Overview
Kimi K2 Thinking was released on November 6, 2025. Pricing starts at $0.400 per million input tokens and $1.75 per million output tokens. The model supports a context window of up to 262K tokens. API access is available through Moonshotai.
Context Window
262K
tokens
Pricing
Input$0.400
Output$1.75
per 1M tokens
Speed
Output87 tok/s
TTFT0.60s
median latency
Capabilities
ReasoningTools
Pricing Comparison
Compare Kimi K2 Thinking with 10 similar models by price.
Current Pricing (per 1M tokens)
11 models
Provider | Model | Input $/M | Output $/M | Context | Actions |
|---|---|---|---|---|---|
$0.400 | $1.750 | 262,144 | |||
AM | $0.300 | $2.500 | 1,000,000 | ||
QW | $0.300 | $1.500 | 128,000 | ||
$0.300 | $0.300 | 65,536 | |||
$0.300 | $0.400 | 8,192 | |||
Z | $0.350 | $1.500 | 202,752 | ||
Z | $0.350 | $1.550 | 131,072 | ||
$0.350 | $0.400 | 32,768 | |||
$0.390 | $1.900 | 262,144 | |||
QW | $0.400 | $1.200 | 1,000,000 | ||
Z | $0.400 | $1.500 | 202,752 |
* Some models use tiered pricing based on prompt length. Displayed prices are for prompts ≤ 200k tokens.
Compare Providers
Kimi K2 Thinking is available from multiple providers with different pricing and availability.
12
Providers
$0.400
Cheapest Input/M
$1.750
Cheapest Output/M
Chutes
Best Price
Provider Pricing
12 models
Provider | Input $/M | Output $/M | Uptime |
|---|---|---|---|
C Chutes Best Price | $0.400 | $1.750 | - |
D DeepInfra | $0.470 | $2.000 | 100.0% |
P Parasail | $0.500 | $2.500 | - |
S SiliconFlow | $0.550 | $2.500 | - |
A AtlasCloud | $0.600 | $2.500 | - |
N Nebius | $0.600 | $2.500 | - |
B BaseTen | $0.600 | $2.500 | - |
F Fireworks | $0.600 | $2.500 | - |
 Google | $0.600 | $2.500 | 100.0% |
N Novita | $0.600 | $2.500 | - |
 Moonshot AI | $1.150 | $8.000 | 98.9% |
T Together | $1.200 | $4.000 | - |
Provider pricing data sourced from OpenRouter and Helicone
Cost vs. Quality
Compare Kimi K2 Thinking's benchmark performance against all models.
X-axis:
Y-axis:
Loading chart...
Kimi K2 Thinking
Other models
Detailed Benchmark Scores
Intelligence
40.3 (94th pct)
Coding
33.5 (89th pct)
Math
94.7 (95th pct)
MMLU Pro
84.8 (91th pct)
GPQA
83.8 (95th pct)
LiveCodeBench
85.3 (96th pct)
AIME
-
Aider
-
Benchmark data from Artificial Analysis and HuggingFace Open LLM Leaderboard
Try Kimi K2 Thinking
Use our Calculator
Estimate your costs based on expected token usage.
Open Cost CalculatorTry in Playground
Test Kimi K2 Thinking directly in your browser.
Open PlaygroundFrequently Asked Questions
All Moonshotai Models
See pricing for all Moonshotai models.
View all Moonshotai models →