AI model comparison
Kimi K2 0905 vs Gemini 2.5 Flash
Pricing, context window, benchmarks, and features compared side by side. Or skip the guesswork and send one prompt to both.
Moonshot AI
Kimi K2 0905
Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2).
- Input / 1M
- $0.60
- Output / 1M
- $2.50
- Context
- 262K
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
At a glance
Quick verdict
How the two models stack up on the things people ask about most.
Lower price
Gemini 2.5 Flash
1.3x cheaper for a typical chat
Higher intelligence score
Gemini 2.5 Flash
15.5 vs 15.3 on Artificial Analysis
Larger context window
Gemini 2.5 Flash
1.05M vs 262K tokens
Newer release
Kimi K2 0905
Released September 4, 2025
Benchmarks
Benchmark scores
Independent scores from Artificial Analysis. Higher is better.
Intelligence index
Gemini 2.5 Flash15.5Coding index
Gemini 2.5 FlashNot availableAgentic index
Gemini 2.5 FlashNot availablePricing
Kimi K2 0905 vs Gemini 2.5 Flash API pricing
Per-token API rates. Cheaper option highlighted.
| Metric | Gemini 2.5 Flash | |
|---|---|---|
| Input tokensPer 1M tokens | $0.60 | $0.30 |
| Output tokensPer 1M tokens | $2.50 | $2.50 |
| Cached input (read)Per 1M tokens | Not available | $0.03 |
| Cache writePer 1M tokens | Not available | $0.08 |
| Web searchPer request | Not available | $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$1.85Coding task
30K in, 4K out
Gemini 2.5 Flash$19$10.90 cachedLong document summary
150K in, 2K out
Gemini 2.5 Flash$50$9.50 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 | |
|---|---|---|
| Context window | 262K tokens | 1.05M tokens |
| Max output | 98K tokens | 66K tokens |
| Input types | Text | 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 | September 4, 2025 | June 17, 2025 |
Features
Supported features
API features available for each model.
| Metric | Gemini 2.5 Flash | |
|---|---|---|
| Tool calling | Supported | Supported |
| Structured outputs | Supported | Supported |
| JSON mode | Supported | Supported |
| Reasoning | Not 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 Gemini 2.5 Pro
- 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 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
Our take
Gemini 2.5 Flash is 1.3x cheaper for a typical chat. Gemini 2.5 Flash scores higher on the Artificial Analysis Intelligence Index (15.5 vs 15.3). Gemini 2.5 Flash has the larger context window (1.05M vs 262K tokens). 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 Kimi K2 0905 or Gemini 2.5 Flash 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 Kimi K2 0905 costs $0.60 per 1M input tokens and $2.50 per 1M output tokens.
Which has a bigger context window, Kimi K2 0905 or Gemini 2.5 Flash?
Gemini 2.5 Flash supports up to 1.05M tokens of context, compared with 262K for Kimi K2 0905.
Is Kimi K2 0905 smarter than Gemini 2.5 Flash?
On the Artificial Analysis Intelligence Index, Kimi K2 0905 scores 15.3 and Gemini 2.5 Flash scores 15.5, putting Gemini 2.5 Flash ahead. Benchmarks don't capture everything, so the best test is running your own prompts through both.
Can I use Kimi K2 0905 and Gemini 2.5 Flash at the same time?
Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see Kimi K2 0905 and Gemini 2.5 Flash answer side by side and keep the better response.
Why choose? Ask both.
Send one prompt to Kimi K2 0905 and Gemini 2.5 Flash at the same time. Compare the answers side by side and keep the best one.