Kimi K3.1 Pro

Provider: Moonshot AI (Kimi) CN Official API price

Input price
$2.00
/ 1M tokens
Output price
$10.00
/ 1M tokens
Cache price
$0.20
/ 1M tokens (read)
Batch API
$0.70 / $6.00
input / output per 1M tokens
Context
1.05M tokens
Max output 944K tokens

Overview

Moonshot AI's flagship open-weight multimodal reasoning model features a 1M-token context window and 943k max output. It targets long-horizon coding and complex reasoning workloads.

Strengths

  • 1048576 token context window capacity
  • 943718 token maximum output length
  • Cached input priced at $0.2 per million
  • Supports vision, function-calling, json-mode, and thinking

Best use cases

  • Long-horizon code generation tasks
  • Processing large multimodal documents
  • Complex reasoning workflows

Pricing position

Input matches GPT-4.1 and o3 at $2/1M, but output is higher at $10/1M versus their $8/1M.

Caveats

No free tier is available; lighter sibling models like Kimi K2.5 cost under a third of the input price.

Notes drafted by an LLM from the figures on this page (2026-11-12) and rewritten when the price changes.

Key facts

Price basis
Official API price
Max output
944K tokens
Listed on OpenRouter
2026-10-23
Tracked since
2026-10-23
Last updated
2026-11-12

Features

Image inputFunction callingJSON outputReasoning

Price history

  • 2026-10-23 Added

Monthly cost estimate

Scale Input (M) Output (M) Monthly
0.1M (hobby) 0.1 0.05 $0.70
1M (small app) 1 0.5 $7.00
10M (mid scale) 10 5 $70.00
100M (large) 100 50 $700.00

※ Cache and batch discounts not factored in. Detailed calculator

Official resources

Other models from Moonshot AI (Kimi)

Similar-priced models

Source: OpenRouter API (moonshotai/kimi-k3.1-pro)