MoonshotAI: Kimi K2.5
The MoonshotAI Kimi K2.5 handles text and image inputs with a context length of 262,144 tokens; it supports reasoning and tools but does not offer structured output. With both input and completion token limits set at 262,144, this model is designed for extensive textual tasks that require handling large contexts or complex multimodal data. Considering its pricing at $0.57 per million input tokens and $2.85 per million output tokens, the MoonshotAI Kimi K2.5 is most suitable for users with specific budget constraints. Its blended benchmark score of 64.5 across four independent benchmarks places it in a competitive position, especially given its support for reasoning and tools.
Benchmark results
Independent, published benchmarks. Blended score 64.5 across 4 benchmarks, last refreshed 2026-08-13. How scoring works →
| Benchmark | Measures | Score |
|---|---|---|
| AI Index | broad capability composite | 59.4 |
| AI Index Coding | software engineering tasks | 77.2 |
| AI Index Agentic | multi-step tool-using tasks | 35.8 |
| 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
- 262,144 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 $0.57/M input and $2.85/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 | $0.43 |
| A month of a busy support chatbot | 5M in / 2M out | $8.55 |
Category rankings
Where MoonshotAI: Kimi K2.5 places across the 6 categories it ranks in. How we rank →
| # | Category | Score |
|---|---|---|
| #14 | Trivia & General KnowledgePersonal · of 25 ranked | 120 |
| #16 | Short-Form SummarizationWriting · of 25 ranked | 130 |
| #16 | Chat CompanionPersonal · of 25 ranked | 130 |
| #17 | Email DraftingWriting · of 25 ranked | 126 |
| #17 | Language LearningEducation · of 25 ranked | 126 |
| #24 | Image CaptioningVision · of 25 ranked | 120 |
Similar models
MoonshotAI: Kimi K3
MoonshotAI: Kimi K2.7 Code
MoonshotAI: Kimi K2.7 Code (batch)
MoonshotAI: Kimi K2.6
MoonshotAI: Kimi K2 Thinking
MoonshotAI: Kimi K2 0905
Quick answers
- How much does MoonshotAI: Kimi K2.5 cost?
- $0.57 per million input tokens and $2.85 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.