Kimi API pricing

Kimi API prices per million tokens, context windows, open-weights status and independent benchmark scores from Moonshot.

Prices updated . Benchmarks updated .

Prices are the current OpenRouter rate, refreshed about hourly. This page does not chart older prices.

ModelYou send / 1MIt replies / 1MContextECILaunched
Kimi K3Open weights$0.192$15.001.05M158.32026-07-16
Kimi K2.6Open weights$0.650$3.41262K151.12026-04-20
Kimi K2.7 CodeOpen weights$0.600$3.50262K150.22026-06-12
Kimi K2.5Open weights$0.500$2.50262K148.12026-01-27
Kimi K2 ThinkingOpen weights$0.600$2.50262K145.92025-11-06
Kimi K3.1 ProClosed$2.00$10.001.05Mn/a2026-10-23
Kimi K2 0905Open weights$0.600$2.50262Kn/a2025-09-05
Kimi K2 0711Open weights$0.570$2.30256Kn/a2025-07-11

Which Moonshot model ranks highest?

Kimi K3 has the highest Epoch Capabilities Index among Moonshot models on this page, at 158.3. Kimi K2.6 is next at 151.1. Kimi K3 costs $15.00 per million output tokens and reads 1.05M of context. The index is an independent score from Epoch AI. Lab-reported numbers are kept off this ranking.

Which Moonshot model is cheapest?

Kimi K2 0711 has the lowest published output price among Moonshot models here, at $2.30 per million tokens. Input tokens cost $0.570 per million and the context window is 256K. Kimi K2.5 is next at $2.50 per million output tokens. It has no published Epoch Capabilities Index in the current file. Prices are the current public rate and can change.

Which Moonshot open-weight models lead?

Kimi K3 leads Moonshot open-weight models that have a published Epoch Capabilities Index, at 158.3. It is from Moonshot, costs $15.00 per million output tokens, and reads 1.05M. Kimi K2.6 from Moonshot follows at 151.1. Open weights means the lab published the weights. The license on the model page says what you can do with them.

FAQ

Which Moonshot model ranks highest?

Kimi K3 has the highest Epoch Capabilities Index among Moonshot models on this page, at 158.3. Kimi K2.6 is next at 151.1. Kimi K3 costs $15.00 per million output tokens and reads 1.05M of context. The index is an independent score from Epoch AI. Lab-reported numbers are kept off this ranking.

Which Moonshot model is cheapest?

Kimi K2 0711 has the lowest published output price among Moonshot models here, at $2.30 per million tokens. Input tokens cost $0.570 per million and the context window is 256K. Kimi K2.5 is next at $2.50 per million output tokens. It has no published Epoch Capabilities Index in the current file. Prices are the current public rate and can change.

How many Moonshot models are listed?

This page lists 8 Moonshot models with a public price or an independent score. Open the comparison table to filter the full catalogue.

Sources and licenses

  • OpenRouter: Prices, context windows, modalities and the model list come from the OpenRouter public API. Data: OpenRouter.
  • Vercel AI Gateway: The no-training flag comes from the Vercel AI Gateway model list.
  • models.dev: Lab launch dates, open-weights flags and knowledge cutoffs come from models.dev. Copyright (c) 2025 models.dev, MIT License.
  • Epoch AI: Independent benchmark scores and the Epoch Capabilities Index (ECI) come from Epoch AI's Benchmarking Hub, used under CC BY 4.0. Epoch AI, Capabilities & benchmarking, epoch.ai/benchmarks. Scores Epoch marks as external keep their original license, and the source is named on each score.
  • LMArena: Arena Elo (text, webdev and vision) comes from the LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset), CC BY 4.0, leaderboard date 2026-10-28.
  • Lab-reported scores, when an editor has added them, are the lab's own numbers. Each one links to the source and is labeled lab-reported. They are not used to rank the lists.
  • What a score measures: the benchmark guide.