Moonshot AI
Moonshot AI’s premier flagship model with 2.8 trillion parameters, Kimi Delta Attention, 1M context, and open weights.
1.049M ctx$3.00 / 1M tok (2.8T Open Weights)
Introducing Kimi K2.7 Code HighSpeedMoonshot AIReleased June 15, 2026
Kimi K2.7 Code HighSpeed
High-speed variant of Kimi K2.7 Code with generation speeds of 180 to 260 tokens per second for instantaneous coding feedback.
reasoning-llmProprietary API$1.90 / 1M tok (180-260 tok/s)Context: 262.144K (262,144 tokens)Arena ELO: 1485
Technical Specifications
Architecture Type
High-Throughput Dedicated Coding Transformer
Total Parameters
Frontier Scale
Context Window
262.144K (262,144 tokens)
Max Output Tokens
65.536K (65,536 tokens)
Knowledge Cutoff
May 2026
Supported Modalities
text, code, vision, reasoning
License & Access
Moonshot AI Terms of Service
Benchmark Evaluations
Humaneval
97.4
Tokens Per Sec
220
Swe Bench Verified
76.5
Chatbot Arena ELO
1485
Deep Architectural Overview
Kimi K2.7 Code HighSpeed serves the exact same model weights as K2.7 Code on dedicated high-throughput clusters. Delivering between 180 and 260 tokens/second, it eliminates coding wait times in CLI agents and interactive IDE completions.
Strengths & Considerations
Core Strengths
- Blazing generation speed (180 to 260 tokens/second)
- Zero capability degradation compared to standard K2.7 Code
- Full 256k context and 64k output window
Known Limitations
- Capacity can be allocated dynamically during heavy load
Token & API Pricing
Input Tokens (1M)$1.90
Output Tokens (1M)$8.00
Cached Input (1M)$0.3800
Pricing is verified directly against Moonshot AI's developer documentation and API rate sheets.
Similar & Alternative Models
Explore other frontier models from Moonshot AI and comparable reasoning engines.
Moonshot AI
Dedicated coding model delivering higher task success rates, tighter instruction following, and a 30% reduction in overthinking.
262.144K ctx$0.95 / 1M tok (Dedicated Coding)
Moonshot AI
General-purpose model supporting text, image, and video inputs, switchable thinking modes, and autonomous agent tasks over 256k context.
262.144K ctx$0.95 / 1M tok (Vision & Agentic)