Moonshot AI: Kimi K3.1 Pro Highspeed
Kimi K3.1 Pro Highspeed is a reasoning model from Moonshot AI released on Oct 23, 2026. It reads text, images and video and writes text, with a 1.05M token context window and up to 1.05M tokens per reply.
Show moreShow less
It costs $4 per million input tokens and $20 per million output tokens. Cached input bills at $0.20, 95% less than fresh input.
It supports tool calling, structured JSON output and prompt caching.
14 providers serve it, including Vercel AI Gateway, DevPass (LLM Gateway) and Eden AI. The lowest input price is $2 per million tokens at Vercel AI Gateway.
- Modalities
- In / out price
- $4 / $20 per 1M
- Context
- 1.05M
- Max output
- 1.05M
- Released
- Oct 23, 2026
- Knowledge cutoff
- n/a
- Tool calling
- Structured output
- Reasoning
- Prompt caching
- Open weights
- Free to use
Kimi K3.1 Pro Highspeed pricing
USD, as listed on Oct 24, 2026. Most bills are input heavy, so the cached input rate matters as much as the headline price.
| Input | $4 / 1M tokens | |
|---|---|---|
| Output | $20 / 1M tokens | |
| Cached input (read) | $0.20 / 1M tokens | 95% off input |
| Cache write | $4 / 1M tokens |
Kimi K3.1 Pro Highspeed providers
14 providers serve it, including Vercel AI Gateway, DevPass (LLM Gateway) and Eden AI. The lowest input price is $2 per million tokens at Vercel AI Gateway. Each host sets its own price and limits, so the cheapest one is not always the one with the longest context.
| Provider | Input /M | Output /M | Cache read /M | Context | Max output |
|---|---|---|---|---|---|
| Moonshot AI First party | $4 | $20 | $0.20 | 1.05M | 1.05M |
| Vercel AI Gateway | $2 | $10 | $0.20 | 1.05M | 1.05M |
| DevPass (LLM Gateway) | $2 | $10 | $0.20 | 1.05M | 131K |
| Eden AI | $2 | $10 | $0.20 | 1.05M | 131K |
| Kilo Gateway | $2 | $10 | $0.20 | 1.05M | 944K |
| LLM Gateway | $2 | $10 | $0.20 | 1.05M | 1.05M |
| Merge Gateway | $2 | $10 | $0.20 | 1.05M | 1.05M |
| NanoGPT | $2 | $10 | $0.20 | 1.05M | 1.05M |
| Prime Inference | $2 | $10 | n/a | 1.05M | 944K |
| Venice AI | $3 | $15 | $0.30 | 1M | 131K |
| Moonshot AI (China) | $3.89 | $20.33 | $0.1944 | 1.05M | 1.05M |
| Requesty | $4 | $20 | $0.20 | 1.05M | 1.05M |
Showing 12 of 14 providers: the lab first, then the major clouds, then the cheapest resellers.
What Kimi K3.1 Pro Highspeed costs per month
Pick a workload close to yours or type your own volumes.
Supported request parameters
What you can set when you call Kimi K3.1 Pro Highspeed through an OpenAI compatible API.
- Tools
tools - Structured outputs
structured_outputs - Reasoning
reasoning
Alternatives to Kimi K3.1 Pro Highspeed
Models that take the same inputs and call tools, closest in price, cheaper ones first.
- Index 43.6
Reads text, images and video. Tool calling, structured output, reasoning. Served by 72 providers.
by moonshotaiJul 16, 20261.05M context$3/M input tokens$15/M output tokens72 providers
- 1.05M context
Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 10 providers.
by metaOct 12, 2026$4/M input tokens$20/M output tokens10 providers
- Index 29.7
Reads text, images, audio and video. Tool calling, structured output, reasoning. Served by 5 providers.
by googleFeb 19, 20261.05M context$2/M input tokens$12/M output tokens5 providers
- 1M context
Reads text, images, files, audio and video. Tool calling, structured output, reasoning.
by visparkMay 15, 2024$4.21/M input tokens$12.63/M output tokens
- 1.05M context
Reads text, images, audio and video. Tool calling, structured output, reasoning. Served by 8 providers.
by xiaomiSep 21, 2026$4.35/M input tokens$8.70/M output tokens8 providers
- 1.05M context
Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 24 providers.
by googleJun 17, 2025$1.25/M input tokens$10/M output tokens24 providers
More from Moonshot AI
- 1.05M context
Reads text, images and video. Tool calling, reasoning. Served by 2 providers.
by moonshotaiSep 11, 2026$0/M input tokens$0/M output tokens2 providers
- Index 43.6
Reads text, images and video. Tool calling, structured output, reasoning. Served by 72 providers.
by moonshotaiJul 16, 20261.05M context$3/M input tokens$15/M output tokens72 providers
- Index 25.8
Reads text, images and video. Tool calling, structured output, reasoning. Served by 43 providers.
by moonshotaiJun 12, 2026262K context$0.95/M input tokens$4/M output tokens43 providers
- 262K context
Reads text, images and video. Tool calling, structured output, reasoning. Served by 14 providers.
by moonshotaiJun 12, 2026$1.90/M input tokens$8/M output tokens14 providers
- 1.05M context
Reads text and images. Tool calling, structured output, reasoning. Served by 3 providers.
by moonshotaiMay 3, 2026$3/M input tokens$15/M output tokens3 providers
- 262K context
Reads text, images and video. Tool calling, structured output, reasoning. Served by 53 providers.
by moonshotaiApr 20, 2026$0.95/M input tokens$4/M output tokens53 providers
Kimi K3.1 Pro Highspeed questions
How much does the Kimi K3.1 Pro Highspeed API cost?
$4 per million input tokens and $20 per million output tokens, with cached input at $0.20. The estimator on this page turns that into a monthly bill for your own workload.
What is the context window of Kimi K3.1 Pro Highspeed?
1,048,576 tokens of input, and it can write up to 1,048,576 tokens in one reply. As a rough guide, a million tokens is around 750,000 English words.
Which providers serve Kimi K3.1 Pro Highspeed?
14 providers serve it, including Vercel AI Gateway, DevPass (LLM Gateway) and Eden AI. The lowest input price is $2 per million tokens at Vercel AI Gateway. Prices differ by host, so the Providers table on this page lists each one with its input and output price.
Does Kimi K3.1 Pro Highspeed support tool calling?
Yes. It accepts tool definitions and can return JSON that matches a schema, which is what an agent needs to call your APIs.
Is Kimi K3.1 Pro Highspeed open source?
No. Moonshot AI serves it through an API only, so you cannot download the weights or host it yourself.
When was Kimi K3.1 Pro Highspeed released?
Oct 23, 2026.
Catalog data from models.dev (MIT licensed), refreshed daily, last on Oct 24, 2026. The summary is written from these facts.