Price Per TokenPrice Per Token
Moonshotai
Moonshotai
vs
Moonshotai
Moonshotai

Kimi K2 0905 (exacto) vs Kimi K2 Thinking

A detailed comparison of pricing, benchmarks, and capabilities

OpenClaw

Best LLMs for OpenClaw Vote for which model works best with OpenClaw

100 out of our 304 tracked models have had a price change in February.

Get our weekly newsletter on pricing changes, new releases, and tools.

Key Takeaways

Kimi K2 0905 (exacto) wins:

  • Cheaper input tokens

Kimi K2 Thinking wins:

  • Cheaper output tokens
  • Faster response time
  • Higher intelligence benchmark
  • Better at coding
  • Better at math
  • Has reasoning mode
Price Advantage
Kimi K2 0905 (exacto)
Benchmark Advantage
Kimi K2 Thinking
Context Window
Kimi K2 Thinking
Speed
Kimi K2 Thinking

Pricing Comparison

Price Comparison

MetricKimi K2 0905 (exacto)Kimi K2 ThinkingWinner
Input (per 1M tokens)$0.39$0.40 Kimi K2 0905 (exacto)
Output (per 1M tokens)$1.90$1.75 Kimi K2 Thinking
Using a 3:1 input/output ratio, Kimi K2 Thinking is 4% cheaper overall.

Kimi K2 0905 (exacto) Providers

Chutes $0.39 (Cheapest)
SiliconFlow $0.40
DeepInfra $0.40
Parasail $0.59
AtlasCloud $0.60

Kimi K2 Thinking Providers

Chutes $0.40 (Cheapest)
DeepInfra $0.47
Parasail $0.50
SiliconFlow $0.55
AtlasCloud $0.60

Benchmark Comparison

6
Benchmarks Compared
0
Kimi K2 0905 (exacto) Wins
6
Kimi K2 Thinking Wins

Benchmark Scores

BenchmarkKimi K2 0905 (exacto)Kimi K2 ThinkingWinner
Intelligence Index
Overall intelligence score
30.840.7
Coding Index
Code generation & understanding
25.934.8
Math Index
Mathematical reasoning
57.394.7
MMLU Pro
Academic knowledge
81.984.8
GPQA
Graduate-level science
76.783.8
LiveCodeBench
Competitive programming
61.085.3
Kimi K2 Thinking significantly outperforms in coding benchmarks.

Cost vs Quality

X-axis:
Y-axis:
Loading chart...
Kimi K2 0905 (exacto)
Other models

Context & Performance

Context Window

Kimi K2 0905 (exacto)
262,144
tokens
Max output: 262,144 tokens
Kimi K2 Thinking
262,144
tokens
Max output: 65,535 tokens

Speed Performance

MetricKimi K2 0905 (exacto)Kimi K2 ThinkingWinner
Tokens/second51.7 tok/s95.3 tok/s
Time to First Token0.54s0.60s
Kimi K2 Thinking responds 84% faster on average.

Capabilities

Feature Comparison

FeatureKimi K2 0905 (exacto)Kimi K2 Thinking
Vision (Image Input)
Tool/Function Calls
Reasoning Mode
Audio Input
Audio Output
PDF Input
Prompt Caching
Web Search

License & Release

PropertyKimi K2 0905 (exacto)Kimi K2 Thinking
LicenseProprietaryProprietary
AuthorMoonshotaiMoonshotai
ReleasedSep 2025Nov 2025

Kimi K2 0905 (exacto) Modalities

Input
text
Output
text

Kimi K2 Thinking Modalities

Input
text
Output
text

Related Comparisons

Compare Kimi K2 0905 (exacto) with:

Compare Kimi K2 Thinking with:

Frequently Asked Questions

Kimi K2 0905 (exacto) has cheaper input pricing at $0.39/M tokens. Kimi K2 Thinking has cheaper output pricing at $1.75/M tokens.
Kimi K2 Thinking scores higher on coding benchmarks with a score of 34.8, compared to Kimi K2 0905 (exacto)'s score of 25.9.
Kimi K2 0905 (exacto) has a 262,144 token context window, while Kimi K2 Thinking has a 262,144 token context window.
Kimi K2 0905 (exacto) does not support vision. Kimi K2 Thinking does not support vision.