Models / Moonshot AI / Kimi K2.5
Moonshot AI · kimi-k2
Kimi K2.5
Earlier Kimi frontier model for long-context agents, coding, and multimodal work
$0.60 in · $3.00 out
per 1M tokens · provider rate closest to the median. No first-party Moonshot AI price was listed. The reference price is Amazon Bedrock's rate, the provider closest to the median.
Provider input prices run from $0.38 to $0.72 per 1M tokens. Output prices run from $1.98 to $3.60.
- Context
- 262,144
- Max output
- 262,144
- Cache read
- —
- Cache write
- —
- Reasoning
- Yes
- Tool calls
- Yes
- Structured output
- Yes
- Vision
- Yes
- Open weights
- Yes
- License
- —
- Released
- Jan 1, 2026
- Updated in source
- Jan 1, 2026
- Knowledge
- 2025-01
- Providers
- 25
Providers
| Provider | Input | Output | Cache read | Cache write | Status |
|---|---|---|---|---|---|
| NanoGPT | $0.38 | $2.00 | $0.07 | — | — |
| DevPass | $0.41 | $1.98 | $0.23 | — | — |
| Auriko | $0.50 | $2.80 | — | — | — |
| Eden AI | $0.50 | $2.80 | $0.13 | — | — |
| OpenRouter | $0.50 | $2.50 | $0.15 | — | — |
| TensorX | $0.50 | $2.80 | $0.13 | $0.63 | — |
| Venice AI | $0.56 | $3.50 | $0.22 | — | — |
| LLM Gateway | $0.57 | $3.01 | — | — | — |
| Melious | $0.58 | $2.96 | $0.14 | — | — |
| Amazon Bedrockreference | $0.60 | $3.00 | — | — | — |
| Azure Cognitive Services | $0.60 | $3.00 | — | — | — |
| DaoXE | $0.60 | $3.00 | $0.10 | — | — |
| HPC-AI | $0.60 | $3.00 | $0.10 | — | — |
| Jalapeno Cloud | $0.60 | $3.00 | — | — | — |
| Kilo Gateway | $0.60 | $3.00 | — | — | — |
| Merge Gateway | $0.60 | $3.00 | $0.10 | — | — |
| Novita AI | $0.60 | $3.00 | $0.10 | — | — |
| Ofox | $0.60 | $3.00 | $0.10 | — | — |
| OrcaRouter | $0.60 | $3.00 | $0.10 | $0 | — |
| Vercel AI Gateway | $0.60 | $3.00 | — | — | — |
| 302.AI | $0.66 | $3.30 | — | — | — |
| Requesty | $0.72 | $3.60 | $0.72 | $0.72 | — |
| Alibaba Token Plan | $0 | $0 | $0 | $0 | — |
| Alibaba Token Plan | $0 | $0 | $0 | $0 | — |
| SCNet Token Plan | $0 | $0 | $0 | — | — |
Jobs this model qualifies for
- Coding agents — clears the bar
- Long-document Q&A — clears the bar
- Cheapest summarization — clears the bar