Kimi K3.1 Pro
−64% vs officialContext
1Mtokens
Input
$2.00 $0.72/1M
Cached $0.20$0.07 /1M
Output
$10.00 $3.60/1M
You save
64%
Quickstart
Use the OpenAI SDK with your Ruvicode API key. Just change the base URL and model name.
curl https://api.ruvicode.com/v1/chat/completions \
-H "Authorization: Bearer rvcd_..." \
-H "Content-Type: application/json" \
-d '{
"model": "kimi-k3.1-pro",
"messages": [{"role": "user", "content": "Hello"}]
}'Need the full API reference?
Authentication, streaming, error handling, and rate limits.
Reference pricing
Live market pricing, refreshed every 2 minutes. No credit expiry. Savings versus official list prices.
Specs
About Kimi K3.1 Pro
Kimi K3.1 Pro is a Moonshot model with image input, tool calling and built-in reasoning. On Ruvicode you call it as kimi-k3.1-pro through the OpenAI-compatible Chat Completions API at https://api.ruvicode.com/v1, with the same API key and prepaid wallet as every other model, billed per token. It takes up to 1M tokens of context and writes up to 128K tokens per response.
Kimi K3.1 Pro FAQ
- How is Kimi K3.1 Pro priced on Ruvicode?
- Kimi K3.1 Pro is billed per token from a prepaid wallet, with no subscription: an input rate and an output rate per million tokens, plus a cached input rate for repeated prompt prefixes, applied automatically. The rates follow the provider market, refresh every 2 minutes, and are shown at the top of this page next to the official list price. Every response reports its exact charge in usage.cost.
- Is Kimi K3.1 Pro OpenAI-compatible on Ruvicode?
- Yes. Send requests to https://api.ruvicode.com/v1/chat/completions with "model": "kimi-k3.1-pro" and your Ruvicode API key as a Bearer token. Any OpenAI SDK works by changing the base URL, and streaming, tool calling and usage reporting work the same way as in the OpenAI API.
- What is the context window of Kimi K3.1 Pro?
- Kimi K3.1 Pro takes up to 1M tokens of context, with up to 128K output tokens per response.
- Why does Kimi K3.1 Pro sometimes return an empty answer?
- Kimi K3.1 Pro reasons before it answers, and that reasoning counts against max_tokens. If max_tokens is too small, the whole budget can go to reasoning and the response ends with finish_reason "length" and empty content. Give it a budget in the thousands of tokens, and check finish_reason before treating an answer as empty.
- Can Kimi K3.1 Pro read images?
- Yes. Send images in the messages array as image_url parts, either a public URL or a base64 data URL, the same way as with the OpenAI API.
- Can I use Kimi K3.1 Pro in Cursor, Cline or OpenCode?
- Yes. Add Ruvicode as an OpenAI-compatible provider with the base URL https://api.ruvicode.com/v1, your Ruvicode API key, and the model id kimi-k3.1-pro. The integrations page has step-by-step setup for each tool. Claude Code works too, through 9router, which translates its Anthropic requests.
Setup for each tool is on the integrations page, and the full API reference is in the chat completions docs.