Home/Models
Models/Google

Gemini 2.5 Flash-Lite

Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance across common benchmarks compared to earlier Flash models. By default, "thinking" (i.e. multi-pass reasoning) is disabled to prioritize speed, but developers can enable it via the Reasoning API parameter to selectively trade off cost for intelligence.

google/gemini-2.5-flash-lite
Organization
Google
Family
gemini-flash-lite
Providers
19
Context
1,048,576
Output limit
65,536
Knowledge
2025-01
Release
2025-06-17
Updated
2025-06-17
Weights
Closed
Input
text, image, audio, video, pdf
Output
text
Capabilities
Tools, Reasoning, Structured, Temperature

Providers

Compare every cataloged offer for this model, including its provider, route, token limits, price, and capabilities.

24 offers · USD per million tokens
ProviderModel IDContextOutputInput / output · 1MReasoningToolsStructuredDetails
AIHubMix
gemini-2.5-flash-lite
1,048,57665,536$0.10 / $0.40YesYesYes
View
AnyAPI
google/gemini-2.5-flash-lite
1,048,57665,536— / —YesYesYes
View
CrossModel
gemini/gemini-2.5-flash-lite
1,048,57665,536$0.10 / $0.40YesYesYes
View
DevPass (LLM Gateway)
gemini-2.5-flash-lite
1,048,57665,536$0.10 / $0.40YesYesYes
View
Impossibl
google/gemini-2.5-flash-lite
1,048,57665,536$0.10 / $0.40YesYesYes
View
Kenari
gemini-2-5-flash-lite
1,048,57665,536$0.00 / $0.00YesYesYes
View
Kilo Gateway
google/gemini-2.5-flash-lite
1,048,57665,535$0.10 / $0.40YesYesYes
View
LLM Gateway
google-vertex/gemini-2.5-flash-lite
1,048,57665,535$0.10 / $0.40NoYesYes
View
LLM Gateway
google-ai-studio/gemini-2.5-flash-lite
1,048,57665,535$0.10 / $0.40NoYesYes
View
LLMTR
google/gemini-2.5-flash-lite
1,048,57665,536$0.10 / $0.10YesYesYes
View
Merge Gateway
google/gemini-2.5-flash-lite
1,000,00065,536$0.10 / $0.40YesYesYes
View
NanoGPT
gemini-2.5-flash-lite
1,048,57665,536$0.10 / $0.40YesYesNo
View
NEAR AI Cloud
google/gemini-2.5-flash-lite
1,048,57665,536$0.10 / $0.40YesYesYes
View
Ofox
google/gemini-2.5-flash-lite
1,048,57665,536$0.10 / $0.40YesYesYes
View
Googlevia OpenRouter
google/gemini-2.5-flash-lite
unknown		1,048,57665,535$0.10 / $0.40YesYesYes
View
Googlevia OpenRouter
google/gemini-2.5-flash-lite
unknown		1,048,57665,535$0.10 / $0.40YesYesYes
View
Google AI Studiovia OpenRouter
google/gemini-2.5-flash-lite
unknown		1,048,57665,535$0.10 / $0.40YesYesYes
View
Google AI Studiovia OpenRouter
google/gemini-2.5-flash-lite
unknown		1,048,57665,535$0.05 / $0.20YesYesYes
View
Google AI Studiovia OpenRouter
google/gemini-2.5-flash-lite
unknown		1,048,57665,535$0.18 / $0.72YesYesYes
View
OrcaRouter
google/gemini-2.5-flash-lite
1,048,57665,536$0.10 / $0.40YesYesYes
View
Requesty
gemini-2.5-flash-lite@eu
1,048,57665,535$0.10 / $0.40YesYesYes
View
SAP AI Core
gemini-2.5-flash-lite
1,048,57665,536$0.10 / $0.40YesYesYes
View
Vercel AI Gateway
google/gemini-2.5-flash-lite
1,048,57665,535$0.10 / $0.40YesYesYes
View
Vertex
gemini-2.5-flash-lite
1,048,57665,535$0.10 / $0.40YesYes—
View

Prices and limits apply to each offer. A dash means the value is not provided. OpenRouter offers show the hosting provider and routing channel separately.

