MoonshotAI: Kimi K2.6
MoonshotAI's Kimi K2.6 is designed for handling both text and image inputs, with a substantial context length of 262,144 tokens and a maximum completion capacity of the same token count. It supports reasoning and tools integration, making it versatile for complex tasks that require multi-modal input processing and practical tool utilization. While Kimi K2.6 offers robust capabilities, its pricing at $0.95 per million input tokens and $4.0 per million output tokens might be considered high by some users. However, with a blended benchmark score of 79.3 across four independent evaluations, it performs well in both AI Index and EQBench scores, particularly excelling in coding tasks with a perfect 100.0 score. Given its price point, it is best suited for those who require high-quality text and image processing alongside reasoning and tool support, especially when working on projects that demand detailed and accurate output.
Benchmark results
Independent, published benchmarks. Blended score 79.3 across 4 benchmarks, last refreshed 2026-08-13. How scoring works →
| Benchmark | Measures | Score |
|---|---|---|
| AI Index | broad capability composite | 74.5 |
| AI Index Coding | software engineering tasks | 100.0 |
| AI Index Agentic | multi-step tool-using tasks | 51.4 |
| EQ-Bench | emotional understanding in dialogue | 76.6 |
- Model ID
- moonshotai/kimi-k2.6
- Vendor
- moonshotai
- Released
- April 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 $0.95/M input and $4.00/M output rates. Run your own numbers →
| Job | Tokens | Cost |
|---|---|---|
| Summarize a 50-page report | 30k in / 1.5k out | $0.03 |
| Classify 1,000 customer emails | 500k in / 50k out | $0.68 |
| A month of a busy support chatbot | 5M in / 2M out | $12.75 |
Price & spec history
Tracked daily by PicksByModel since 2026-07-17.
| Date | Input /M | Output /M | Context |
|---|---|---|---|
| 2026-08-10 | $0.95 | $4.00 | 262,144 |
| 2026-08-08 | $0.58 | $2.44 | 262,144 |
| 2026-08-04 | $0.59 | $2.48 | 262,144 |
| 2026-08-01 | $0.60 | $3.41 | 262,144 |
| 2026-07-31 | $0.95 | $4.00 | 262,144 |
| 2026-07-25 | $0.65 | $2.72 | 262,144 |
| 2026-07-19 | $0.68 | $3.42 | 262,144 |
| 2026-07-17 | $0.95 | $4.00 | 262,144 |
Strong choice for
Short-Form Summarization
Email Drafting
Language Learning
Chat Companion
Trivia & General Knowledge
Category rankings
Where MoonshotAI: Kimi K2.6 places across the 23 categories it ranks in. How we rank →
| # | Category | Score |
|---|---|---|
| #5 | Short-Form SummarizationWriting · of 25 ranked | 131 |
| #5 | Email DraftingWriting · of 25 ranked | 127 |
| #5 | Language LearningEducation · of 25 ranked | 127 |
| #5 | Chat CompanionPersonal · of 25 ranked | 131 |
| #5 | Trivia & General KnowledgePersonal · of 25 ranked | 122 |
| #7 | Image CaptioningVision · of 25 ranked | 121 |
| #10 | JSON ExtractionData · of 25 ranked | 147 |
| #14 | Dataset AnnotationResearch · of 25 ranked | 143 |
| #15 | Sales / Cold EmailBusiness · of 25 ranked | 123 |
| #15 | Job Application DraftingBusiness · of 25 ranked | 123 |
| #15 | Journaling HelperPersonal · of 25 ranked | 123 |
| #15 | Recipe GenerationPersonal · of 25 ranked | 123 |
| #16 | Customer SupportBusiness · of 25 ranked | 133 |
| #19 | Bulk Data LabelingData · of 25 ranked | 134 |
| #19 | Resume WritingBusiness · of 25 ranked | 118 |
| #21 | Regex WritingCode · of 25 ranked | 136 |
| #21 | Language TranslationWriting · of 25 ranked | 136 |
| #21 | Tutoring for KidsPersonal · of 25 ranked | 136 |
| #23 | Screenshot DebuggingVision · of 25 ranked | 142 |
| #25 | Frontend Component DesignCode · of 25 ranked | 146 |
| #25 | Marketing CopyWriting · of 25 ranked | 131 |
| #25 | Standardized Test PrepEducation · of 25 ranked | 131 |
| #25 | Chart & Graph ReadingVision · of 25 ranked | 152 |
Similar models
MoonshotAI: Kimi K3
MoonshotAI: Kimi K2.7 Code
MoonshotAI: Kimi K2.7 Code (batch)
MoonshotAI: Kimi K2.5
MoonshotAI: Kimi K2 Thinking
MoonshotAI: Kimi K2 0905
Quick answers
- How much does MoonshotAI: Kimi K2.6 cost?
- $0.95 per million input tokens and $4.00 per million output tokens.
- What is MoonshotAI: Kimi K2.6's context window?
- 262,144 tokens, roughly 393 pages of text in a single request.
- Does MoonshotAI: Kimi K2.6 support tool calling?
- It supports tool calling, structured output, a reasoning mode.
- Can MoonshotAI: Kimi K2.6 process images?
- Yes, it accepts image input.