LLM Reference

Gemini 2.5 Flash

Released
2025-06-17
Last refreshed
2026-06-29
Status
Researched 74d ago
ProprietaryCommercial use: conditionalMultimodalCodingRAGAgentsLong contextVisionClassificationJSON / Tool use

Gemini 2.5 Flash is worth evaluating for coding, rag, and agents when its provider route and context window match the workload.

Use it for

  • Teams evaluating coding, rag, and agents
  • Workloads that can use a 1m context window
  • Buyers comparing 4 tracked provider routes

Do not use it for

  • Workloads where another current model has stronger sourced task evidence
Specifications
Released
2025-06-17
Context
1m
Architecture
Decoder Only
Knowledge cutoff
2025-01
Specialization
general
Openness
Proprietary
License
ProprietaryCommercial use: conditional
Training
Pretrained
Created by

Pioneering artificial intelligence research.

London, United Kingdom
Founded 2014
Website
Pricing
Output / 1M
$2.50
Input / 1M
$0.300

Cheapest of 6 routes · GCP Vertex AI

About

Google: Gemini 2.5 Flash available via OpenRouter. Pricing: $0.3/1M input, $2.5/1M output.

Gemini 2.5 Flash is a proprietary model in the Gemini 2.5 family. The structured metadata tracks a 1m-token context window, multimodal input, function calling, tool use, structured outputs, and code execution. This page tracks provider routes through Google AI Studio, GCP Vertex AI, Replicate API, and 3 more, with the cheapest tracked route listed at $0.3 input and $2.5 output per 1M tokens. Headline tracked benchmarks include HumanEval 90.1, LiveCodeBench 76.2, and Aider Polyglot 55.1.

Top use-case fit: coding, agents, and build tasks

Coding

Q/$ C

3 relevant benchmarks in the decision map.

RAG

Included by capability and metadata signals in the decision map.

Agents

Included by capability and metadata signals in the decision map.

Provider price ladder

Compare all 6

Compare API pricing across 4 providers for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MRoute
GCP Vertex AI$0.300$2.50
Serverless
Google AI Studio$0.300$2.50
Serverless
OpenRouter$0.300$2.50
Serverless
Replicate API$0.300$2.50
Serverless

Available via routers & gateways(13)

Capabilities

VisionMultimodalFunction CallingTool UseStructured OutputsCode Execution

Benchmark peer barsfor Coding

Benchmark scores(8)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionSource
HumanEval90.12025-05https://storage.googleapis.com/deepmind-media/gemini/gemini_v2_5_report.pdf
LiveCodeBench76.22026-04https://livecodebench.github.io/performances_generation.json
Aider Polyglot55.12026-04https://aider.chat/docs/leaderboards
Chatbot Arena1320.0https://lmarena.ai
Massive Multi-discipline Multimodal Understanding79.7https://mmmu-benchmark.github.io/
BFCL56.2https://gorilla.cs.berkeley.edu/leaderboard.html
MMLU PRO88.4https://deepmind.google/technologies/gemini/flash/
Google-Proof Q&A82.8https://deepmind.google/technologies/gemini/flash/

Migration checks

No linked migration route is available for this model yet.

Compare Gemini 2.5 Flash with other models

Show all 53 popular comparisonssorted by 7-day search impressions
Gemini 2.5 Flash vs Qwen3.6-35B-A3B257Gemini 2.5 Flash vs GPT-5.4202Gemini 2.5 Flash vs Claude Sonnet 4.5199Gemini 2.5 Flash vs GPT-5.5169Gemini 2.5 Flash vs Llama 3.1 70B Instruct122Gemini 2.5 Flash vs Llama 3 70B Instruct103Gemini 2.5 Flash vs Qwen3.6-27B102Gemini 2.5 Flash vs Qwen3.5-35B-A3B66Gemini 2.5 Flash vs Qwen2-7B-Instruct64Gemini 2.5 Flash vs Claude Opus 4.763Gemini 2.5 Flash vs Claude 3.7 Sonnet59Gemini 2.5 Flash vs DeepSeek V3.256Gemini 2.5 Flash vs DeepSeek V3.151Gemini 2.5 Flash vs DeepSeek R1 052851Gemini 2.5 Flash vs Grok-346Gemini 2.5 Flash vs GLM-546Gemini 2.5 Flash vs o3 Deep Research45Gemini 2.5 Flash vs Llama 3.2 1B Instruct43Gemini 2.5 Flash vs o3-pro40Gemini 2.5 Flash vs Qwen2.5-72B-Instruct39Gemini 2.5 Flash vs Qwen3.5-27B38Gemini 2.5 Flash vs Mistral Large 236Gemini 2.5 Flash vs Phi 3.5 Mini Instruct23Gemini 2.5 Flash vs Phi-3 Mini 4k21Gemini 2.5 Flash vs Gemma 7B Instruct21Gemini 2.5 Flash vs Kimi K2.520Gemini 2.5 Flash vs Claude Opus 4.618Gemini 2.5 Flash vs Qwen3-Max17Gemini 2.5 Flash vs GPT-5.4-Cyber16Gemini 2.5 Flash vs o3 Mini16Gemini 2.5 Flash vs Mixtral 8x7B15Gemini 2.5 Flash vs GPT-5.5 Pro14Gemini 2.5 Flash vs Mistral Small 414Gemini 2.5 Flash vs Phi-4 Mini Flash Reasoning13Gemini 2.5 Flash vs Mistral Nemotron12Gemini 2.5 Flash vs o311Gemini 2.5 Flash vs Llama 3 8B Instruct10Gemini 2.5 Flash vs GPT-5.210Gemini 2.5 Flash vs Qwen3.5-122B-A10B10Gemini 2.5 Flash vs Grok 3 Mini10Gemini 2.5 Flash vs Qwen3.5-397B-A17B9Gemini 2.5 Flash vs Together AI - Llama 3 8B Lite9Gemini 2.5 Flash vs GPT-5.5 Instant9Gemini 2.5 Flash vs Claude 3.5 Sonnet9Gemini 2.5 Flash vs Llama 2 70B Chat8Gemini 2.5 Flash vs GLM-5V-Turbo8Gemini 2.5 Flash vs Trinity-Large-Thinking7Gemini 2.5 Flash vs Claude Opus 4.56Gemini 2.5 Flash vs Llama 2 13B Chat6Gemini 2.5 Flash vs Kimi K2 Instruct4Gemini 2.5 Flash vs Llama Guard 3 1B3Gemini 2.5 Flash vs Code Davinci 0013Gemini 2.5 Flash vs Llama 3.1 405B Instruct1

Frequently asked questions

What is the context window of Gemini 2.5 Flash?

Gemini 2.5 Flash has a context window of 1m tokens.

How much does Gemini 2.5 Flash cost?

Gemini 2.5 Flash is available at $0.3/1M input tokens through Google AI Studio.

When was Gemini 2.5 Flash released?

Gemini 2.5 Flash was released on 2025-06-17.

Which providers offer Gemini 2.5 Flash?

Gemini 2.5 Flash is available from 6 providers: Google AI Studio, GCP Vertex AI, Replicate API, OpenRouter, Vercel AI Gateway, Inceptron.

What benchmarks has Gemini 2.5 Flash been tested on?

Gemini 2.5 Flash has been evaluated on 8 benchmarks, including HumanEval, LiveCodeBench, Aider Polyglot, Chatbot Arena, Massive Multi-discipline Multimodal Understanding.