Jahanzaib
Google: gemini-2.5-flash-preview-05-20Official docs

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

byGoogle
Official docs

gemini-2.5-flash-preview-05-20 is a reasoning model from Google released on May 20, 2025. It reads text, images, audio and video and writes text, with a 1.05M token context window and up to 66K tokens per reply.

Show more

It costs $0.1425 per million input tokens and $3.33 per million output tokens. Cached input bills at $0.0285, 80% less than fresh input.

It supports tool calling, structured JSON output and prompt caching.

Modalities
In / out price
$0.1425 / $3.33 per 1M
Context
1.05M
Max output
66K
Released
May 20, 2025
Knowledge cutoff
Jan 2025
  • Tool calling
  • Structured output
  • Reasoning
  • Prompt caching
  • Open weights
  • Free to use

gemini-2.5-flash-preview-05-20 pricing

USD, as listed on Oct 22, 2026. Most bills are input heavy, so the cached input rate matters as much as the headline price.

Input$0.1425 / 1M tokens
Output$3.33 / 1M tokens
Cached input (read)$0.0285 / 1M tokens

What gemini-2.5-flash-preview-05-20 costs per month

Pick a workload close to yours or type your own volumes.

gemini-2.5-flash-preview-05-20 per month
$40.47
Without caching
$45.60
Per request
$0.0013

Supported request parameters

What you can set when you call gemini-2.5-flash-preview-05-20 through an OpenAI compatible API.

  • Toolstools
  • Structured outputsstructured_outputs
  • Reasoningreasoning
  • Temperaturetemperature

Alternatives to gemini-2.5-flash-preview-05-20

Models that take the same inputs and call tools, closest in price, cheaper ones first.

  • Google: Gemini 3.5 Flash Lite

    Index 22.2

    Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 27 providers.

    by googleJul 21, 20261.05M context$0.30/M input tokens$2.50/M output tokens27 providers

  • Google: Gemini 2.5 Flash

    Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 25 providers.

    by googleJun 17, 2025$0.30/M input tokens$2.50/M output tokens25 providers

  • Google: Gemini Flash-Lite Latest

    Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 5 providers.

    by googleJul 21, 2026$0.30/M input tokens$2.50/M output tokens5 providers

  • Google: Gemini 3.1 Flash Lite

    Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 26 providers.

    by googleMar 3, 2026$0.25/M input tokens$1.50/M output tokens26 providers

  • Xiaomi: MiMo-V2.6-Pro

    Index 46.3

    Reads text, images, audio and video. Tool calling, structured output, reasoning. Served by 19 providers.

    by xiaomiSep 22, 20261.05M context$0.435/M input tokens$0.87/M output tokens19 providers

  • Xiaomi: MiMo V2 Omni

    Reads text, images, files, audio and video. Tool calling, reasoning.

    by xiaomiMar 18, 2026$0.40/M input tokens$2/M output tokens

More from Google

  • Gemini 4 Argon

    Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 21 providers.

    by googleOct 13, 2026$2/M input tokens$10/M output tokens21 providers

  • Nano Banana 2.1

    Image

    Generates images from text and images. Served by 4 providers.

    by googleOct 6, 2026$1.50/M input tokens$7.50/M output tokens4 providers

  • Gemini 3.8 Flash-Lite TTS

    Speech

    Turns text into spoken audio.

    by googleSep 22, 2026$0.50/M input tokens$6/M output tokens

  • Gemini 3.8 Flash TTS

    Speech

    Turns text into spoken audio.

    by googleSep 22, 2026$0.50/M input tokens$9/M output tokens

  • Gemma 4 26B A4B Cybersecurity

    Reads text and images. Tool calling, reasoning.

    by googleSep 19, 2026$0.1056/M input tokens$0.3344/M output tokens

  • Gemma 4 31B Split-Untied

    Reads text. Tool calling.

    by googleSep 17, 2026$0.10/M input tokens$0.30/M output tokens

All Google models

gemini-2.5-flash-preview-05-20 questions

How much does the gemini-2.5-flash-preview-05-20 API cost?

$0.1425 per million input tokens and $3.33 per million output tokens, with cached input at $0.0285. The estimator on this page turns that into a monthly bill for your own workload.

What is the context window of gemini-2.5-flash-preview-05-20?

1,048,576 tokens of input, and it can write up to 65,536 tokens in one reply. As a rough guide, a million tokens is around 750,000 English words.

Does gemini-2.5-flash-preview-05-20 support tool calling?

Yes. It accepts tool definitions and can return JSON that matches a schema, which is what an agent needs to call your APIs.

Is gemini-2.5-flash-preview-05-20 open source?

No. Google serves it through an API only, so you cannot download the weights or host it yourself.

When was gemini-2.5-flash-preview-05-20 released?

May 20, 2025, with training data up to Jan 2025.

Catalog data from models.dev (MIT licensed), refreshed daily, last on Oct 22, 2026. The summary is written from these facts.