gemini-2.5-pro vs kimi-k2.5
Side-by-side comparison of gemini-2.5-pro and kimi-k2.5: benchmarks, pricing, context window and capabilities. Both are accessible through Requesty's unified API. kimi-k2.5 outperforms gemini-2.5-pro on 6 of 6 shared benchmarks.
gemini-2.5-pro
Input / 1M
$1.25
Output / 1M
$10.00
Context
1.0M
Model ID
google/gemini-2.5-pro
kimi-k2.5
Input / 1M
$0.60
Output / 1M
$3.00
Context
262K
Model ID
moonshot/kimi-k2.5
Benchmark comparison
Intelligence Indexreasoning
gemini-2.5-pro19.0%
kimi-k2.527.6%
Coding Indexcoding
gemini-2.5-pro33.3%
kimi-k2.546.8%
Math Indexmath
gemini-2.5-pro87.7%
kimi-k2.5N/A
GPQA Diamondreasoning
gemini-2.5-pro84.4%
kimi-k2.587.9%
AIME 2025math
gemini-2.5-pro87.7%
kimi-k2.5N/A
LiveCodeBenchcoding
gemini-2.5-pro80.1%
kimi-k2.5N/A
Terminal-Bench Hardagentic
gemini-2.5-pro26.5%
kimi-k2.534.8%
τ²-Benchagentic
gemini-2.5-pro54.1%
kimi-k2.595.9%
MMLU Proknowledge
gemini-2.5-pro86.2%
kimi-k2.5N/A
Humanity's Last Examreasoning
gemini-2.5-pro22.5%
kimi-k2.530.7%
Scores sourced from official model cards, Artificial Analysis, and public leaderboards. Benchmarks measure specific skills and don't capture every aspect of model quality.
Pricing & specifications
| gemini-2.5-pro | kimi-k2.5 | |
|---|---|---|
| Input price / 1M | $1.25 | $0.60 |
| Output price / 1M | $10.00 | $3.00 |
| Context window | 1.0M tokens | 262K tokens |
| Max output | 66K tokens | 262K tokens |
| Vision input | Yes | Yes |
| Tool calling | Yes | Yes |
| Reasoning | Yes | Yes |
| Prompt caching | Yes | Yes |
| Computer use | N/A | N/A |
| Provider | Google LLC (Gemini API) | Moonshot AI |
Questions people ask
Is gemini-2.5-pro better than kimi-k2.5?
kimi-k2.5 outperforms gemini-2.5-pro on 6 of 6 shared benchmarks. See the benchmark comparison above for specifics: gemini-2.5-pro and kimi-k2.5 have different strengths across reasoning, coding, math and multimodal tasks.
Which is cheaper, gemini-2.5-pro or kimi-k2.5?
kimi-k2.5 is cheaper. gemini-2.5-pro costs $1.25/$10.00 per 1M input/output tokens, while kimi-k2.5 costs $0.60/$3.00.
Can I use gemini-2.5-pro and kimi-k2.5 through the same API?
Yes. Requesty provides a single OpenAI-compatible API that routes to both. Change just the "model" parameter to switch between "google/gemini-2.5-pro" and "moonshot/kimi-k2.5", no other code changes needed.
What are the context windows?
gemini-2.5-pro supports up to 1.0M tokens of context. kimi-k2.5 supports up to 262K tokens. Longer context means you can feed larger documents or codebases in a single prompt, though quality often degrades past 128K for most models.
Switch between gemini-2.5-pro and kimi-k2.5 with one line of code
Requesty provides a single OpenAI-compatible API for 600+ models. Change the model parameter, not your code.