Pricing

Compare token rates and cache charges across available routes and hosting configurations.

USD per million tokens
Input from$0.00Per 1M input tokens
Output from$0.00Per 1M output tokens
Available offers24Across 19 providers

Lowest listed input and output prices across the offers above; they may belong to different providers. These are base rates, before conditional pricing, discounts or additional fees.

Endpoint price comparisonLatest observed snapshot · 5 lowest-priced configurations
InputOutput
Google AI Studiogoogle-ai-studio/flex
$0.05$0.20
Googlegoogle-vertex/eu
$0.10$0.40
Googlegoogle-vertex
$0.10$0.40
Google AI Studiogoogle-ai-studio
$0.10$0.40
Google AI Studiogoogle-ai-studio/priority
$0.18$0.72
google/gemini-2.5-flash-liteObserved
Input
$0.10
Output
$0.40
Cache read
$0.01
Cache write
$0.083333
Additional fees and pricing conditions
audio
$0.0000003 / audio token
image
$0.0000001 / image
web search
$0.014 / search
input audio cache
$0.00000003 / audio token
internal reasoning
$0.0000004 / reasoning token
Hosting prices through OpenRouter All endpoints and cache rates
EndpointInput / 1MOutput / 1MCache read / 1MCache write / 1M
Googlegoogle-vertex/eu$0.10$0.40$0.01$0.083333
Googlegoogle-vertex$0.10$0.40$0.01$0.083333
Google AI Studiogoogle-ai-studio$0.10$0.40$0.01$0.083333
Google AI Studiogoogle-ai-studio/flex$0.05$0.20$0.005$0.041667
Google AI Studiogoogle-ai-studio/priority$0.18$0.72$0.018$0.15

Each row is a hosting configuration. Open an offer in Providers for its full pricing conditions and additional fees. Endpoint observations may differ from the routing catalog's base price.

Performance

Review reported latency and output-throughput percentiles from the latest observed rolling window.

Latest 30-minute observation

Time to first token · milliseconds

Latency distributionRolling 30-minute snapshot · 4 endpoints
P50P75P90P99
Googlegoogle-vertex/eu
565–4,169.44 ms
Googlegoogle-vertex
1,124.5–4,765.18 ms
Google AI Studiogoogle-ai-studio
487–5,235.17 ms
Google AI Studiogoogle-ai-studio/flex
334–7,551.77 ms
All latency percentiles 4 endpoints
EndpointP50P75P90P99
Googlegoogle-vertex/eu565 ms777 ms1,519.9 ms4,169.44 ms
Googlegoogle-vertex1,124.5 ms1,571.25 ms2,705.9 ms4,765.18 ms
Google AI Studiogoogle-ai-studio487 ms675 ms1,327.9 ms5,235.17 ms
Google AI Studiogoogle-ai-studio/flex334 ms571.5 ms880 ms7,551.77 ms

Output throughput · tokens per second

Throughput distributionRolling 30-minute snapshot · 4 endpoints
P50P75P90P99
Googlegoogle-vertex/eu
170–464 t/s
Googlegoogle-vertex
95–405 t/s
Google AI Studiogoogle-ai-studio
251–547 t/s
Google AI Studiogoogle-ai-studio/flex
165–444.29 t/s
All throughput percentiles 4 endpoints
EndpointP50P75P90P99
Googlegoogle-vertex/eu170 t/s243 t/s341 t/s464 t/s
Googlegoogle-vertex95 t/s172 t/s243 t/s405 t/s
Google AI Studiogoogle-ai-studio251 t/s343 t/s444 t/s547 t/s
Google AI Studiogoogle-ai-studio/flex165 t/s280.25 t/s357.4 t/s444.29 t/s

Percentiles describe the observed request distribution. These are snapshots of a rolling window, not a historical time series.

Uptime

Compare successful request rates across the latest 5-minute, 30-minute, and 24-hour observations.

