Kimi K2.8 Preview

Tool callingReasoningImage inputVideo input

Website

Kimi coding model with more efficient thinking and up to 1M context, available through Kimi Code

Context: 1.0M
Released: 1mo ago

Sources:models.dev

Benchmarks

DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.

Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.

No benchmark results have been matched to this model yet.

Specifications

Developer: Moonshot AI
Model family: Kimi
Type: Language model
Predecessor: —
Successor: —
Released: September 11, 2026
Model ID: moonshotai/kimi-k2.8-preview
Openness: Closed
License: —
Input modalities: text, image, video
Output modalities: text
Modality: text+image+video->text
Hugging Face: —
Source freshness: Metadata synced Oct 8, 2026, 10:17 PM UTC

Additional source evidence

Source model: moonshotai/kimi-k2.8-preview
Source family: kimi-k2
Last updated: 2026-09-11
Model context: 1.0M
Open weights: No
File attachments: Yes
Reasoning: Yes
Tool calling: Yes

Complete source record (JSON)

{
  "id": "moonshotai/kimi-k2.8-preview",
  "name": "Kimi K2.8 Preview",
  "description": "Kimi coding model with more efficient thinking and up to 1M context, available through Kimi Code",
  "family": "kimi-k2",
  "last_updated": "2026-09-11",
  "attachment": true,
  "reasoning": true,
  "tool_call": true,
  "modalities": {
    "input": [
      "text",
      "image",
      "video"
    ],
    "output": [
      "text"
    ]
  },
  "limit": {
    "context": 1048576
  },
  "release_date": "2026-09-11",
  "open_weights": false
}

Infrastructure

Provider availability

All providers

Provider endpoint data will appear after this model's first OpenRouter endpoint sync.