Where is the Gemini 2.5 Flash documentation?

The Gemini 2.5 Flash documentation on OpenRouter includes the Gemini 2.5 Flash API - Pricing, Quickstart & Provider Comparison blog post. The quickstart covers API keys and your first request, and the API reference lists every parameter.

How much does Gemini 2.5 Flash cost?

Gemini 2.5 Flash costs $0.30/M input tokens and $2.50/M output tokens, with separate rates for Cache Read at $0.03/M tokens, Cache Write at $0.08333/M tokens, Image Input at $0.30/M tokens, Input Audio at $1.00/M tokens, and Input Audio Cache at $0.10/M tokens.

What is the context length of Gemini 2.5 Flash?

Gemini 2.5 Flash has a 1,048,576 token context window. It supports up to 65,535 completion tokens.

Does Gemini 2.5 Flash support tool calling and structured outputs?

Yes. Gemini 2.5 Flash accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.

What inputs and outputs does Gemini 2.5 Flash support?

Gemini 2.5 Flash accepts files such as PDFs, images, text, audio, and video as input and returns text.

Which providers serve Gemini 2.5 Flash?

Gemini 2.5 Flash is served by 1 provider on OpenRouter: Google AI Studio.

What other text models does Google have?

Gemini 4 Hydrogen, Gemini Decision 1, Gemini 4 Carbon and 31 more are other text models from Google.

When was Gemini 2.5 Flash released?

Gemini 2.5 Flash was released on June 17, 2025. Its knowledge cutoff is January 31, 2025.

Google: Gemini 2.5 Flash

google/gemini-2.5-flash

Compare

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).

Modalities

In / out price

$0.30 / $2.50per 1M

Context

1.0M

Released

Jun 17, 2025

Knowledge cutoff

Jan 2025

Providers

Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick: Balanced (price + speed), Nitro (fastest), or Floor (cheapest).

Latency / throughput


	$0.30	$2.50	$0.03	$0.10	0.54s	100 tok/s	100.00%
Not used in Standard routing:Why these endpoints are not used
Flex	$0.15	$1.25	$0.015	$0.05	1.09s	94 tok/s	99.88%
Priority	$0.54	$4.50	$0.054	$0.18	0.44s	115 tok/s	92.51%

Input $0.30Output $2.50
100 tok/s100.00% uptime
Not used in Standard routing:Why these endpoints are not used
Input $0.15Output $1.25
Flex
94 tok/s99.88% uptime
Input $0.54Output $4.50
Priority
115 tok/s92.51% uptime

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Weighted average

Input

$0.1898/M tokens

Output

$2.494/M tokens

Gemini 2.5 Flash — Price history

Price history

No effective price data for this selection

		$0.190	$2.50	43.4%	99.2%
Not used in Standard routing:Why these endpoints are not used
	Flex	$0.111	$1.25	34.7%	0.7%
	Priority	$0.452	$4.50	18.1%	0.2%

Effective in $0.190Effective out $2.50
Token share
99.2%
Not used in Standard routing:Why these endpoints are not used
Effective in $0.111Effective out $1.25
FlexToken share
0.7%
Effective in $0.452Effective out $4.50
PriorityToken share
0.2%

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Uptime (3d)

100.00%

Availability (3d)

98.87%

Availability over the last 3 days

Last 72 hours

Availability 98.87%

3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability

98.82%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.

Benchmarks

Scores on standardized evaluations and this model’s own outputs on shared benchmark prompts. Higher percentages are better — and each rank shows where this model lands among the models evaluated on that source.

