Moonshot

Kimi K3.1 PRO Highspeed

Choose this when you want Kimi K3.1 Pro capabilities with more responsive output. It keeps the roughly 1-million-token context, image and video input, and required thinking mode; the official estimate is about 2–3× the speed, at roughly twice the quota usage.

  • Reasoning
  • Tool use
  • Function calling
  • Structured output
  • Long context

AI Chat

Send a prompt and see the response here.

kimi-k3.1-pro-highspeed
Current conversation
How can I help you?

Start a conversation with this model and ask follow-up questions.

Uses your account balance at the model’s current rates.

USD /1M tokens

Pricing

GroupInputOutputCache Read
default$4.2$22.00002$0.19992
kimi-0.9$3.78$19.800018$0.179928
default
Input$4.2Output$22.00002Cache Read$0.19992
kimi-0.9
Input$3.78Output$19.800018Cache Read$0.179928

Public list prices are shown in USD. Final charges may vary by account group and usage tier.

Moonshot

Related models

MoonshotAIMoonshotKimi K3

Moonshot flagship model with native vision and up to a 1M-token context window. It currently runs at max reasoning effort and suits long-horizon coding, knowledge work, and complex tasks that coordinate terminal tools. For stable use, preserve the full reasoning history and start a new session in a compatible agent harness.

$2.7/1M tokensMoonshotAIMoonshotKimi K3.1 PRO

Best suited to long-horizon coding, research, and multi-step agent work. The new Kimi Pro series offers roughly a 1-million-token context window and image and video input; thinking is required, making it a fit when deeper reasoning is worth the extra usage.

$1.89/1M tokensClaudeAnthropicClaude Opus 5 5

Built for long-running agentic coding and knowledge work, especially cross-file refactors, codebase audits, and complex multi-step tasks. Its 1M-token context, always-on adaptive thinking, and text/image input favor high-quality long-horizon execution; compared with Sonnet 5, it prioritizes depth at higher cost and latency.

$1.36/1M tokensDeepSeekDeepSeekDeepSeek V4 Flash

Built for reasoning, coding, and agentic tool use, with stronger long-context, thinking-mode, and complex-task execution than DeepSeek V3.2. Compared with Chinese peers such as Qwen, GLM, and Kimi, it is especially competitive for math, programming, and logical reasoning tasks.

$0.1278/1M tokens

FAQ

Frequently asked questions

What is Kimi K3.1 PRO Highspeed best suited for?

Kimi K3.1 PRO Highspeed is suited to the input, output, and capability types listed on this page. Test production workloads before choosing it for a critical system.

How is Kimi K3.1 PRO Highspeed priced?

Pricing is shown in the pricing section above. Actual cost depends on usage volume, account group, and the request payload.

How can I call Kimi K3.1 PRO Highspeed?

Use the model ID shown above with one of the supported API protocols. Code examples are provided when usage data is available.

Get started

Build with Kimi K3.1 PRO Highspeed

Use in Console