MoonshotAI: Kimi K2.7 Code vs Anthropic: Claude Sonnet Latest
Side-by-side comparison of specs, pricing, benchmark scores, and task rankings. Updated 2026-11-07.
| MoonshotAI: Kimi K2.7 Code | Anthropic: Claude Sonnet Latest | |
|---|---|---|
| Vendor | moonshotai | ~anthropic |
| Quality Score | 100 | 100 |
| Benchmark Score | 74.1 | - |
| Input Price | $0.60/M | $2.00/M |
| Output Price | $3.50/M | $10.00/M |
| Context Window | 262,144 | 1,000,000 |
| Max Output | 235,929 | 128,000 |
| Tool Calling | ✓ | ✓ |
| Structured Output | ✓ | ✓ |
| Reasoning Mode | ✓ | ✓ |
| Vision | ✓ | ✓ |
| Audio | - | - |
| Benchmark Scores | ||
| ai_index | 69.2 | - |
| ai_index_agentic | 48.8 | - |
| ai_index_coding | 100.0 | - |
The verdict
For a sample job of 1 million input tokens and 250,000 output tokens, Kimi K2.7 Code costs $1.48 and Claude Sonnet Latest costs $4.50, so Kimi K2.7 Code is about 3.1 times cheaper for the same work.
Claude Sonnet Latest reads up to 1,000,000 tokens at once, roughly 1,500 pages of text, against about 393 pages for Kimi K2.7 Code.
Across the 20 tasks where they differ, Kimi K2.7 Code scores higher on 20 (SQL Generation, Code Review, Code Completion and others).
Kimi K2.7 Code was released in June 2026 and Claude Sonnet Latest in April 2026.
Pick Kimi K2.7 Code if you need lower cost or the stronger all-round task scores; pick Claude Sonnet Latest if you need long documents.
Costs use current list prices per million tokens; page counts assume about 0.75 words per token and 500 words per page.
Who wins by task?
| Task | MoonshotAI: Kimi K2.7 Code | Anthropic: Claude Sonnet Latest |
|---|---|---|
| SQL Generation | 163 | 132 |
| Code Review | 155 | 132 |
| Code Completion | 129 | 117 |
| Code Refactoring | 151 | 136 |
| Bug Fixing | 165 | 136 |
| Unit Test Generation | 147 | 124 |
| Code Documentation | 135 | 129 |
| Regex Writing | 133 | 117 |
| CI/CD Pipelines | 138 | 120 |
| Frontend Component Design | 142 | 122 |
| Data Analysis | 162 | 124 |
| CSV / Spreadsheet Cleanup | 147 | 132 |
| ETL Scripting | 144 | 128 |
| JSON Extraction | 147 | 121 |
| Bulk Data Labeling | 134 | 118 |
| OCR / Document Parsing | 142 | 131 |
| Table Extraction from PDFs | 142 | 131 |
| Long-Document Summarization | 147 | 136 |
| Short-Form Summarization | 130 | 113 |
| Blog Post Writing | 134 | 120 |
Scores reflect capability match + benchmark data + pricing for each task. Methodology →