moonshotai
MoonshotAI: Kimi K2.6
MoonshotAI's Kimi K2.6 is an advanced AI capable of processing both text and image inputs within extensive 262,144-token contexts; it supports reasoning and tools but does not generate structured output. With robust support for diverse input modalities and analytical capabilities, this model offers flexibility in various applications. For users prioritizing cost-effectiveness while balancing performance across multiple benchmarks, Kimi K2.6 stands out with a blended score of 79.9 from four independent evaluations. Its price points at $0.684 per million input tokens and $3.42 for output tokens make it a competitive choice within its benchmark standing; however, its low coverage in the benchmark might limit comparisons to more comprehensive models.
Quality Score
100/100
price + capability + benchmarks
Input Price
$0.68
per 1M tokens
Output Price
$3.42
per 1M tokens
Context Window
262,144
tokens
Benchmark results
Independent, published benchmarks. Blended score 79.9 across 4 benchmarks, last refreshed 2026-07-21. How scoring works →
| Benchmark | Measures | Score |
|---|---|---|
| AI Index | broad capability composite | 73.0 |
| AI Index Coding | software engineering tasks | 100.0 |
| AI Index Agentic | multi-step tool-using tasks | 49.9 |
| 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 $0.68/M input and $3.42/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 | $0.51 |
| A month of a busy support chatbot | 5M in / 2M out | $10.26 |
Price & spec history
Tracked daily by PicksByModel since 2026-07-17.
| Date | Input /M | Output /M | Context |
|---|---|---|---|
| 2026-07-19 | $0.68 | $3.42 | 262,144 |
| 2026-07-17 | $0.95 | $4.00 | 262,144 |
Strong choice for
Code
Regex Writing
Crafting regular expressions that actually match what you intend.
Data
JSON Extraction
Pulling structured fields out of unstructured text.
Writing
Short-Form Summarization
TL;DRs of articles and emails at scale.
Writing
Email Drafting
Cold emails, replies, and outreach at the right tone.
Writing
Language Translation
High-quality multilingual translation.
Education
Language Learning
Conversational practice, grammar drills, vocabulary.
Category rankings
Where MoonshotAI: Kimi K2.6 places across the 70 categories it ranks in. How we rank →
| # | Category | Score |
|---|---|---|
| #1 | Trivia & General KnowledgePersonal · of 25 ranked | 122 |
| #2 | JSON ExtractionData · of 25 ranked | 147 |
| #2 | Resume WritingBusiness · of 25 ranked | 118 |
| #2 | Image CaptioningVision · of 25 ranked | 121 |
| #3 | Short-Form SummarizationWriting · of 25 ranked | 131 |
| #3 | Email DraftingWriting · of 25 ranked | 127 |
| #3 | Language LearningEducation · of 25 ranked | 127 |
| #3 | Chat CompanionPersonal · of 25 ranked | 131 |
| #4 | Regex WritingCode · of 25 ranked | 136 |
| #4 | Language TranslationWriting · of 25 ranked | 136 |
| #4 | Customer SupportBusiness · of 25 ranked | 133 |
| #4 | Sales / Cold EmailBusiness · of 25 ranked | 123 |
| #4 | Job Application DraftingBusiness · of 25 ranked | 123 |
| #4 | Journaling HelperPersonal · of 25 ranked | 123 |
| #4 | Recipe GenerationPersonal · of 25 ranked | 123 |
| #4 | Tutoring for KidsPersonal · of 25 ranked | 136 |
| #4 | Dataset AnnotationResearch · of 25 ranked | 143 |
| #6 | Marketing CopyWriting · of 25 ranked | 130 |
| #6 | Standardized Test PrepEducation · of 25 ranked | 130 |
| #7 | Bulk Data LabelingData · of 25 ranked | 134 |
