Model
Kimi K2.5
Earlier Kimi frontier model for long-context agents, coding, and multimodal work
12 providersreleased knowledge cutoff 2025-01open weights
$0.3
best input /M · NanoGPT
$1.90
best output /M
262K
context window
262K
max output
Compare providers (sorted by listed input price)
| Provider | Input /M | Output /M | Cache read /M | Cache write /M | Context | Capabilities | Status | Updated |
|---|---|---|---|---|---|---|---|---|
| NanoGPT moonshotai/kimi-k2.5 | $0.3 | $1.90 | $0.15 | — | 256K | no reasoningtoolsno structuredvision | Jan 1, 2026 | |
| OpenRouter moonshotai/kimi-k2.5 | $0.45 | $2.25 | $0.07 | — | 262K | reasoningtoolsstructuredvision | Jan 1, 2026 | |
| TensorX moonshotai/kimi-k2.5 | $0.5 | $2.80 | $0.125 | $0.625 | 262K | reasoningtoolsstructuredvision | Jan 1, 2026 | |
| ZenMux moonshotai/kimi-k2.5 | $0.58 | $3.02 | $0.1 | — | 262K | reasoningtoolsno structuredvision | Jan 27, 2026 | |
| HPC-AI moonshotai/kimi-k2.5 | $0.6 | $3 | $0.1 | — | 256K | reasoningtoolsstructuredvision | Jan 1, 2026 | |
| Jiekou.AI moonshotai/kimi-k2.5 | $0.6 | $3 | — | — | 262K | reasoningtoolsstructuredvision | Jan 1, 2026 | |
| Moonshot AI kimi-k2.5 | $0.6 | $3 | $0.1 | — | 262K | reasoningtoolsstructuredno vision | Jan 1, 2026 | |
| Ofox moonshotai/kimi-k2.5 | $0.6 | $3 | $0.1 | — | 262K | reasoningtoolsstructuredvision | Jan 1, 2026 | |
| Vercel AI Gateway moonshotai/kimi-k2.5 | $0.6 | $3 | $0.1 | — | 262K | reasoningtoolsstructuredvision | Jan 1, 2026 | |
| NovitaAI moonshotai/kimi-k2.5 | $0.6 | $3 | $0.1 | — | 262K | reasoningtoolsstructuredvision | Jan 27, 2026 | |
| Kilo Gateway moonshotai/kimi-k2.5 | $0.6 | $3 | $0.1 | — | 262K | reasoningtoolsstructuredvision | Jan 1, 2026 | |
| Qiniu moonshotai/kimi-k2.5 | — | — | — | — | 256K | no reasoningtoolsno structuredvision | Jan 28, 2026 |
Price badge
https://models.sutraworks.ai/badge/moonshotai/kimi-k2.5.svgLive SVG, regenerated on every hourly sync — paste it into a README to always show the current cheapest listed price. Updates when prices change; no build step needed on your side.
Benchmarks
- SWE-Bench Verified ↗(resolved)report ↗70.8
- SWE-Atlas Codebase QnA(score)report ↗13.1
- SWE-Atlas Refactoring(score)report ↗20.95
- SWE-Atlas Test Writing(score)report ↗25.77
Weights
Prices are per million tokens (USD). “—” means the provider does not publicly list a price for this model. Data from models.dev; verify with the provider before purchasing.