DeepSeek-V2.5 vs Kimi K2-Thinking-0905 Comparison

Comparing DeepSeek-V2.5 and Kimi K2-Thinking-0905 across benchmarks, pricing, and capabilities.

Want to compare interactively?Try the playground

Performance Benchmarks

Comparative analysis across standard metrics

1 benchmarks

DeepSeek-V2.5 outperforms in 0 benchmarks, while Kimi K2-Thinking-0905 is better at 1 benchmark (SWE-Bench Verified).

Kimi K2-Thinking-0905 significantly outperforms across most benchmarks.

Sat Mar 14 2026 • llm-stats.com

Arena Performance

Human preference votes

Pricing Analysis

Price comparison per million tokens

DeepSeek-V2.5 costs less

For input processing, DeepSeek-V2.5 ($0.14/1M tokens) is 3.4x cheaper than Kimi K2-Thinking-0905 ($0.47/1M tokens).

For output processing, DeepSeek-V2.5 ($0.28/1M tokens) is 7.1x cheaper than Kimi K2-Thinking-0905 ($2.00/1M tokens).

In conclusion, Kimi K2-Thinking-0905 is more expensive than DeepSeek-V2.5.*

* Using a 3:1 ratio of input to output tokens

Lowest available price from all providers

Sat Mar 14 2026 • llm-stats.com

DeepSeek-V2.5

Input tokens$0.14

Output tokens$0.28

Best providerDeepSeek

Kimi K2-Thinking-0905

Input tokens$0.47

Output tokens$2.00

Best providerDeepinfra

Notice missing or incorrect data?Start an Issue→

Model Size

Parameter count comparison

764.0B diff

Kimi K2-Thinking-0905 has 764.0B more parameters than DeepSeek-V2.5, making it 323.7% larger.

DeepSeek-V2.5

236.0Bparameters

Kimi K2-Thinking-0905

1000.0Bparameters

236.0B

DeepSeek-V2.5

1000.0B

Kimi K2-Thinking-0905

Context Window

Maximum input and output token capacity

Kimi K2-Thinking-0905 accepts 262,144 input tokens compared to DeepSeek-V2.5's 8,192 tokens. Kimi K2-Thinking-0905 can generate longer responses up to 262,144 tokens, while DeepSeek-V2.5 is limited to 8,192 tokens.

DeepSeek-V2.5

Input8,192 tokens

Output8,192 tokens

Kimi K2-Thinking-0905

Input262,144 tokens

Output262,144 tokens

Sat Mar 14 2026 • llm-stats.com

License

Usage and distribution terms

DeepSeek-V2.5 is licensed under deepseek, while Kimi K2-Thinking-0905 uses MIT.

License differences may affect how you can use these models in commercial or open-source projects.

DeepSeek-V2.5

deepseek

Open weights

Kimi K2-Thinking-0905

MIT

Open weights

Release Timeline

When each model was launched

DeepSeek-V2.5 was released on 2024-05-08, while Kimi K2-Thinking-0905 was released on 2025-09-05.

Kimi K2-Thinking-0905 is 16 months newer than DeepSeek-V2.5.

DeepSeek-V2.5

May 8, 2024

1.8 years ago

Kimi K2-Thinking-0905

Sep 5, 2025

6 months ago

1.3yr newer

Knowledge Cutoff

When training data ends

Neither model specifies a knowledge cutoff date.

Unable to compare the recency of their training data.

No cutoff dates available

Provider Availability

DeepSeek-V2.5 is available from DeepSeek, DeepInfra, Hyperbolic. Kimi K2-Thinking-0905 is available from DeepInfra, Novita, Fireworks. The availability of providers can affect quality of the model and reliability.