Kimi K2 0711
kimi-k2Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for... Built by MoonshotAI.
Prices updated
Input price
$0.57
per 1M tokens · Standard
Output price
$2.30
per 1M tokens · Standard
Input limit
131K
tokens
Output limit
98K
tokens
Input formats
Output formats
Kimi K2 0711 price history
2 price records since 9/25/2026
Kimi K2 0711 cost calculator
$23/month
Standard pricing
Overview
What is Kimi K2 0711?
Kimi K2 0711 is a text & reasoning model from MoonshotAI. Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for... Its 131K context window and $0.57 input price make it a candidate for quality-focused production applications.
Benchmarks
Kimi K2 0711 benchmarks & speed
How Kimi K2 0711 scores on standardized evaluations, and where it lands among every model we track.
12.7
Intelligence Index
54tok/s
Output speed
Reasoning
GPQA Diamond
76.6%
Graduate-level scientific reasoning · top 60%
HLE
7.4%
Humanity's Last Exam · top 68%
Latency & design
- Time to first token
- 1.55s
Independent scores from Artificial Analysis and DesignArena · updated 10/5/2026. Higher is better; ranks compare against every model we track with that score.
Rates
Kimi K2 0711 pricing
Pricing is based on token usage. Provider-specific caching, batch, regional, and tool charges may affect the final cost.
Input · Standard
$0.57
Per 1M tokens
Cached input · Standard
Not available
No listed cached-input rate
Capabilities
Kimi K2 0711 Tools
Tools available when using Kimi K2 0711 through supported provider APIs.
Function calling
Supported
Structured outputs
Not supported
JSON mode
Not supported
Reasoning
Not supported
Built-in web search
Not supported
Log probabilities
Not supported
Deterministic seed
Supported
Parallel tool calls
Not supported
Prompt caching
Not supported
Strengths and limitations
Strengths
- Measured results (AA Intelligence 12.7) position it for demanding production work.
- A 131K context window covers most focused application workflows.
- Supports text & reasoning workloads in one model.
Limitations
- Generated tokens cost 4× more than input tokens, which matters for verbose responses.
- The 131K context window is smaller than several long-context alternatives.
- Arena Elo and MMLU-Pro are directional; test accuracy, latency and reliability on your own workload before committing.
Arena Elo, MMLU-Pro and pricing figures are illustrative; validate current vendor terms before purchase.
Same provider