The AI arena is free today

Open Superagent

Kimi K2 Instruct vs Kimi K2.8 Preview

Comparing Kimi K2 Instruct and Kimi K2.8 Preview across benchmarks, pricing, and capabilities.

Moonshot AI · Moonshot AI · Updated for 2026

Which is better?

Kimi K2 Instruct and Kimi K2.8 Preview trade strengths across price, capabilities, and technical limits. The better choice depends on the workload.

Kimi K2.8 Preview also accepts a larger context window (1,048,576 input tokens), making it the stronger choice for long documents and large codebases.

Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.

Choose Kimi K2 Instruct

  • you need open weights you can self-host or fine-tune

Choose Kimi K2.8 Preview

  • you process long inputs — it offers a 1,048,576 token context window
  • you want the most recent training data — it shipped Sep 2026

At a glance

The differences that matter most.

Benchmark wins
Input price
$0.50 / M
— / M
Output price
$0.50 / M
— / M
Context window
200,000
1,048,576

Individual benchmarks

38 reported for Kimi K2 Instruct · 0 for Kimi K2.8 Preview

No common benchmarks found

Kimi K2 Instruct and Kimi K2.8 Previewdon't have any common benchmark datasets to compare. They may have been evaluated on different testing suites.

Human preference

Blind head-to-head votes and playground preference scores

Context Window

Maximum input and output token capacity

Kimi K2.8 Preview accepts 1,048,576 input tokens compared to Kimi K2 Instruct's 200,000 tokens. Only Kimi K2 Instruct specifies output context (200,000 tokens).

Moonshot AI
Kimi K2 Instruct
Input200,000 tokens
Output200,000 tokens
Moonshot AI
Kimi K2.8 Preview
Input1,048,576 tokens
Output- tokens
Wed Sep 16 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Kimi K2.8 Preview supports multimodal inputs, whereas Kimi K2 Instruct does not.

Kimi K2.8 Preview can handle both text and other forms of data like images, making it suitable for multimodal applications.

Kimi K2 Instruct

Text
Images
Audio
Video

Kimi K2.8 Preview

Text
Images
Audio
Video

License

Usage and distribution terms

Kimi K2 Instruct is licensed under MIT, while Kimi K2.8 Preview uses a proprietary license.

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

Kimi K2 Instruct

MIT

Open weights

Kimi K2.8 Preview

Proprietary

Closed source

Release Timeline

When each model was launched

Kimi K2 Instruct was released on 2025-07-11, while Kimi K2.8 Preview was released on 2026-09-11.

Kimi K2.8 Preview is 14 months newer than Kimi K2 Instruct.

Kimi K2 Instruct

Jul 11, 2025

1.2 years ago

Kimi K2.8 Preview

Sep 11, 2026

4 days ago

1.2yr 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

Kimi K2 Instruct is available from Fireworks, Novita. Kimi K2.8 Preview is available from Moonshot AI.

Kimi K2 Instruct

fireworks logo
Fireworks
Input Price:Input: $0.50/1MOutput Price:Output: $0.50/1M
novita logo
Novita
Input Price:Input: $0.57/1MOutput Price:Output: $2.30/1M

Kimi K2.8 Preview

moonshot logo
Unknown Organization
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion

Judge for yourself.

Run your own prompts against Kimi K2 Instruct and Kimi K2.8 Preview side-by-side, then vote on the output you prefer.

Kimi K2 Instruct
✓ Preferred
Kimi K2.8 Preview
Open in Playground

FAQ

Common questions about Kimi K2 Instruct vs Kimi K2.8 Preview.

Which is better, Kimi K2 Instruct or Kimi K2.8 Preview?

Kimi K2 Instruct (Moonshot AI) and Kimi K2.8 Preview (Moonshot AI) each have strengths in different areas. Compare their benchmark scores, pricing, context windows, and capabilities above to determine which fits your needs.

How does Kimi K2 Instruct compare to Kimi K2.8 Preview in benchmarks?

Kimi K2 Instruct scores MATH-500: 97.4%, GSM8k: 97.3%, CBNSL: 95.6%, HumanEval: 93.3%, MMLU-Redux: 92.7%.

What are the context window sizes for Kimi K2 Instruct and Kimi K2.8 Preview?

Kimi K2 Instruct supports 200K tokens and Kimi K2.8 Preview supports 1.0M tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between Kimi K2 Instruct and Kimi K2.8 Preview?

Key differences include context window (200K vs 1.0M), multimodal support (no vs yes), licensing (MIT vs Proprietary). See the full comparison above for benchmark-by-benchmark results.