Successful requests by window
Availability by endpointCurrent overlapping windows · 5 endpoints
Endpoint5 minutes30 minutes24 hours
Googlegoogle-vertex/eu
Googlegoogle-vertex
Google AI Studiogoogle-ai-studio
Google AI Studiogoogle-ai-studio/flex
Google AI Studiogoogle-ai-studio/priority

Reported by OpenRouter at the time of collection; rate-limited requests are excluded. A dash means no measurement was reported. This is not a live availability check.

Benchmarks

Review attributed evaluation results on each source's original scale.

External evaluations

Sources: Artificial Analysis and Design Arena, via OpenRouter. Scores retain their original scales and are not OpenAI Suite ratings.

Detailed evaluations

Evaluation scoresAccuracy or item F1 · higher is better
gpqa diamondGoogle: Gemini 2.5 Flash Lite
54.882%
tau bench verified airlineGoogle: Gemini 2.5 Flash Lite
50.337%
EvaluationConfigurationSourceResultsDetails
gpqa diamondGoogle: Gemini 2.5 Flash Litegoogle/gemini-2.5-flash-liteOpenRouter54.882%
Details
tau bench verified airlineGoogle: Gemini 2.5 Flash Litegoogle/gemini-2.5-flash-liteOpenRouter50.337%
Details

Sources: Artificial Analysis, Design Arena and OpenRouter. Evaluation configurations and scales differ; results are not interchangeable. Updated Oct 4, 2026.

Apps & session costs

Compare observed median session costs for applications using this model, grouped by conversation length.

30-day sample · through Sep 27, 2026
ApplicationModel routeTurnsMedian cost / sessionDetails
Hermes Agentgoogle/gemini-2.5-flash-lite10–49 turns
$0.020038
Details
Hermes Agentgoogle/gemini-2.5-flash-lite2–9 turns
$0.003633
Details
Hermes Agentgoogle/gemini-2.5-flash-lite50+ turns
$0.118428
Details
Hermes Agentgoogle/gemini-2.5-flash-lite1 turn
$0.000305
Details

Source: OpenRouter, as of Oct 2, 2026. Published under CC BY 4.0. These are observed costs per session, not token prices or a forecast for your workload. Apps are compared separately.

Activity

Daily prompt and completion tokens reported for this model's routes in OpenRouter's top 50. Missing days have no published value.

