AI model comparison
Gemini 2.5 Flash vs Gemini 2.5 Pro
Pricing, context window, benchmarks, and features compared side by side. Or skip the guesswork and send one prompt to both.
Gemini 2.5 Flash
Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks.
Gemini 2.5 Flash is scheduled to be retired on October 20, 2026. Consider Gemini 3.8 Flash instead.
- Input / 1M
- $0.30
- Output / 1M
- $2.50
- Context
- 1.05M
Gemini 2.5 Pro
Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks.
Gemini 2.5 Pro is scheduled to be retired on October 20, 2026. Consider Gemini 3.1 Pro Preview instead.
- Input / 1M
- $1.25
- Output / 1M
- $10
- Context
- 1.05M
At a glance
Quick verdict
How the two models stack up on the things people ask about most.
Lower price
Gemini 2.5 Flash
4.1x cheaper for a typical chat
Higher intelligence score
Gemini 2.5 Pro
16.1 vs 15.5 on Artificial Analysis
Larger context window
Tie
1.05M vs 1.05M tokens
Newer release
Gemini 2.5 Flash
Released June 17, 2025
Benchmarks
Benchmark scores
Independent scores from Artificial Analysis. Higher is better.
Intelligence index
Gemini 2.5 Flash15.5Gemini 2.5 Pro16.1Coding index
Gemini 2.5 FlashNot availableGemini 2.5 Pro33.3Agentic index
Gemini 2.5 FlashNot availableGemini 2.5 Pro1.6Pricing
Gemini 2.5 Flash vs Gemini 2.5 Pro API pricing
Per-token API rates. Cheaper option highlighted.
| Metric | Gemini 2.5 Flash | Gemini 2.5 Pro |
|---|---|---|
| Input tokensPer 1M tokens | $0.30 | $1.25 |
| Output tokensPer 1M tokens | $2.50 | $10 |
| Cached input (read)Per 1M tokens | $0.03 | $0.13 |
| Cache writePer 1M tokens | $0.08 | $0.38 |
| Long-context pricingPer 1M tokens, for very long prompts | Same rate at any length | $2.50 in / $15 out above 200K |
| Web searchPer request | $0.014 | $0.014 |
What it costs in practice
Estimated cost per 1,000 requests at standard rates. Coding and long-document figures also show the cost when the input is already cached.
Chat message
2K in, 500 out
Gemini 2.5 Flash$1.85Gemini 2.5 Pro$7.50Coding task
30K in, 4K out
Gemini 2.5 Flash$19$10.90 cachedGemini 2.5 Pro$77.50$43.75 cachedLong document summary
150K in, 2K out
Gemini 2.5 Flash$50$9.50 cachedGemini 2.5 Pro$207.50$38.75 cachedSpecs
Context window and capabilities
How much each model can read, how much it can write, and what it accepts as input.
| Metric | Gemini 2.5 Flash | Gemini 2.5 Pro |
|---|---|---|
| Context window | 1.05M tokens | 1.05M tokens |
| Max output | 66K tokens | 66K tokens |
| Input types | Audio, File, Image, Text, Video | Audio, File, Image, Text, Video |
| Output types | Text | Text |
| Reasoning effort levels | Not available | Not available |
| Default reasoning effort | Not available | Not available |
| Release date | June 17, 2025 | June 17, 2025 |
Features
Supported features
API features available for each model.
| Metric | Gemini 2.5 Flash | Gemini 2.5 Pro |
|---|---|---|
| Tool calling | Supported | Supported |
| Structured outputs | Supported | Supported |
| JSON mode | Supported | Supported |
| Reasoning | Supported | Supported |
| Temperature | Supported | Supported |
| Stop sequences | Supported | Supported |
| Deterministic seed | Supported | Supported |
| Verbosity control | Not supported | Not supported |
Keep exploring
More on these models
Other head-to-heads, the full model page, and the alternatives list for each model.
Gemini 2.5 FlashView full model details- Gemini 2.5 Flash vs Step 5 Preview
- Gemini 2.5 Flash vs Gemini 3.1 Flash Lite
- Gemini 2.5 Flash vs Gemma 4 31B
- Gemini 2.5 Flash vs Gemma 4 26B A4B
- Gemini 2.5 Flash vs Claude Haiku 4.5
- Gemini 2.5 Flash vs Gemini 3.5 Flash Lite
- Gemini 2.5 Flash vs Muse Glimmer 30B
- Gemini 2.5 Flash vs GLM 4.6
- Gemini 2.5 Flash vs R1 0528
- Gemini 2.5 Flash vs Qwen3.5-122B-A10B
- Gemini 2.5 Flash vs Kimi K2 0905
- Gemini 2.5 Flash vs Mistral Medium 3.5
- Gemini 2.5 Flash vs o4 Mini
- Gemini 2.5 Flash vs DeepSeek V3.1 Terminus
- Gemini 2.5 Flash vs Nova 2 Lite
- Gemini 2.5 Flash vs Command A
- Gemini 2.5 Flash vs GLM 4.5
- Gemini 2.5 Flash vs Kimi K2 0711
- Gemini 2.5 Flash vs Qwen3 235B A22B Thinking 2507
- Gemini 2.5 Flash vs o3 Mini
- Gemini 2.5 Flash vs MiniMax M1
- Gemini 2.5 Flash vs R1
Gemini 2.5 ProView full model details- Gemini 2.5 Pro vs Gemini 3.1 Flash Lite
- Gemini 2.5 Pro vs Claude Haiku 4.5
- Gemini 2.5 Pro vs Claude Sonnet 4.5
- Gemini 2.5 Pro vs GPT-4.1
- Gemini 2.5 Pro vs Claude Sonnet 4
- Gemini 2.5 Pro vs o4 Mini
- Gemini 2.5 Pro vs Kimi K2 0905
- Gemini 2.5 Pro vs o1
- Gemini 2.5 Pro vs Mistral Medium 3.5
- Gemini 2.5 Pro vs Command A
- Gemini 2.5 Pro vs Sonar Reasoning Pro
Our take
Gemini 2.5 Flash is 4.1x cheaper for a typical chat. Gemini 2.5 Pro scores higher on the Artificial Analysis Intelligence Index (16.1 vs 15.5). The right pick depends on your workload, so the quickest way to settle it is to send the same prompt to both and compare.
FAQ
Frequently asked questions
Is Gemini 2.5 Flash or Gemini 2.5 Pro cheaper?
Gemini 2.5 Flash is cheaper for a typical chat (2K input tokens and 500 output tokens). Gemini 2.5 Flash costs $0.30 per 1M input tokens and $2.50 per 1M output tokens, while Gemini 2.5 Pro costs $1.25 per 1M input tokens and $10 per 1M output tokens.
Which has a bigger context window, Gemini 2.5 Flash or Gemini 2.5 Pro?
Gemini 2.5 Flash supports up to 1.05M tokens of context, compared with 1.05M for Gemini 2.5 Pro.
Is Gemini 2.5 Flash smarter than Gemini 2.5 Pro?
On the Artificial Analysis Intelligence Index, Gemini 2.5 Flash scores 15.5 and Gemini 2.5 Pro scores 16.1, putting Gemini 2.5 Pro ahead. Benchmarks don't capture everything, so the best test is running your own prompts through both.
Can I use Gemini 2.5 Flash and Gemini 2.5 Pro at the same time?
Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see Gemini 2.5 Flash and Gemini 2.5 Pro answer side by side and keep the better response.
Why choose? Ask both.
Send one prompt to Gemini 2.5 Flash and Gemini 2.5 Pro at the same time. Compare the answers side by side and keep the best one.