Benchmark score summary for Google: Gemini 2.5 Flash (Artificial Analysis, Design Arena and Vals AI)
Source	Benchmark	Score
Artificial Analysis	Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning) GPQA Diamond	76.6%
Artificial Analysis	Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning) HLE	8.7%
Artificial Analysis	Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning) IFBench	43.5%
Artificial Analysis	Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning) τ²-Bench Telecom	28.4%
Artificial Analysis	Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning) AA-LCR	60.0%
Artificial Analysis	Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning) CritPt	0.0%
Artificial Analysis	Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning) LiveCodeBench	62.5%
Artificial Analysis	Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning) Terminal-Bench Hard	14.4%
Artificial Analysis	Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning) MMLU-Pro	83.6%
Artificial Analysis	Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning) AIME 2025	56.7%
Artificial Analysis	Gemini 2.5 Flash Preview (Non-reasoning) GPQA Diamond	59.4%
Artificial Analysis	Gemini 2.5 Flash Preview (Non-reasoning) HLE	3.8%
Artificial Analysis	Gemini 2.5 Flash Preview (Non-reasoning) LiveCodeBench	40.6%
Artificial Analysis	Gemini 2.5 Flash Preview (Non-reasoning) MMLU-Pro	78.3%
Artificial Analysis	Gemini 2.5 Flash Preview (Non-reasoning) AIME	43.3%
Artificial Analysis	Gemini 2.5 Flash Preview (Non-reasoning) MATH-500	92.6%
Artificial Analysis	Gemini 2.5 Flash (Non-reasoning) GPQA Diamond	68.3%
Artificial Analysis	Gemini 2.5 Flash (Non-reasoning) HLE	4.7%
Artificial Analysis	Gemini 2.5 Flash (Non-reasoning) IFBench	39.0%
Artificial Analysis	Gemini 2.5 Flash (Non-reasoning) τ²-Bench Telecom	14.9%
Artificial Analysis	Gemini 2.5 Flash (Non-reasoning) AA-LCR	49.9%
Artificial Analysis	Gemini 2.5 Flash (Non-reasoning) CritPt	1.4%
Artificial Analysis	Gemini 2.5 Flash (Non-reasoning) LiveCodeBench	49.5%
Artificial Analysis	Gemini 2.5 Flash (Non-reasoning) Terminal-Bench Hard	12.1%
Artificial Analysis	Gemini 2.5 Flash (Non-reasoning) MMLU-Pro	80.9%
Artificial Analysis	Gemini 2.5 Flash (Non-reasoning) AIME 2025	60.3%
Artificial Analysis	Gemini 2.5 Flash (Non-reasoning) AIME	50.0%
Artificial Analysis	Gemini 2.5 Flash (Non-reasoning) MATH-500	93.2%
Artificial Analysis	Gemini 2.5 Flash (Reasoning) GPQA Diamond	79.0%
Artificial Analysis	Gemini 2.5 Flash (Reasoning) HLE	12.1%
Artificial Analysis	Gemini 2.5 Flash (Reasoning) IFBench	50.3%
Artificial Analysis	Gemini 2.5 Flash (Reasoning) τ²-Bench Telecom	31.6%
Artificial Analysis	Gemini 2.5 Flash (Reasoning) AA-LCR	65.3%
Artificial Analysis	Gemini 2.5 Flash (Reasoning) CritPt	1.1%
Artificial Analysis	Gemini 2.5 Flash (Reasoning) LiveCodeBench	69.5%
Artificial Analysis	Gemini 2.5 Flash (Reasoning) Terminal-Bench Hard	13.6%
Artificial Analysis	Gemini 2.5 Flash (Reasoning) MMLU-Pro	83.2%
Artificial Analysis	Gemini 2.5 Flash (Reasoning) AIME 2025	73.3%
Artificial Analysis	Gemini 2.5 Flash (Reasoning) AIME	82.3%
Artificial Analysis	Gemini 2.5 Flash (Reasoning) MATH-500	98.1%
Artificial Analysis	Gemini 2.5 Flash Preview (Sep '25) (Reasoning) GPQA Diamond	79.3%
Artificial Analysis	Gemini 2.5 Flash Preview (Sep '25) (Reasoning) HLE	13.8%
Artificial Analysis	Gemini 2.5 Flash Preview (Sep '25) (Reasoning) IFBench	52.3%
Artificial Analysis	Gemini 2.5 Flash Preview (Sep '25) (Reasoning) τ²-Bench Telecom	45.6%
Artificial Analysis	Gemini 2.5 Flash Preview (Sep '25) (Reasoning) AA-LCR	71.0%
Artificial Analysis	Gemini 2.5 Flash Preview (Sep '25) (Reasoning) CritPt	0.3%
Artificial Analysis	Gemini 2.5 Flash Preview (Sep '25) (Reasoning) LiveCodeBench	71.3%
Artificial Analysis	Gemini 2.5 Flash Preview (Sep '25) (Reasoning) Terminal-Bench Hard	16.7%
Artificial Analysis	Gemini 2.5 Flash Preview (Sep '25) (Reasoning) MMLU-Pro	84.2%
Artificial Analysis	Gemini 2.5 Flash Preview (Sep '25) (Reasoning) AIME 2025	78.3%
Artificial Analysis	Gemini 2.5 Flash Preview (Reasoning) GPQA Diamond	69.8%
Artificial Analysis	Gemini 2.5 Flash Preview (Reasoning) HLE	12.1%
Artificial Analysis	Gemini 2.5 Flash Preview (Reasoning) LiveCodeBench	50.5%
Artificial Analysis	Gemini 2.5 Flash Preview (Reasoning) MMLU-Pro	80.0%
Artificial Analysis	Gemini 2.5 Flash Preview (Reasoning) AIME	84.3%
Artificial Analysis	Gemini 2.5 Flash Preview (Reasoning) MATH-500	98.1%
Design Arena	Gemini 2.5 Flash Preview 09-2025 Models Arena 3D Elo	1051
Design Arena	Gemini 2.5 Flash Preview 09-2025 Models Arena Code Categories Elo	1093
Design Arena	Gemini 2.5 Flash Preview 09-2025 Models Arena Data Visualization Elo	1131
Design Arena	Gemini 2.5 Flash Preview 09-2025 Models Arena Game Development Elo	1055
Design Arena	Gemini 2.5 Flash Preview 09-2025 Models Arena SVG Elo	1009
Design Arena	Gemini 2.5 Flash Preview 09-2025 Models Arena UI Component Elo	1083
Design Arena	Gemini 2.5 Flash Preview 09-2025 Models Arena Website Elo	1107
Vals AI	Gemini 2.5 Flash (7/17) (Nonthinking) IOI v1	2.6%
Vals AI	Gemini 2.5 Flash (7/17) (Nonthinking) MedCode	38.4%
Vals AI	Gemini 2.5 Flash (7/17) (Nonthinking) MedScribe	82.9%
Vals AI	Gemini 2.5 Flash (7/17) (Nonthinking) SAGE v1	44.8%

