Use Kimi K3 for long-context chat, coding, and agent workloads through PoYo's OpenAI-compatible chat endpoint.
Answer: To use the Kimi K3 API, send a server-side request to POST https://api.poyo.ai/v1/chat/completions with model kimi-k3 and a PoYo API key. The examples in this repository are runnable with Node.js 22+ or cURL.
Last verified against the live PoYo schema and pricing on August 9, 2026.
- Create a key in the PoYo dashboard.
- Copy
.env.exampleto.envand replace the placeholder. - Run
node node/index.mjs.
POYO_API_KEY=YOUR_POYO_API_KEY_HERE
POYO_BASE_URL=https://api.poyo.aiThe complete cURL request is in curl/generate.md. The Node.js example prints the complete JSON response.
kimi-k3
Use the exact IDs above. Product names and API model IDs are not always identical.
| Field | Requirement | Meaning |
|---|---|---|
| model | required | kimi-k3. |
| messages | required | OpenAI-style role/content messages. |
| temperature | optional | Sampling temperature. |
| max_tokens | optional | Maximum generated tokens. |
| stream | optional | Enable streaming when your client supports SSE. |
| Usage | Price |
|---|---|
| Input | $2.28 per 1M tokens |
| Output | $11.40 per 1M tokens |
Pricing can change. Confirm the current amount on the model page before a production rollout.
- long-context analysis
- coding assistants
- agent planning
- Kimi K3 supports a context window of up to 1 million tokens; practical limits also depend on request and output settings.
- Send requests from a trusted backend so the API key never reaches browser code.
- Log request IDs and usage, not full sensitive prompts.
Set an application timeout, retry only transient failures, cap output size, and record token usage. Do not put POYO_API_KEY in browser or mobile client code.
curl/generate.md— copy-paste requestnode/index.mjs— dependency-free Node.js exampledocs/production-notes.md— limits and rollout checklist
MIT