Context Window
262,144
Input tokens
Full-context input ≈ $0.16
Model Cost Profile
Developer: moonshotai· Tokenizer: Other · Quantization: bf16
Canonical ID: moonshotai/kimi-k2-thinking-20251106
Pricing updated Apr 24, 2026
Live Pricing
Input: $0.6000
Output: $2.50
Last synced Apr 24, 2026 · MMLU score via public benchmark data
MoonshotAI's Kimi K2 Thinking model features an extensive context window of 131,072 tokens, making it ideal for complex tasks such as long-form content generation, detailed data analysis, and comprehensive conversational AI applications. With an input price of $0.47 per million tokens and an output price of $2.00 per million tokens, teams can effectively budget for projects that require significant text processing and generation capabilities. This model is particularly suited for enterprises needing to handle large datasets or create intricate narratives while managing operational costs efficiently.
Context Window
262,144
Input tokens
Full-context input ≈ $0.16
Max Output
262,144
Completion tokens
Input Price / 1M
$0.6000
Prompt tokens
Output Price / 1M
$2.50
Completion tokens
Top Benchmark
84.8
MMLU score — highest of MMLU, GPQA, MATH, HumanEval
Evaluation scores for MoonshotAI: Kimi K2 Thinking. The “Top Benchmark” shown above is the highest score across MMLU, GPQA, MATH & HumanEval.
Price History
Current Input / 1M
$0.6000
Current Output / 1M
$2.50
Performance History
Current TPS
0.00
Current Latency
0ms
Uptime
99.3%
| Usage Type | Price / 1M Tokens |
|---|---|
| Input (Prompt) | $0.6000 |
| Output (Completion) | $2.50 |
| Cache Read | $0.1500 |
Estimate monthly spend for MoonshotAI: Kimi K2 Thinking based on your workload.
Estimated Monthly Cost
$45
25M input + 12M output tokens
Quick links for cost-down decisions before production rollout.