Kimi K2.5
ModelOpen sourceActiveby Moonshot AI · family “kimi-k”
Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed... (description from the OpenRouter listing)
in: textin: imageout: textReasoningTool useStructured output
Epoch Capabilities Index
148.1 #58 of 268
90% CI 146.2 – 149.3
Released
27 Jan 2026
Context window
262K tokens
Max output
236K tokens
Input $ / 1M tokens
$0.45
Output $ / 1M tokens
$2.25
Cached input $ / 1M
$0.070
Each benchmark shown separately with its own source
Benchmark results (12)
| Benchmark | Domain | Score | vs best recorded | Setting | Run | Source |
|---|---|---|---|---|---|---|
| CL-bench Life | long-context | 13.2% | 59% | — | — | External ↗ |
| CL-bench | long-context | 19.3% | 69% | — | — | External ↗ |
| SimpleQA Verified | knowledge | 34.3% ±1.5 | 45% | — | 27 Aug 2026 | Eval log ↗ |
| Terminal Bench | agents | 43.2% ±2.9 | 51% | agent: Terminus 2 | 27 Jan 2026 | External ↗ |
| ARC-AGI-2 | reasoning | 11.8% | 12% | — | — | External ↗ |
| Fiction.LiveBench | long-context | 86.1% | 89% | — | — | External ↗ |
| HLE | knowledge | 24.4% | 44% | — | — | External ↗ |
| WeirdML | coding | 45.6% ±0.0 | 49% | — | — | External ↗ |
| SimpleBench | reasoning | 46.8% | 57% | — | — | External ↗ |
| SWE-Bench verified | coding | 73.8% ±2.0 | 88% | — | 17 Feb 2026 | Eval log ↗ |
| OSWorld | agents | 63.3% | 88% | agent: Kimi-K2.5 | — | External ↗ |
| ARC-AGI | reasoning | 65.3% | 66% | — | — | External ↗ |
Source: Epoch AI Benchmarking Hub (CC BY 4.0). “External” rows are leaderboard results Epoch collects from third parties. Best reported setting per benchmark is shown.
API list price over time
Price history
$ per 1M tokens
9 recorded prices on 1 Feb 2026 (OpenRouter listing + Internet Archive snapshots); re-read on every data refresh, most recently 39m ago. Steps show when the price changed.
Events
- BenchmarkEpoch AI evaluates Kimi K2.5Epoch AI Benchmarking Hub
- Open releaseMoonshotAI releases Kimi K2.5Epoch AI Benchmarking Hub