Last 90 complete UTC days
Daily token usage8,804,558,059,187 reported tokens · 89 days with observations
Jul 6, 2026Oct 3, 2026
Daily observations · 89 days
Date (UTC)Reported tokensReported routes
Oct 3, 202673,890,189,8151
Oct 2, 202692,174,544,3641
Oct 1, 2026102,006,037,0591
Sep 30, 2026105,251,361,3651
Sep 29, 2026112,434,896,1031
Sep 28, 2026105,358,397,2981
Sep 27, 202689,955,852,2851
Sep 26, 202699,050,965,6581
Sep 25, 2026108,300,129,0631
Sep 24, 2026104,209,598,5641
Sep 23, 2026100,908,837,4421
Sep 22, 202698,043,846,7661
Sep 21, 202696,348,495,5471
Sep 20, 202680,620,236,8151
Sep 19, 2026104,211,878,1831
Sep 18, 202691,722,304,3801
Sep 17, 2026101,482,460,3681
Sep 16, 202699,841,312,2511
Sep 15, 2026102,523,689,9371
Sep 14, 2026105,022,357,0401
Sep 13, 2026110,404,178,2921
Sep 12, 202690,543,739,4261
Sep 11, 2026107,348,184,2181
Sep 10, 2026108,118,682,4031
Sep 9, 2026124,962,878,1371
Sep 8, 2026106,626,561,9441
Sep 7, 2026105,320,186,1891
Sep 6, 202696,818,867,5681
Sep 5, 202693,988,850,5161
Sep 4, 2026102,797,355,0361
Sep 3, 2026103,533,250,7651
Sep 2, 202699,621,512,0641
Sep 1, 202693,380,451,9581
Aug 31, 2026115,243,737,9271
Aug 30, 2026154,340,362,2151
Aug 29, 2026131,830,298,0841
Aug 28, 2026138,291,026,8521
Aug 27, 2026149,696,920,3891
Aug 26, 2026147,073,763,2231
Aug 25, 2026116,549,610,5971
Aug 24, 2026115,798,847,9341
Aug 23, 202688,136,436,9531
Aug 22, 202688,867,416,4171
Aug 21, 202699,991,870,2191
Aug 20, 2026110,265,864,3891
Aug 19, 2026114,564,689,3601
Aug 18, 2026112,866,555,2191
Aug 17, 2026101,035,974,3701
Aug 16, 202686,149,525,2011
Aug 15, 202687,188,493,6541
Aug 14, 2026101,950,258,0331
Aug 13, 2026104,681,243,2141
Aug 12, 2026116,633,149,9481
Aug 11, 2026119,223,100,2591
Aug 10, 202696,498,770,4481
Aug 9, 202680,094,522,7001
Aug 8, 202676,530,482,9601
Aug 7, 202684,011,767,3741
Aug 6, 2026101,332,793,2181
Aug 5, 202696,684,467,0911
Aug 4, 202692,040,390,5851
Aug 3, 202687,924,218,6821
Aug 2, 202674,874,145,3661
Aug 1, 202674,226,786,8991
Jul 31, 202684,631,625,6621
Jul 30, 202693,490,264,3031
Jul 29, 2026117,391,949,6421
Jul 28, 2026108,856,906,6241
Jul 27, 202699,931,399,0531
Jul 26, 202688,198,462,3001
Jul 25, 202675,564,282,0671
Jul 24, 2026119,874,846,2691
Jul 23, 2026116,121,863,8641
Jul 22, 202686,774,656,2511
Jul 21, 202691,549,179,0621
Jul 20, 202687,007,755,3391
Jul 19, 202670,762,199,6141
Jul 18, 202673,591,298,9281
Jul 17, 202679,211,108,1131
Jul 16, 202683,094,330,8291
Jul 15, 202685,171,256,1381
Jul 14, 202693,494,400,8211
Jul 13, 202688,575,295,7171
Jul 12, 202663,455,432,5851
Jul 11, 202664,444,665,7131
Jul 10, 202677,866,716,9851
Jul 9, 202689,019,998,9881
Jul 8, 2026106,805,487,0211
Jul 7, 202678,253,098,7001

Source: OpenRouter (openrouter.ai/rankings), as of Oct 4, 2026. CC BY 4.0. Totals include only individually published routes. Tokenizers differ by provider; the aggregated “other” category is never assigned to a model.

Technical details & API

Explore specifications, supported parameters, reasoning controls, and API identifiers for each OpenRouter route.

Current route specifications
google/gemini-2.5-flash-liteObserved
Context
1,048,576
Maximum output
65,535
Tokenizer
Gemini
Input
text, image, file, audio, video
Output
text
Moderation
No
Knowledge cutoff
2025-01-31
Retirement
2026-10-20
Added to OpenRouter
2025-07-22
Base URLhttps://openrouter.ai/api/v1
Model IDgoogle/gemini-2.5-flash-lite
Version IDgoogle/gemini-2.5-flash-lite

Reasoning

Required
No
Enabled by default
Not reported
Default effort
—
Supported efforts
—

Supported parameters

  • include_reasoning
  • max_tokens
  • reasoning
  • response_format
  • seed
  • stop
  • structured_outputs
  • temperature
  • tool_choice
  • tools
  • top_p

Frequently asked questions

Answers based on the model metadata and serving offers currently in the catalog.

How much does Gemini 2.5 Flash-Lite cost?

Listed rates start at $0.00 per million input tokens and $0.00 per million output tokens. Prices vary by provider and configuration; see Pricing for details.

Which providers offer Gemini 2.5 Flash-Lite?

There are 24 cataloged offers across 19 providers. Compare model IDs, prices and limits in Providers.

What is the context window?

The cataloged model context is 1,048,576 tokens. Each serving endpoint may apply a different limit.

Does it support tools and structured output?

Tool calling: Yes. Structured output: Yes. Support can vary by endpoint.

Catalog history · 2 recorded revisions

Metadata observations since this model was first cataloged. These are not model release versions.

  • · 030f3859e140
  • · 7de810d5262b