Kimi K2.5 by Moonshot AI demonstrates competitive pricing. View detailed benchmark data including scores across coding, math, reasoning, speed, and cost metrics.
Specifications last checked against the provider on . Benchmark scores carry their own source, linked beside each number.
Coding Benchmarks
Artificial Analysis composite coding score
Artificial Analysis (via OpenRouter)Human preference ELO for building a working web page from a brief
Design Arena (via OpenRouter)Human preference ELO for building things — websites, UI, games, charts, SVG
Design Arena (via OpenRouter)Reasoning Benchmarks
Multi-turn service agent making tool calls under strict policy constraints
OpenRouter (measured)Speed Benchmarks
Cost Benchmarks
Cost per 1M cached input tokens — the price that actually applies to a long agent conversation
OpenRouter APIContext Benchmarks
Available from 44 providers
The same model costs different amounts depending on who serves it. You can bring your own key for 8 of these — connect it here.
| Provider | Input / 1M | Output / 1M | Cached in | Context | Your key |
|---|---|---|---|---|---|
| Alibaba Coding Plan | $0 | $0 | $0 | 262K | — |
| Alibaba Coding Plan (China) | $0 | $0 | $0 | 262K | — |
| Alibaba Token Plan | $0 | $0 | $0 | 262K | — |
| Alibaba Token Plan (China) | $0 | $0 | $0 | 262K | — |
| SCNet Token Plan | $0 | $0 | $0 | 262K | — |
| Tencent Coding Plan (China) | $0 | $0 | $0 | 262K | — |
| NanoGPT | $0.3 | $1.9 | $0.15 | 256K | — |
| DevPass (LLM Gateway) | $0.405 | $1.98 | $0.225 | 262K | — |
| Deep Infra | $0.45 | $2.25 | $0.07 | 262K | Supported |
| Meganova | $0.45 | $2.8 | — | 262K | — |
| OpenRouter | $0.45 | $2.25 | $0.07 | 262K | Supported |
| Cortecs | $0.495 | $2.768 | $0.124 | 262K | — |
| Auriko | $0.5 | $2.8 | — | 262K | — |
| DigitalOcean | $0.5 | $2.7 | $0.203 | 262K | — |
| TensorX | $0.5 | $2.8 | $0.125 | 262K | — |
| Together AI | $0.5 | $2.8 | — | 262K | Supported |
| Charm Hyper | $0.5584 | $2.935 | $0.2792 | 262K | — |
| Venice AI | $0.56 | $3.5 | $0.22 | 256K | — |
| ZenMux | $0.58 | $3.02 | $0.1 | 262K | — |
| Abacus | $0.6 | $3 | — | 262K | — |
| AIHubMix | $0.6 | $3 | $0.1 | 262K | — |
| Amazon Bedrock | $0.6 | $3 | — | 262K | Supported |
| Azure | $0.6 | $3 | — | 262K | Supported |
| Azure Cognitive Services | $0.6 | $3 | — | 262K | — |
| Baseten | $0.6 | $3 | $0.12 | 262K | Supported |
| DaoXE | $0.6 | $3 | $0.1 | 262K | — |
| Eden AI | $0.6 | $3 | — | 262K | — |
| FrogBot | $0.6 | $3 | $0.1 | 256K | — |
| HPC-AI | $0.6 | $3 | $0.1 | 256K | — |
| Hugging Face | $0.6 | $3 | $0.1 | 262K | Supported |
| Jalapeno Cloud | $0.6 | $3 | — | 262K | — |
| Jiekou.AI | $0.6 | $3 | — | 262K | — |
| Kilo Gateway | $0.6 | $3 | $0.1 | 262K | — |
| LLM Gateway | $0.6 | $3 | $0.1 | 262K | — |
| Merge Gateway | $0.6 | $3 | $0.1 | 262K | — |
| NovitaAI | $0.6 | $3 | $0.1 | 262K | — |
| Ofox | $0.6 | $3 | $0.1 | 262K | — |
| OpenCode Go | $0.6 | $3 | $0.1 | 262K | — |
| OpenCode Zen | $0.6 | $3 | $0.08 | 262K | — |
| OrcaRouter | $0.6 | $3 | $0.1 | 262K | — |
| Poe | $0.6 | $3 | $0.1 | 128K | — |
| Vercel AI Gateway | $0.6 | $3 | $0.1 | 262K | Supported |
| 302.AI | $0.66 | $3.3 | — | 262K | — |
| Ollama Cloud | — | — | — | 262K | — |
Kimi K2.5 — Benchmark Scores Overview
Scores normalized to percentage scale for visual comparison. ELO scores mapped to 0-100 range (1100-1500).
Compare Kimi K2.5 With
Kimi K2.5 — Frequently Asked Questions
How much does Kimi K2.5 cost?
Kimi K2.5 costs $0.45 per 1M input tokens and $2.3 per 1M output tokens. This makes it one of the more affordable models.
How fast is Kimi K2.5?
Kimi K2.5 generates output at 45 tokens per second, which is slower, prioritizing quality over speed compared to other models. The time to first token is 1210 ms.
What is the context window of Kimi K2.5?
Kimi K2.5 has a context window of 262K tokens. This determines how much text, conversation history, and code the model can process in a single request.
Who created Kimi K2.5?
Kimi K2.5 was created by Moonshot AI. It is classified as a flagship model in our catalogue.
Is Kimi K2.5 open source?
No, Kimi K2.5 is a proprietary model. It is available through Moonshot AI's API and compatible providers.