| #7 | SOP / Process DocsBusiness · of 25 ranked | 137 |
| #8 | Screenshot DebuggingVision · of 25 ranked | 142 |
| #9 | Frontend Component DesignCode · of 25 ranked | 146 |
| #9 | Diagram ExtractionVision · of 25 ranked | 148 |
| #9 | Chart & Graph ReadingVision · of 25 ranked | 152 |
| #9 | Fitness CoachingPersonal · of 25 ranked | 134 |
| #11 | Math TutoringEducation · of 25 ranked | 147 |
| #11 | Experiment DesignResearch · of 25 ranked | 157 |
| #12 | Blog Post WritingWriting · of 25 ranked | 139 |
| #12 | Financial AnalysisProfessional · of 25 ranked | 157 |
| #12 | Trip PlanningPersonal · of 25 ranked | 139 |
| #13 | SQL GenerationCode · of 25 ranked | 168 |
| #13 | Code DocumentationCode · of 25 ranked | 141 |
| #13 | OCR / Document ParsingData · of 25 ranked | 145 |
| #13 | Table Extraction from PDFsData · of 25 ranked | 145 |
| #13 | Browser AutomationAgents · of 25 ranked | 166 |
| #14 | Unit Test GenerationCode · of 25 ranked | 153 |
| #14 | CI/CD PipelinesCode · of 25 ranked | 143 |
| #14 | Data AnalysisData · of 25 ranked | 167 |
| #14 | Meeting NotesBusiness · of 25 ranked | 150 |
| #15 | Physics TutoringEducation · of 25 ranked | 147 |
| #15 | Function / Tool CallingAgents · of 25 ranked | 149 |
| #15 | Character RoleplayPersonal · of 25 ranked | 148 |
| #16 | Code ReviewCode · of 25 ranked | 165 |
| #16 | Code CompletionCode · of 25 ranked | 132 |
| #16 | Essay GradingEducation · of 25 ranked | 165 |
| #17 | CSV / Spreadsheet CleanupData · of 25 ranked | 152 |
| #17 | ETL ScriptingData · of 25 ranked | 152 |
| #17 | Long-Document SummarizationWriting · of 25 ranked | 158 |
| #17 | Creative WritingWriting · of 25 ranked | 156 |
| #17 | Screenwriting & DialogWriting · of 25 ranked | 156 |
| #17 | Academic WritingWriting · of 25 ranked | 156 |
| #17 | Legal DraftingProfessional · of 25 ranked | 156 |
| #17 | Medical Note SummarizationProfessional · of 25 ranked | 152 |
| #17 | History TutoringEducation · of 25 ranked | 143 |
| #17 | OKRs & Strategic PlanningBusiness · of 25 ranked | 156 |
| #17 | Math ProofsResearch · of 25 ranked | 156 |
| #18 | Code RefactoringCode · of 25 ranked | 161 |
| #18 | Bug FixingCode · of 25 ranked | 176 |
| #18 | Legal ResearchProfessional · of 25 ranked | 165 |
| #18 | Contract ReviewProfessional · of 25 ranked | 174 |
| #18 | Scientific ResearchProfessional · of 25 ranked | 165 |
| #18 | RFP ResponseBusiness · of 25 ranked | 171 |
| #18 | Agent WorkflowsAgents · of 25 ranked | 186 |
| #18 | RAG PipelinesAgents · of 25 ranked | 161 |
| #18 | Coding AgentsAgents · of 25 ranked | 186 |
| #18 | Fiction CollaboratorPersonal · of 25 ranked | 165 |
| #18 | Scientific CodingResearch · of 25 ranked | 176 |
| #18 | Literature ReviewResearch · of 25 ranked | 165 |
| #20 | Long-Context Q&AAgents · of 25 ranked | 152 |
Similar models
moonshotai
MoonshotAI: Kimi K2.7 Code
$0.82 in / $3.75 out
262,144 ctx
100
moonshotai
MoonshotAI: Kimi K2.5
$0.57 in / $2.85 out
262,144 ctx
100
moonshotai
MoonshotAI: Kimi K2 Thinking
$0.60 in / $2.50 out
262,144 ctx
98
moonshotai
MoonshotAI: Kimi K3
$3.00 in / $15.00 out
1,048,576 ctx
96
moonshotai
MoonshotAI: Kimi K2 0905
$0.60 in / $2.50 out
262,144 ctx
93
moonshotai
MoonshotAI: Kimi K2 0711
$0.57 in / $2.30 out
131,072 ctx
79
Quick answers
- How much does MoonshotAI: Kimi K2.6 cost?
- $0.68 per million input tokens and $3.42 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.