Kimi K3 API
Kimi K3 is a language model from its provider, available on Routeriva under the model ID kimi-k3. You call it with the same sk- key you use for every other model — no separate provider account is needed.
On Routeriva it costs $1.95 per 1M input tokens and $9.75 per 1M output tokens, compared with the official list price of $2.50 / $12.50 — about 22% less. Prices shown are the lowest across the routes that serve this model; your key is charged at its own route's price.
The context window is 1,000,000 tokens, so you can send long documents, codebases or chat histories in a single request.
Kimi K3 is served through the OpenAI-compatible /v1/chat/completions endpoint, so any OpenAI SDK or tool works by changing the base URL.
Key facts
- Model ID:
kimi-k3 - Provider: —
- Type: text
- Context window: 1,000,000 tokens
- Input: $1.95 / 1M (list $2.50)
- Output: $9.75 / 1M (list $12.50)
- Endpoints: /v1/chat/completions, /v1/responses
Good for
- General chat and writing
- Coding help
- Summarisation and extraction
Prices by route
| Route | Input / 1M | Output / 1M |
|---|---|---|
| OSS | $1.95 | $9.75 |
Code sample
from openai import OpenAI
client = OpenAI(base_url="https://api.routeriva.com/v1", api_key="sk-your-key")
r = client.chat.completions.create(model="kimi-k3", messages=[{"role": "user", "content": "Hello"}])
print(r.choices[0].message.content)FAQ
How much does the Kimi K3 API cost on Routeriva?
From $1.95 per 1M input tokens and $9.75 per 1M output tokens (official list $2.50 / $12.50, about 22% less). Live prices are on routeriva.com/models/kimi-k3.
What model ID do I use for Kimi K3?
Use "kimi-k3" as the model value with base URL https://api.routeriva.com/v1 and your sk- key.
Which endpoints support Kimi K3?
/v1/chat/completions, /v1/responses on https://api.routeriva.com.
What is the context window of Kimi K3?
1,000,000 tokens.