Kimi K3.1 Pro Highspeed is the faster serving tier of Moonshot AI's Kimi K3.1 Pro. It runs the same post-trained 3T-class model with identical capabilities, and Moonshot AI reports two to three times faster output. It is built for latency-sensitive coding, agent and chat workloads. On AI/ML API it is available through the OpenAI-compatible chat completions endpoint.
Both variants share the same model and benchmarks. Highspeed trades a higher per-token price for faster generation; the standard Kimi K3.1 Pro costs half as much and suits batch or background work.
Interactive coding assistants
IDE and terminal agents where developers wait on every response.
Real-time agent loops
Multi-step tool use where each step's latency adds up across the run.
User-facing chat
Products where faster replies directly improve the experience.
Kimi K3.1 Pro Highspeed fits interactive coding assistants and IDE agents, where each response is on the critical path for the developer.
It suits real-time agent loops with many tool calls, since faster generation shortens every step of a long run.
It works for user-facing chat and support products where response time affects the experience.
It keeps the full Kimi K3.1 Pro capability set, including reasoning, vision and a 1M-token context window.
import requests r = requests.post( "https://api.aimlapi.com/v1/chat/completions", headers={"Authorization": "Bearer " + AIMLAPI_KEY}, json={ "model": "moonshot/kimi-k3-1-pro-highspeed", "messages": [ { "role": "user", "content": "Hello!" } ] }, ) print(r.json())
const r = await fetch("https://api.aimlapi.com/v1/chat/completions", { method: "POST", headers: { Authorization: `Bearer ${process.env.AIMLAPI_KEY}`, "Content-Type": "application/json", }, body: JSON.stringify({ "model": "moonshot/kimi-k3-1-pro-highspeed", "messages": [ { "role": "user", "content": "Hello!" } ] }), }); console.log(await r.json());
curl -X POST https://api.aimlapi.com/v1/chat/completions \ -H "Authorization: Bearer $AIMLAPI_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"moonshot/kimi-k3-1-pro-highspeed","messages":[{"role":"user","content":"Hello!"}]}'
OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Input | |
| Output | |
| Cached input |
Cached input is billed at $0.20 / 1M tokens. The full 1M context window is included at standard pricing.
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
Kimi K3.1 Pro Highspeed This page | Low-latency coding & agents | |||
| Agentic coding & long-horizon work | ||||
| Long-context, multimodal & agentic workflows | ||||
| Coding + agents | ||||
| Reasoning + agents |
Kimi K3.1 Pro Highspeed is the high-speed variant of Moonshot AI's Kimi K3.1 Pro. It has the same model capabilities and 1M-token context window, and Moonshot AI reports it generates output two to three times faster.
Kimi K3.1 Pro Highspeed takes text and image input and returns text. It supports reasoning, tool calling (including parallel tool calls), vision, structured output and streaming.
Kimi K3.1 Pro Highspeed has a 1,048,576-token context window and can return up to 1,048,576 tokens.
Kimi K3.1 Pro Highspeed costs $4 per 1M input tokens, $0.20 per 1M cached input tokens and $20 per 1M output tokens. Reasoning tokens are billed at the output rate.
Choose Highspeed for interactive apps, coding assistants and agent loops where response time matters. Choose the standard Kimi K3.1 Pro for batch or background work where cost matters more than speed: it costs half as much per token.
Send a request to the OpenAI-compatible chat completions endpoint https://api.aimlapi.com/v1/chat/completions with the model ID moonshot/kimi-k3-1-pro-highspeed and your AI/ML API key.
