Kimi K2 0905 vs Kimi K2 Instruct
Kimi K2 0905 significantly outperforms across most benchmarks. Kimi K2 Instruct is 2.1x cheaper per token.
Moonshot AI · Moonshot AI · Updated for 2026
Which is better?
Kimi K2 0905 outperforms in 5 benchmarks (AIME 2024, GPQA, HumanEval, MMLU, MMLU-Pro), while Kimi K2 Instruct is better at 0 benchmarks. Kimi K2 0905 significantly outperforms across most benchmarks.
On price, Kimi K2 Instruct is roughly 2.1x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.
Kimi K2 0905 also accepts a larger context window (262,144 input tokens), making it the stronger choice for long documents and large codebases.
Based on current benchmark, pricing, and model metadata for 2026.
Choose Kimi K2 0905
- you want the strongest raw capability — it leads on 5 of 5 shared benchmarks
- you process long inputs — it offers a 262,144 token context window
- you want the most recent training data — it shipped Sep 2025
Choose Kimi K2 Instruct
- cost matters — it's about 2.1x cheaper per token
- you need open weights you can self-host or fine-tune
At a glance
The differences that matter most.
Performance Benchmarks
Comparative analysis across standard metrics
Kimi K2 0905 outperforms in 5 benchmarks (AIME 2024, GPQA, HumanEval, MMLU, MMLU-Pro), while Kimi K2 Instruct is better at 0 benchmarks.
Kimi K2 0905 significantly outperforms across most benchmarks.
Arena Performance
Playground indexes and blind preference scores
Pricing Analysis
Price comparison per million tokens
For input processing, Kimi K2 0905 ($0.60/1M tokens) is 1.2x more expensive than Kimi K2 Instruct ($0.50/1M tokens).
For output processing, Kimi K2 0905 ($2.50/1M tokens) is 5.0x more expensive than Kimi K2 Instruct ($0.50/1M tokens).
In conclusion, Kimi K2 0905 is more expensive than Kimi K2 Instruct.*
* Using a 3:1 ratio of input to output tokens
Model Size
Parameter count comparison
Kimi K2 Instruct has 0.0B more parameters than Kimi K2 0905, making it 0.0% larger.
Context Window
Maximum input and output token capacity
Kimi K2 0905 accepts 262,144 input tokens compared to Kimi K2 Instruct's 200,000 tokens. Kimi K2 0905 can generate longer responses up to 262,144 tokens, while Kimi K2 Instruct is limited to 200,000 tokens.
License
Usage and distribution terms
Kimi K2 0905 is licensed under a proprietary license, while Kimi K2 Instruct uses MIT.
License differences may affect how you can use these models in commercial or open-source projects.
Proprietary
Closed source
MIT
Open weights
Release Timeline
When each model was launched
Kimi K2 0905 was released on 2025-09-05, while Kimi K2 Instruct was released on 2025-07-11.
Kimi K2 0905 is 2 months newer than Kimi K2 Instruct.
Sep 5, 2025
11 months ago
1mo newerJul 11, 2025
1.1 years ago
Knowledge Cutoff
When training data ends
Neither model specifies a knowledge cutoff date.
Unable to compare the recency of their training data.
Provider Availability
Kimi K2 0905 is available from Novita. Kimi K2 Instruct is available from Fireworks, Novita.
Kimi K2 0905
Kimi K2 Instruct
Outputs Comparison
Judge for yourself.
Run your own prompts against Kimi K2 0905 and Kimi K2 Instruct side-by-side, then vote on the output you prefer.
FAQ
Common questions about Kimi K2 0905 vs Kimi K2 Instruct.