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

KoalaBear

new

50.9Btokens

OpenClaw

OpenClaw is an open-source AI agent that connects to your messaging apps and takes real actions on your behalf, from running commands and browsing the web to managing files and sending emails.

24.4Btokens

Hermes Agent

Hermes Agent is an open-source, self-improving AI agent by Nous Research that runs persistently with memory across sessions, and builds reusable skills from experience. It comes with 40+ built-in tools, including web search, browser automation, and vision, plus scheduled automations and subagents.

23.5Btokens

Senuto Brand Intelligence

new

5.47Btokens

OP.GG

new

5.43Btokens

Rest of OpenRouter

15.3B

Top 5 Apps

2.29B

Not currently available through EU in-region routing. In-region routing docs

More models from Google

Gemini 4 Hydrogen

Gemini 4 Hydrogen is the high-efficiency workhorse model of the Gemini 4 family from Google, built for high-throughput agentic workflows, coding and multi-model routing at lower cost and latency than Gemini 4 Carbon. It takes text, image, audio, video and file input, supports long decode of up to 1M output tokens through continuation, and controls thinking depth with low, medium, high and xhigh reasoning effort.

Text1.0M context$1.50 / $7.50

Gemini 4 Hydrogen (batch)

Text1.0M context$0.75 / $3.75

Gemini Decision 1

Gemini Decision 1 is Google's model for the Decisions API. It answers structured questions about an input state (true/false, multiple choice with up to 255 options, and score with up to 255 levels) and returns a confidence for every answer, plus a legend and probabilities for score questions.

It reads text, images, audio, video, and documents (PDF, CSV, and Office files) sent inline as base64 or by public URL. Every question needs instructions.

Decisions$0.10 / $0

Gemini 4 Carbon

Gemini 4 Carbon is a frontier Gemini 4 model from Google for coding, agentic and complex reasoning work. It takes text, image, audio, video and file input, supports long decode of up to 1M output tokens through continuation, and controls thinking depth with low, medium and high reasoning effort.

