Inference
EN
Google

Gemini 2.5 Flash

Gemini 2.5 Flash is a standard model from Google. 13 benchmarks count toward its index, in 7 categories.

  • Closed weights
  • Standard
  • Input: file · image · text · audio · video
  • Released 2025-06
RankedEnough results for an index.
IndexAll categories, out of 100.35.0±5.0Median 51.0
CoverageIndex weight that has results.95%
SpeedOutput tokens per second.95/sMedian 67/s
First tokenSeconds to the first output token.0.6 sMedian 1.3 s
Input / 1MUS dollars per 1M input tokens.$0.30batch $0.15Median $0.60
Output / 1MUS dollars per 1M output tokens.$2.50batch $1.25 Batch price per 1M output tokens.Median $2.55
ContextMaximum tokens in one request.1.05MMedian 262K
EloLMArena rating and rank.1417±2 #129Median 1422

Details

From OpenRouter
API IDThe model ID on OpenRouter.
google/gemini-2.5-flash
Max outputMaximum output tokens per request.
66K
Knowledge cutoffLast date of training data.
31 Jan 2025
ToolsTool calls on OpenRouter.
Yes
JSON outputOutput follows a given JSON schema.
Yes
Cache read / 1MUS dollars per 1M cached tokens.
$0.03
WeightsLink to the published weights.
—
RetiresDate OpenRouter removes the model.
—

Where to run

APIs that serve this model.
4 providers
ProviderTypeMaker, cloud, host or router.InputOutputContext
DatabricksDeprecatedCloud$0.30$2.501.05M
Google AI StudioMaker$0.30$2.501.05M
OpenRouterDeprecatedRouter$0.30$2.501.05M
SAP AI CoreDeprecatedCloud$0.30$2.501.05M

US dollars per 1M tokens, list price. From models.dev (opens in a new tab) (MIT).

Capabilities

Index per category, out of 100.
Out of 100
AgenticMulti-step tasks with tools.1 counted12.7—
CodingCode writing and repair.2 counted31.9196 / 209
ReasoningLogic problems and puzzles.2 counted40.5157 / 227
MultimodalTasks with images and text.1 counted40.4—
KnowledgeFacts and expert knowledge.3 counted37.5211 / 268
MultilingualTasks in many languages.None counted——
InstructionTasks with strict prompt rules.1 counted25.5—
MathMath problems.3 counted44.1109 / 168

Results

13 counted
BenchmarkThe benchmark name.ResultThe score from the source.PlacePlace among results on this benchmark.
FrontierMath-Tier-4-2025-07-01-PrivateMath4.2% ±2.926 / 55
OTIS Mock AIME 2024-2025Math71.9% ±5.597 / 200
Critical Physics TasksReasoning1.4%113 / 214
Artificial Analysis Omniscience AccuracyKnowledge26.1%98 / 164
FrontierMath-2025-02-28-PrivateMath4.8% ±1.346 / 69
Artificial Analysis GPQA DiamondKnowledge68.3%135 / 199
Artificial Analysis MMMU-ProMultimodal65.5%81 / 113
SWE-bench Verified · swebench.comCoding28.7%33 / 46
Artificial Analysis Long Context ReasoningReasoning49.9%156 / 217
Artificial Analysis IFBenchInstruction39.0%108 / 146
Artificial Analysis Humanity's Last ExamKnowledge4.7%183 / 222
SWE-bench Verified · SWE-bench/experimentsCoding28.7%55 / 65
IOI v1Coding2.6% ±1.054 / 61
τ²-Bench Tool-Agent-User EvaluationAgentic14.9%140 / 149
MedScribeHealthcare82.9% ±1.950 / 109
MedCodeHealthcare38.4% ±1.971 / 106

Sources

BenchLMCC BY-NC 4.0OpenRouterTerms restrict reuseEpoch AICC BYSWE-bench teamNo licence statedVals AINo licence statedmodels.devMIT

History

5 releases
Index35.8 → 35.0
23 Oct 202612 Nov 2026
Output / 1M$2.50 → $2.50
23 Oct 202612 Nov 2026

Questions

How much does Gemini 2.5 Flash cost?
$0.30 per 1M input tokens, $2.50 per 1M output tokens.
How good is Gemini 2.5 Flash?
Its index is 35.0 out of 100. That is place 235 of 283 ranked models.
What is Gemini 2.5 Flash best at?
Math: 44.1 out of 100, place 109 of 168.
How fast is Gemini 2.5 Flash?
95 output tokens per second, 0.6 s to the first token.
What is the context window of Gemini 2.5 Flash?
1.05M tokens.
Is Gemini 2.5 Flash open source?
No. Its weights are not published.
When was Gemini 2.5 Flash released?
June 2025.

Badge

Gemini 2.5 Flash on Inference360: place 235 of 283, index 35.0
HTML
<a href="https://inference360.ai/models/gemini-2-5-flash"><img src="https://inference360.ai/badges/gemini-2-5-flash.svg" alt="Gemini 2.5 Flash on Inference360: place 235 of 283, index 35.0" height="20"></a>
Markdown
[![Gemini 2.5 Flash on Inference360: place 235 of 283, index 35.0](https://inference360.ai/badges/gemini-2-5-flash.svg)](https://inference360.ai/models/gemini-2-5-flash)

Compare with

GPT-4.1 mini34.5Llama 4 Maverick34.4Nemotron Ultra 253B35.9Gemini 2.5 Flash-Lite27.1Gemma 3 27B25.3

Lower price

dots3-note Preview63.4 · FreeApodex 1.1 Mini55.7 · FreeNemotron 3 Ultra50.8 · Free

More from Google

All models
Gemini 2.5 Pro Preview 06-05UnrankedGemini 2.5 Flash-Lite27.1Gemma 3 27B25.3Gemini 2.5 Pro46.6Gemini 2.0 Flash-LiteUnranked