Kimi K3.1 Pro

• Type: Generation
• Capabilities: reasoning, vision
• Cache read: $0.20 per 1M input tokens (0.1× standard input price). See prompt caching.

Overview

Kimi K3.1 Pro is an open-weight multimodal reasoning model from Moonshot AI, the successor to Kimi K3, with a one-million-token context window. It is suited for complex coding, knowledge work, and long-horizon agentic workflows that use tools and iterate against images, logs, tests, and runtime feedback.

Reasoning efforts

• Supported: none, minimal, low, medium, high, xhigh, max

See the reasoning effort guide for request examples.

Pricing

Priority	Input Tokens (per 1M)	Cache Read Tokens (per 1M)	Output Tokens (per 1M)
Realtime1	$2.00	$0.20	$10.00
Async	$1.40	$0.14	$7.00
Batch (24h)	$1.00	$0.10	$5.00

Playground

Open this model in the Playground.

Footnotes

1. Realtime availability is limited. Doubleword is primarily a batch API. ↩