Kimi K3 API
Moonshot's frontier model — long-context reasoning and agentic tool use.
Starting at
$3.15
input price per 1M tokens
Kimi K3 playground
Input
openaiInput
$3.15 / 1M
Output
$15.75 / 1M
Output

Start a conversation
Ask Kimi K3 anything. Messages are sent directly to the API and charged by token usage.
Sign in to chatKimi K3 API pricing
| Option | Price per 1M tokens |
|---|---|
| input | $3.15 |
| output | $15.75 |
| cacheRead | $0.315 |
Quick start
Full API reference →1curl -X POST https://api.api-stock.com/api/v1/chat/completions \2 -H "Authorization: Bearer $API_STOCK_KEY" \3 -H "Content-Type: application/json" \4 -d '{5 "model": "kimi-k3",6 "messages": [7 {8 "role": "user",9 "content": "A cinematic shot of a city at dusk"10 }11 ]12 }'
Frequently asked questions
How much does Kimi K3 cost?
Kimi K3 starts at $3.15 per 1M input tokens on API Stock. The final charge depends on the selected settings.
When was Kimi K3 released?
Kimi K3 was released on July 16, 2026 and is available through API Stock.
How do I get an API key for Kimi K3?
Create an account and API key on API Stock, then fund your balance. The same key works with Kimi K3 and other catalog models.
How do I call the Kimi K3 API?
Send a POST request to https://api.api-stock.com/api/v1/chat/completions with your API key and the model "kimi-k3", using the openai-compatible request format shown in the quick start above.
What happens if a Kimi K3 request fails?
API Stock automatically retries the request on a reserve provider. If every provider fails, the charge is refunded to your balance.
Can I use Kimi K3 with the same API key as other models?
Yes. Use your API Stock API key and balance for Kimi K3 and other catalog models.
Other Chat models
- Kimi K2.7 CodeMoonshot$1.11/ 1M tokens
- Gemini 4 CarbonGoogle$2.4/ 1M tokens
- GPT 6 SolOpenAI$2.4/ 1M tokens
- Claude Opus 5Anthropic$3/ 1M tokens
- GPT 5.6 SolOpenAI$3/ 1M tokens
- Claude Fable 5.2Anthropic$3.6/ 1M tokens
- Claude Opus 5.5Anthropic$4.8/ 1M tokens
- GPT 6 AstraOpenAI$8/ 1M tokens
- Claude Fable 5.1Anthropic$10/ 1M tokens
Guides
- Choose a model for an agent taskCompare models on completed tool-using tasks, repeated attempts and observed cost before setting an agent's default.2 min read
- LLM API pricing: GPT, Claude, Gemini, DeepSeek comparedCompare LLM API pricing for GPT, Claude, Gemini, DeepSeek, Grok and Kimi per 1M tokens, with worked monthly cost examples and practical ways to cut the bill.9 min read
- Give your coding agent image, video and music toolsConnect Claude Code, Codex, OpenCode or OpenClaw to API Stock and use generated media in a page, app or content draft.3 min read
