MoonshotAI: Kimi K2.7 Code
MoonshotAI Kimi K2.7 Code supports both text and image inputs and can handle contexts up to 262,144 tokens. The model is capable of reasoning and working with tools but does not offer structured output. With a blended benchmark score of 73.4 across three independent benchmarks, it excels in coding tasks but lags in agentic behavior assessment. This model should be considered for projects requiring text and image processing along with robust reasoning capabilities, despite its premium pricing at $0.73 per million input tokens and $3.5 per million output tokens. Its performance is solid but users should carefully weigh the cost against their specific needs given the lower agentic score; it remains a strong contender in contexts where coding proficiency and contextual understanding are paramount.
Benchmark results
Independent, published benchmarks. Blended score 73.4 across 3 benchmarks, last refreshed 2026-07-29. How scoring works →
| Benchmark | Measures | Score |
|---|---|---|
| AI Index | broad capability composite | 69.2 |
| AI Index Coding | software engineering tasks | 100.0 |
| AI Index Agentic | multi-step tool-using tasks | 48.8 |
- Model ID
- moonshotai/kimi-k2.7-code
- Vendor
- moonshotai
- Released
- June 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 $0.73/M input and $3.50/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 | $0.54 |
| A month of a busy support chatbot | 5M in / 2M out | $10.65 |
Price & spec history
Tracked daily by PicksByModel since 2026-07-17.
| Date | Input /M | Output /M | Context |
|---|---|---|---|
| 2026-07-27 | $0.73 | $3.50 | 262,144 |
| 2026-07-26 | $0.75 | $3.50 | 262,144 |
| 2026-07-25 | $0.78 | $3.50 | 262,144 |
| 2026-07-24 | $0.71 | $3.50 | 262,144 |
| 2026-07-21 | $0.82 | $3.75 | 262,144 |
| 2026-07-19 | $0.85 | $3.80 | 262,144 |
| 2026-07-18 | $1.00 | $4.40 | 262,144 |
| 2026-07-17 | $0.75 | $3.50 | 262,144 |
Category rankings
Where MoonshotAI: Kimi K2.7 Code places across the 10 categories it ranks in. How we rank →
| # | Category | Score |
|---|---|---|
| #7 | Image CaptioningVision · of 25 ranked | 121 |
| #8 | JSON ExtractionData · of 25 ranked | 147 |
| #11 | Dataset AnnotationResearch · of 25 ranked | 143 |
| #13 | Customer SupportBusiness · of 25 ranked | 133 |
| #13 | Trivia & General KnowledgePersonal · of 25 ranked | 120 |
| #14 | Short-Form SummarizationWriting · of 25 ranked | 130 |
| #14 | Email DraftingWriting · of 25 ranked | 126 |
| #14 | Language LearningEducation · of 25 ranked | 126 |
| #14 | Chat CompanionPersonal · of 25 ranked | 130 |
| #15 | Bulk Data LabelingData · of 25 ranked | 134 |
Similar models
MoonshotAI: Kimi K2.6
MoonshotAI: Kimi K2.5
MoonshotAI: Kimi K2 Thinking
MoonshotAI: Kimi K3
MoonshotAI: Kimi K2 0905
MoonshotAI: Kimi K2 0711
Quick answers
- How much does MoonshotAI: Kimi K2.7 Code cost?
- $0.73 per million input tokens and $3.50 per million output tokens.
- What is MoonshotAI: Kimi K2.7 Code's context window?
- 262,144 tokens, roughly 393 pages of text in a single request.
- Does MoonshotAI: Kimi K2.7 Code support tool calling?
- It supports tool calling, structured output, a reasoning mode.
- Can MoonshotAI: Kimi K2.7 Code process images?
- Yes, it accepts image input.