Skip to content
Kimi K3.1 Pro logo

Kimi K3.1 Pro

Moonshot AI

Key facts · verified Oct 27, 2026

Kimi K3.1 Pro is a Moonshot AI model released on 24 Oct 2026. Its API price is $2 per million input tokens and $10 per million output tokens ($0.20 cached input). Its context window is 1M tokens. It is not yet ranked on LMArena's text leaderboard. Source: platform.kimi.ai.

Moonshot AI’s Kimi K3.1 Pro, released 24 October 2026: the first model in its K3.1 series, a post-trained version of Kimi K3 that Moonshot describes as its most capable 3T-class open-weight model, with a 1-million-token context window. Moonshot names coding, 3D creation and financial research as the main gains. It is on Kimi.ai, Kimi Work, Kimi Code and the Kimi API at $2 per million input tokens and $10 per million output tokens, with a Highspeed version at 2-3 times the speed for $4 and $20. Moonshot states the full weights will be released by 4 November 2026.

Pricing & specs checkedSource: vendor documentation · checked Oct 27, 2026
Pricing

$2 / $10 per million tokens

Context

1M tokens

LMArena Elo

Not rated

LMArena rank

Not ranked

Key Features

Long-Horizon Coding Agentic Native Vision Long Context Tool Use Cached Input Discount Highspeed Variant

Full Specifications

$2 / $10 per million tokens
Identity
DeveloperMoonshot AI
ReleasedOct 2026
StatusGA
LicenceOpen weights announced — Moonshot states full weights by 4 November 2026
Self-hostableNot yet — weights due by 4 November 2026
Cost
Blended $/1M tokensinput × 0.75 + output × 0.25$4.000 / 1M tokens
Input price$2.000 / 1M tokens
Output price$10.000 / 1M tokens
Cached input$0.20 / 1M tokens; cache writes $2 (5-minute TTL) or $4 (1-hour TTL)
Free tierNot offered — unlocked after a minimum $1 top-up
Capacity
Context window1M tokens
Max output131,072 tokens by default; max_completion_tokens up to 1,048,576
Capability
Vision inYes — images and video (base64 or uploaded files; no public URLs)
Audio inNot stated
Function callingYes
Structured outputYes — json_schema with strict: true
Extended reasoningYes — always on; reasoning_effort low, high or max (default max)
Web searchBeing updated by Moonshot; not recommended for production in the near term
Access
APIYes
Chat appYes