MoonshotAI: Kimi K2.5
The MoonshotAI: Kimi K2.5 is an AI model that supports both text and image input modalities. It can handle long context lengths up to 262144 tokens and provide multiple completion tokens up to 235929. Consider shortlisting the MoonshotAI: Kimi K2.5 if you need a model that supports reasoning tasks, as indicated by its true support for tools and reasoning capabilities. However, with a blended benchmark score of 60.9 across two independent benchmarks, it may not be the top choice in terms of performance. Pricing also comes into play, with input tokens costing $0.45/M and output tokens at $2.25/M; users should weigh these costs against their specific needs and the value they expect to gain from the model's capabilities.
Benchmark results
Independent, published benchmarks. Blended score 60.9 across 2 benchmarks, last refreshed 2026-09-10. How scoring works →
| Benchmark | Measures | Score |
|---|---|---|
| AI Index | broad capability composite | 38.7 |
| EQ-Bench | emotional understanding in dialogue | 72.5 |
- Model ID
- moonshotai/kimi-k2.5
- Vendor
- moonshotai
- Released
- January 2026
- Tokenizer
- Other
- Input Modalities
- text, image
- Output Modalities
- text
- Max Output
- 235,929 tokens
- Tool Calling
- ✓ supported
- Structured Output
- ✓ supported
- Reasoning Mode
- ✓ supported
- Vision
- ✓ accepts images
- Audio
- no
- Moderated
- no
What it costs in practice
Computed from the current $0.45/M input and $2.25/M output rates. Run your own numbers →
| Job | Tokens | Cost |
|---|---|---|
| Summarize a 50-page report | 30k in / 1.5k out | $0.02 |
| Classify 1,000 customer emails | 500k in / 50k out | $0.34 |
| A month of a busy support chatbot | 5M in / 2M out | $6.75 |
Price & spec history
Tracked daily by PicksByModel since 2026-07-17.
| Date | Input /M | Output /M | Context |
|---|---|---|---|
| 2026-09-01 | $0.45 | $2.25 | 262,144 |
| 2026-08-28 | $0.60 | $3.00 | 262,144 |
| 2026-08-27 | $0.45 | $2.25 | 262,144 |
| 2026-08-25 | $0.60 | $3.00 | 262,144 |
| 2026-08-19 | $0.45 | $2.25 | 262,144 |
| 2026-07-17 | $0.57 | $2.85 | 262,144 |
Category rankings
Where MoonshotAI: Kimi K2.5 places across the 10 categories it ranks in. How we rank →
| # | Category | Score |
|---|---|---|
| #10 | Trivia & General KnowledgePersonal · of 25 ranked | 117 |
| #14 | Short-Form SummarizationWriting · of 25 ranked | 126 |
| #14 | Email DraftingWriting · of 25 ranked | 122 |
| #14 | Language LearningEducation · of 25 ranked | 122 |
| #14 | Chat CompanionPersonal · of 25 ranked | 126 |
| #23 | Sales / Cold EmailBusiness · of 25 ranked | 118 |
| #23 | Job Application DraftingBusiness · of 25 ranked | 118 |
| #23 | Journaling HelperPersonal · of 25 ranked | 118 |
| #23 | Recipe GenerationPersonal · of 25 ranked | 118 |
| #25 | Resume WritingBusiness · of 25 ranked | 113 |
Similar models
MoonshotAI: Kimi K3
MoonshotAI: Kimi K3 (batch)
MoonshotAI: Kimi K2.7 Code
MoonshotAI: Kimi K2.6
MoonshotAI: Kimi K2 Thinking
MoonshotAI: Kimi K2 0905
Quick answers
- How much does MoonshotAI: Kimi K2.5 cost?
- $0.45 per million input tokens and $2.25 per million output tokens.
- What is MoonshotAI: Kimi K2.5's context window?
- 262,144 tokens, roughly 393 pages of text in a single request.
- Does MoonshotAI: Kimi K2.5 support tool calling?
- It supports tool calling, structured output, a reasoning mode.
- Can MoonshotAI: Kimi K2.5 process images?
- Yes, it accepts image input.