiestext
CapabilitiesThinking, Tool calling, Web search, URL context, Code interpreter, File search, Structured outputs, Prompt caching

Frequently asked questions

What is Gemini 2.5 Flash?

Gemini 2.5 Flash is Google’s best model in terms of both performance and cost efficiency, offering a comprehensive set of capabilities. It is the first Flash model to support visible reasoning, allowing insight into the thought process behind its responses. With its strong price–performance ratio, the model is well suited for large-scale processing, low-latency, high-throughput tasks that require reasoning, as well as agent-based application scenarios.

What is the context length of Gemini 2.5 Flash?

Gemini 2.5 Flash has a 1,048,576 token context window.

How much does Gemini 2.5 Flash cost?

On AIHubMix, Gemini 2.5 Flash costs $0.3 per million input tokens and $2.499 per million output tokens. Cached input reads are billed at $0.03 per million tokens.

What modalities does Gemini 2.5 Flash support?

Gemini 2.5 Flash accepts text, image, video, audio and PDF input. It returns text output.

What capabilities does Gemini 2.5 Flash support?

Gemini 2.5 Flash supports tool calling, function calling and structured outputs. Per-protocol parameter support is listed in the capability table on this page.

How do I call Gemini 2.5 Flash via API?

Gemini 2.5 Flash is available through the AIHubMix unified API. The API is OpenAI-compatible: point your OpenAI SDK at https://aihubmix.com/v1, use your AIHubMix API key, and set the model name to gemini-2.5-flash — no other code changes needed.

Who created Gemini 2.5 Flash?

Gemini 2.5 Flash is developed by Google. AIHubMix aggregates it alongside models from other providers behind one API and one bill.

When was Gemini 2.5 Flash released?

Gemini 2.5 Flash was released on June 17, 2025 by Google.

More models from Google

See all Google models →

Gemini 4 Neon

by Google

Gemini 4 Neon is the latest model in Google’s Gemini 4 series. It features frontier-level…

$3/1M in · $15/1M out
1,048,576 tokens context

Genie 4

by Google

Genie 4 is Google’s latest real-time interactive world generation model. Through the…

$1.5/1M in · $9/1M out

Gemini 4 Hydrogen

by Google

Gemini 4 Hydrogen is a Google Gemini 4 model focused on speed and efficiency. Potential…

$1.5/1M in · $7.5/1M out
1,048,576 tokens context

Gemini Decision 1

by Google

Gemini Decision 1 is designed for judgment and decision-making tasks, helping developers…

$0.1/1M in
262,144 tokens context

Gemini 3.8 Live

by Google

Gemini 3.8 Live is a multimodal AI model from Google that delivers a low-latency…

$3/1M in · $12/1M out

Gemini 2.5 Flash Live

by Google

Gemini 2.5 Flash Live is Google's multimodal AI model for real-time interactions…

$3/1M in · $12/1M out

Browse models available on AIHubMix — one interface for every major LLM.