Text1.0M context$2 / $10

Gemini 4 Carbon (batch)

Text1.0M context$1 / $5

Gemini Omni 1.2 Flash

Gemini Omni 1.2 Flash is Google's native multimodal video generation and editing model, the successor to Gemini Omni 1.1 Flash. It generates clips up to 15 seconds long with native audio in 16:9 or 9:16, from 360p drafts up to 4K, and supports text-to-video, image-to-video, first and last frame interpolation, subject and video references with improved reference management, and editing or extending an uploaded video. Multi-turn editing and extension of a prior generation is supported through previous_job_id.

Note: video generation is only supported through the Video Generation API. See the guide: https://openrouter.ai/docs/guides/overview/multimodal/video-generation

Text131K context$1.50 / $9

Gemini Omni 1.1 Flash

Gemini Omni 1.1 Flash is Google's native multimodal video generation and editing model, the generally available successor to Gemini Omni Flash Preview. It is suited for text-to-video, image-to-video, first and last frame interpolation, subject and video references (up to three reference clips), and editing or extending an uploaded video, and generates clips from 360p drafts up to 4K with native audio in 16:9 or 9:16. Multi-turn editing and extension of a prior generation is supported through previous_job_id, up to 40 seconds of total video.

Note: video generation is only supported through the Video Generation API. See the guide: https://openrouter.ai/docs/guides/overview/multimodal/video-generation

Text131K context$1.50 / $9

Gemini 4 Argon

Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across long, multi-step tasks and to turn long documents mixing text, tables, charts and images into a single grounded output. It leads the Vals Index across finance, legal, coding and tax work, and supports long decode of up to 1M output tokens in a single response.

Text1.0M context$2 / $10

Gemini 4 Argon (batch)

Text1.0M context$1 / $5

Nano Banana 2.1

Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pro. It improves product recontextualization, mask- and ink-based editing, and factual accuracy, and renders photorealistic skin tones, detailed materials, lighting, and coherent backgrounds. It accepts text and image inputs, returns images with optional text, and supports 1K, 2K, and 4K output plus extended aspect ratios via the image_config API Parameter.

Image66K context$1.50 / $30

Gemini 3.5 Transcribe

Gemini 3.5 Transcribe is a speech-to-text model from Google. It is suited for synchronous transcription that needs word-level timestamps or speaker diarization, with support for up to eight speakers. Audio can be up to one hour, or 30 minutes when timestamps or diarization are enabled.

Transcription$2 / $12

Gemini 3.8 Flash Lite TTS

Gemini 3.8 Flash Lite TTS is a text-to-speech model from Google and the fast, high-throughput member of the 3.8 TTS family alongside Gemini 3.8 Flash TTS. It is suited for conversational voice-agent pipelines, high-volume read-aloud, and voice replication workloads where latency and cost matter more than maximum expressiveness.

It accepts the same speech configuration as Gemini 3.1 Flash TTS Preview, including the 30 prebuilt studio voices, and supports Google's Voice Design and Voice Replication through voice_... identifiers.

Speech$0.50 / $6

Gemini 3.8 Flash TTS

Gemini 3.8 Flash TTS is a text-to-speech model from Google and the successor to Gemini 3.1 Flash TTS Preview. It is the creative tier of the 3.8 TTS family, suited for narration, character work, and multi-speaker dialogue where voice fidelity, acting nuance, and regional dialect coverage matter more than latency.

It accepts the same speech configuration as its predecessor, including the 30 prebuilt studio voices, and supports Google's Voice Design (custom voices from a text description) and Voice Replication (voices cloned from a short sample) through voice_... identifiers.

Speech$0.50 / $9

Gemini 3.8 Flash

Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.

Text1.0M context$0.75 / $3.75

Gemini 3.8 Flash (batch)

Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.

Text1.0M context$0.375 / $1.875

Gemini 3.7 Flash

Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step problem solving.

Text1.0M context$0.75 / $3.75

Gemini 3.7 Flash (batch)

Text1.0M context$0.375 / $1.875

Gemini 3.6 Flash

Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and less hedging, while reducing token use and the number of model calls needed to complete a task.

Text1.0M context$0.75 / $3.75

Gemini 3.6 Flash (batch)

Text1.0M context$0.375 / $1.875

Gemini 3.5 Flash Lite

Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.

Text1.0M context$0.30 / $2.50

Google: Gemini 2.5 Flash

Providers