We moved our high-volume classification and summarization to the Kimi K2.5 API — the quality is plenty and the bill dropped hard.
The Kimi K2.5 API is Moonshot AI's open-weight, value-tier Kimi K2 model — capable general chat, reasoning, coding, and agents at open-model prices, with native tool calling, structured outputs, and a long context window. The Kimi K2.5 API is OpenAI-compatible: point any existing SDK at RouterBase and set the model to kimi-k2-5. Input at $0.57 / 1M tokens, output at $2.85 / 1M tokens — 5% below the official rate, all through one REST endpoint.
Input
Kimi K2.5
Hi! I'm a helpful AI assistant. What can I do for you?
Kimi K2.5 API: Chat
Use the Kimi K2.5 API to run Moonshot AI's value-tier open model — Kimi K2.5 is a capable general and agentic Kimi K2 model that holds up on real work while costing a fraction of frontier APIs.
The Kimi K2.5 API is Moonshot AI's value-tier open model — a capable general and agentic Kimi K2 model at open-model prices, with native tool calling, structured outputs, and a long context window. Routed through RouterBase, the Kimi K2.5 API is fully OpenAI-compatible: point any existing SDK at RouterBase's base URL, set the model to kimi-k2-5, and your first Kimi K2.5 API call goes through immediately.
Pricing for the Kimi K2.5 API is $0.57 / 1M input and $2.85 / 1M output — 5% below the official rate, via one RouterBase key (no Moonshot AI account).
Six reasons teams ship on the Kimi K2.5 API
From capable everyday output to a 5%-off price — why teams run high-volume workloads on the Kimi K2.5 API.
Capable at a low price
Kimi K2.5 covers the bulk of real production work — chat, reasoning, agents, and coding — at a price low enough to run at high volume without watching the meter.
Open-weight value
The Kimi K2.5 API is an open-weight Kimi K2 model, so you get solid general capability at open-model economics — far below closed frontier pricing.
Native tool calling
The Kimi K2.5 API does function / tool calling in the OpenAI format — Kimi K2 was built for tool use, so it slots into agents without custom glue.
Long context window
The Kimi K2.5 API takes a long context — feed it whole documents, codebases, or full conversation history in one call.
OpenAI-compatible, one key
The Kimi K2.5 API uses the OpenAI chat-completions format, so one RouterBase key swaps Kimi K2.5 in beside GPT-5.5, Claude, Gemini, and 200+ other models.
5% off the list price
Kimi K2.5 runs 5% under Moonshot AI's published rate — $0.57 / 1M input, $2.85 / 1M output. Open-model pricing that scales cheaply, billed per token, nothing per request.
Quickstart
Get started with the Kimi K2.5 API in 3 steps
From sign-up to your first response in under 5 minutes.
Create a RouterBase API key
Sign up and create an API key — it reaches Kimi K2.5 and every other model in the RouterBase catalog from one account.
Send your first message
Point any OpenAI-compatible SDK at routerbase.com/v1 and set the model to kimi-k2-5. Streaming, tool calls, and structured outputs all follow the standard chat-completions schema.
Inspect usage
Every Kimi K2.5 API response returns a token breakdown — input and output — so cost stays visible on every call.
Pay only for what you use
RouterBase passes through partner-tier pricing. Compared against the model's official published API rate.
What teams build with the Kimi K2.5 API
Real production loads running on the RouterBase model catalog across 200+ models.
Kimi K2.5 is our default cheap model through RouterBase — good enough for most requests, and we escalate only the rare hard ones.
We run thousands of agent steps a day on the Kimi K2.5 API — at this price we stopped rationing calls.
We A/B the Kimi K2.5 API against pricier models behind one RouterBase key — for most of our traffic the cheaper one wins on cost per good answer.
Pointing our OpenAI SDK at the Kimi K2.5 API took one base-URL change, and our per-request cost fell overnight.
Long documents go straight into the Kimi K2.5 API without chunking gymnastics — cheap context made our pipeline simpler.
As a solo dev the Kimi K2.5 API is the open model I actually ship on — capable, and cheap enough to leave running.
On cost per token the Kimi K2.5 API is the best value in our eval suite — we route the bulk of traffic to it.
Per-token billing plus Kimi K2.5 rates means our margins survive even at high request volume.
Frequently Asked Questions
Common questions about the Kimi K2.5 API.
The Kimi K2.5 API is RouterBase's pass-through to Moonshot AI's Kimi K2.5 — an open-weight Kimi K2 model that handles general chat, reasoning, coding, and agents at low cost, served over an OpenAI-compatible REST interface with native tool calling and structured outputs.