Kimi K2.5
Kimi K2.5 is served by 8 providers that kRouter can route to, with a 262K-token context window and pricing from $1.20 per 1M input tokens. Because more than one provider offers it, the price you pay depends on which one you route to — the same request, the same model, different bills.
Where to get Kimi K2.5
| Provider | Route as |
|---|---|
| Cursor IDE | cu/kimi-k2.5 |
| OpenCode Go | opencode-go/kimi-k2.5 |
| Kimchi | kimchi/kimi-k2.5 |
| CodeBuddy CN | cbcn/kimi-k2.5 |
| Kimi | kimi/kimi-k2.5 |
| Alibaba | alicode/kimi-k2.5 |
| Alibaba Intl | alicode-intl/kimi-k2.5 |
| Ollama Cloud | ollama/kimi-k2.5 |
What Kimi K2.5 is suited for
A 262K window comfortably holds a long file plus its surrounding context, which covers most day-to-day coding turns without compaction. It supports extended reasoning, which helps on debugging and multi-step planning but spends output tokens on thinking before the answer appears — worth knowing when you set max_tokens. Tool and function calling are supported, so it can drive an agent loop. It accepts images, so screenshots and diagrams can go straight into the prompt. Cached input is billed at $0.60 against $1.20 fresh, which is the difference that matters most for agent work — the same context is resent on every turn.
Specs
- Context window
- 262K
- Max output
- 262K
- Input / 1M
- $1.20
- Output / 1M
- $4.80
- Extended reasoning
- Image input
- Tool / function calling
Cheaper alternatives to Kimi K2.5
Comparable capabilities at a lower rate. With a kRouter combo you can send routine turns to one of these and reserve Kimi K2.5 for the work that actually needs it.
- Qwen3 Coder Plus$1.00 in · $4.00 out per 1M
- GPT-5 Mini$0.75 in · $3.00 out per 1M
- Gemini 3 Flash Preview$0.50 in · $3.00 out per 1M
- Gemini 3.1 Pro$0.50 in · $3.00 out per 1M
Kimi K2.5 FAQ
How much does Kimi K2.5 cost?
Kimi K2.5 is $1.20 per 1M input tokens and $4.80 per 1M output tokens. Cached input is $0.60, which matters a lot for agent work that resends the same context each turn.
Which providers serve Kimi K2.5?
8 providers: Cursor IDE, OpenCode Go, Kimchi, CodeBuddy CN, Kimi, Alibaba, Alibaba Intl, Ollama Cloud. Through kRouter you can switch between them by changing the route prefix, without changing your tool.
What is Kimi K2.5's context window?
262K tokens, with up to 262K tokens of output. kRouter publishes this on /v1/models as context_length, so clients read the real number instead of guessing from the model name.
Is there a cheaper alternative to Kimi K2.5?
Yes — Qwen3 Coder Plus ($1.00/1M in), GPT-5 Mini ($0.75/1M in), Gemini 3 Flash Preview ($0.50/1M in), Gemini 3.1 Pro ($0.50/1M in) are cheaper with comparable capabilities. A kRouter combo can send routine turns to one of those and keep Kimi K2.5 for the work that needs it.
Route to Kimi K2.5 from any tool
kRouter runs locally and gives Claude Code, Cursor, Codex and the rest one endpoint that reaches every provider above — with automatic failover. Free and MIT-licensed.
Install kRouter