Moonshot AI
Kimi K2.5
Earlier Kimi frontier model for long-context agents, coding, and multimodal work
Model facts
- Context window
- 262K tokens
- Maximum output
- 262K tokens
- Cheapest paid input
- $0.3 per 1M tokens
- Cheapest paid output
- $1.9 per 1M tokens
- Open weights
- yes
- Providers
- 51
Capabilities and modalities
reasoning, tool calling, structured output, attachments, temperature control, open weights, text, image, video.
Local hardware estimate
At 4K context: Q4_K_M 629.5 GiB, Q8_0 1107.7 GiB, F16 2004.2 GiB working memory.
- Parameters
- 1026.9 billion
- Architecture
- kimik25
- Model license
- other
Planning estimate adapted from the MIT-licensed whichllm estimator using metadata from Hugging Face; not a vendor minimum requirement.
Artificial Analysis benchmarks
Compare this model on the full LLM benchmark leaderboard.
| Configuration | AAI | Coding | Math | Output tokens/s |
|---|---|---|---|---|
| Reasoning | 36.0 | 46.8 | not measured | not measured |
| Non-reasoning | 30.1 | not measured | not measured | not measured |
Observed price history
- 2026-08-24: $0.3 input / $1.9 output per 1M tokens
API providers
- Alibaba Coding Plan — model id kimi-k2.5; free input / free output per 1M tokens; provider documentation
- Alibaba Coding Plan (China) — model id kimi-k2.5; free input / free output per 1M tokens; provider documentation
- Alibaba Token Plan — model id kimi-k2.5; free input / free output per 1M tokens; provider documentation
- Alibaba Token Plan (China) — model id kimi-k2.5; free input / free output per 1M tokens; provider documentation
- SCNet Token Plan — model id Kimi-K2.5; free input / free output per 1M tokens; provider documentation
- Tencent Coding Plan (China) — model id kimi-k2.5; free input / free output per 1M tokens; provider documentation
- NanoGPT — model id moonshotai/kimi-k2.5; $0.3 input / $1.9 output per 1M tokens; provider documentation
- DevPass (LLM Gateway) — model id kimi-k2.5; $0.405 input / $1.98 output per 1M tokens; provider documentation
- LLM Gateway (EmberCloud) — model id embercloud/kimi-k2.5; $0.405 input / $1.98 output per 1M tokens; provider documentation
- Deep Infra — model id moonshotai/Kimi-K2.5; $0.45 input / $2.25 output per 1M tokens; provider documentation
- Eden AI — model id deepinfra/moonshotai/Kimi-K2.5; $0.45 input / $2.25 output per 1M tokens; provider documentation
- LLM Gateway (DeepInfra) — model id deepinfra/kimi-k2.5; $0.45 input / $2.25 output per 1M tokens; provider documentation
- OpenRouter — model id moonshotai/kimi-k2.5; $0.45 input / $2.25 output per 1M tokens; provider documentation
- DigitalOcean — model id kimi-k2.5; $0.5 input / $2.7 output per 1M tokens; provider documentation
- Meganova — model id moonshotai/Kimi-K2.5; $0.45 input / $2.8 output per 1M tokens; provider documentation
- Cortecs — model id kimi-k2.5; $0.495 input / $2.77 output per 1M tokens; provider documentation
- Auriko — model id kimi-k2.5; $0.5 input / $2.8 output per 1M tokens; provider documentation
- Eden AI — model id tensorx/moonshotai/kimi-k2.5; $0.5 input / $2.8 output per 1M tokens; provider documentation
- TensorX — model id moonshotai/kimi-k2.5; $0.5 input / $2.8 output per 1M tokens; provider documentation
- Together AI — model id moonshotai/Kimi-K2.5; $0.5 input / $2.8 output per 1M tokens; provider documentation
- Charm Hyper — model id kimi-k2.5; $0.528 input / $2.79 output per 1M tokens; provider documentation
- LLM Gateway (Alibaba Cloud) — model id alibaba/kimi-k2.5; $0.574 input / $3.01 output per 1M tokens; provider documentation
- AIHubMix — model id kimi-k2.5; $0.6 input / $3 output per 1M tokens; provider documentation
- Abacus — model id kimi-k2.5; $0.6 input / $3 output per 1M tokens; provider documentation
- Amazon Bedrock — model id moonshotai.kimi-k2.5; $0.6 input / $3 output per 1M tokens; provider documentation
- Azure — model id kimi-k2.5; $0.6 input / $3 output per 1M tokens; provider documentation
- Azure Cognitive Services — model id kimi-k2.5; $0.6 input / $3 output per 1M tokens; provider documentation
- Baseten — model id moonshotai/Kimi-K2.5; $0.6 input / $3 output per 1M tokens; provider documentation
- DaoXE — model id kimi-k2.5; $0.6 input / $3 output per 1M tokens; provider documentation
- Eden AI — model id amazon/moonshotai.kimi-k2.5; $0.6 input / $3 output per 1M tokens; provider documentation
- FrogBot — model id kimi-k2.5; $0.6 input / $3 output per 1M tokens; provider documentation
- HPC-AI — model id moonshotai/kimi-k2.5; $0.6 input / $3 output per 1M tokens; provider documentation
- Hugging Face — model id moonshotai/Kimi-K2.5; $0.6 input / $3 output per 1M tokens; provider documentation
- Jalapeno Cloud — model id Kimi-K2.5; $0.6 input / $3 output per 1M tokens; provider documentation
- Jiekou.AI — model id moonshotai/kimi-k2.5; $0.6 input / $3 output per 1M tokens; provider documentation
- Kilo Gateway — model id moonshotai/kimi-k2.5; $0.6 input / $3 output per 1M tokens; provider documentation
- LLM Gateway (Moonshot AI) — model id moonshot/kimi-k2.5; $0.6 input / $3 output per 1M tokens; provider documentation
- Merge Gateway — model id moonshot/kimi-k2.5; $0.6 input / $3 output per 1M tokens; provider documentation
- Moonshot AI — model id kimi-k2.5; $0.6 input / $3 output per 1M tokens; provider documentation
- Moonshot AI (China) — model id kimi-k2.5; $0.6 input / $3 output per 1M tokens; provider documentation
- NovitaAI — model id moonshotai/kimi-k2.5; $0.6 input / $3 output per 1M tokens; provider documentation
- Ofox — model id moonshotai/kimi-k2.5; $0.6 input / $3 output per 1M tokens; provider documentation
- OpenCode Go — model id kimi-k2.5; $0.6 input / $3 output per 1M tokens; provider documentation
- OpenCode Zen — model id kimi-k2.5; $0.6 input / $3 output per 1M tokens; provider documentation
- OrcaRouter — model id kimi/kimi-k2.5; $0.6 input / $3 output per 1M tokens; provider documentation
- Poe — model id novita/kimi-k2.5; $0.6 input / $3 output per 1M tokens; provider documentation
- Vercel AI Gateway — model id moonshotai/kimi-k2.5; $0.6 input / $3 output per 1M tokens; provider documentation
- ZenMux — model id moonshotai/kimi-k2.5; $0.58 input / $3.02 output per 1M tokens; provider documentation
- CrossModel — model id moonshot/kimi-k2.5; $0.62 input / $3.3 output per 1M tokens; provider documentation
- Venice AI — model id kimi-k2-5; $0.56 input / $3.5 output per 1M tokens; provider documentation
- Ollama Cloud — model id kimi-k2.5; not published input / not published output per 1M tokens; provider documentation