Kimi K2.7 Code · Highspeed
Low-latency variant. Same input, output 2x more expensive for compute priority. For chatbots with high concurrency.
moonshot/kimi-k2.7-code-highspeed
- Context
- 262k tokens
- Completion cap
- —
- Tools
- Yes
- JSON
- No
Call it from Geek Hub
Same OpenAI SDK. Change the base URL and the model id.
curl https://api.geekhub.mx/v1/chat/completions \
-H "Authorization: Bearer $GEEKHUB_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "moonshot/kimi-k2.7-code-highspeed",
"messages": [{"role": "user", "content": "Hola"}]
}'Frequently asked questions
- What is Kimi K2.7 Code · Highspeed?
- Low-latency variant. Same input, output 2x more expensive for compute priority. For chatbots with high concurrency. Kimi K2.7 Code · Highspeed runs on the Geek Hub API (OpenAI-compatible). Model id: moonshot/kimi-k2.7-code-highspeed.
- Is Kimi K2.7 Code · Highspeed free?
- No. Input is $1.0356 per 1M tokens and output is $8.7205 per 1M tokens on Geek Hub (markup included).
- What is the context length of Kimi K2.7 Code · Highspeed?
- Kimi K2.7 Code · Highspeed has a 262k tokens context window.
- Does Kimi K2.7 Code · Highspeed support tool calling and structured outputs?
- Kimi K2.7 Code · Highspeed accepts tools and tool_choice for function calling. Structured outputs are not listed for this endpoint.