Kimi K3: price, context window and capabilities

What it costs in practice

Using the listed prices: a chat turn of 2,000 input and 500 output tokens costs about $0.0079, so 10,000 such turns cost about $79.40. Summarising a 100,000-token document into 2,000 tokens costs about $0.098. A long agent run that reads 1 million tokens and writes 50,000 costs about $1.37.

How it compares

Among the 40 models we track, Kimi K3 ranks #21 by input price and #37 by output price (1 is cheapest), and #6 by context window (1 is largest). Models with the same tool and reasoning support that cost less per output token: DeepSeek V4 Pro 0423 ($0.418), Qwen3.8 Omni Flash ($0.470), Qwen3.8 Flash ($0.470), GPT-6 Luna Pro ($0.500). Models with a larger context window at the same or lower output price: Llama 4 Scout (1.3M), GPT-6.1 Sol Pro (1.1M), GPT-6.1 Sol (1.1M), GPT-6 Luna Pro (1.1M).

More from Moonshot AI

• Kimi K2.7 Code: $0.671 in / $3.35 out, 262K context
• Kimi K2.6: $0.950 in / $4.00 out, 262K context
• Kimi K2.5: $0.450 in / $2.25 out, 262K context

In the news

• Cognition Drops SWE-2: Fine-Tuning a 2.8T Model for Shell Dominance September 14, 2026
• Kimi K3: Open Frontier Intelligence - Moonshot AI's Open-Weight Model Challenges Western Dominance August 20, 2026
• That viral Kimi K3 sandbox escape? It was OpenAI's models 7 Aug 2026
• Moonshot Drops Kimi K3: The 2.8T Parameter Open-Weight Behemoth Shaking Up Sovereign AI August 2, 2026
• Kimi K3's 2.8T Open Weights Just Spooked the Chip Market 29 Jul 2026

Prices and limits come from OpenRouter's public model catalogue, last synced 4 Oct 2026. Provider pricing can differ from OpenRouter's and changes often; confirm on the provider's own page before you commit. See the guide to choosing a model or the full comparison.