RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

MoonshotAI: Kimi K3 API pricing

$0.192 per 1M input tokens and $16.00 per 1M output tokens on OpenRouter. Context window: 1,048,576 tokens.

$0.192input / 1M tokens
$16.00output / 1M tokens
$0.182cached input / 1M
1Mcontext
text+image+video->textmodality

What it costs in practice

WorkloadCost
Chatbot: 10,000 messages (1,500 in / 400 out tokens each)$66.88
RAG: 1,000 queries (8,000 in / 600 out each)$11.14
Summarize 100 long documents (50,000 in / 1,000 out each)$2.56

Cross-check against the provider's list price

LiteLLM's price map lists moonshot/kimi-k3 (moonshot) at $3.00 in / $15.00 out per 1M tokens. Differs from OpenRouter OpenRouter routes to several hosts and may list a different provider's price than the model maker's own API.

Price history

No price change recorded since we started tracking on Nov 17, 2026. We check every 6 hours and log every change.

Run it yourself instead

The open weights are on Hugging Face. See the VRAM Kimi K3 needs and which GPUs fit it →

Cheaper alternatives with similar context

Text models with at least 125K context and a lower blended price (75% input, 25% output). Price only, not a quality ranking.

ModelInput / 1MOutput / 1MContext
Google: Gemini 4 Carbon$2.00$10.001M
Google: Gemini 4 Argon$2.00$10.001M
OpenAI: GPT-6.1 Sol Pro$2.00$10.001.0013580322265625M
OpenAI: GPT-6.1 Sol$2.00$10.001.0013580322265625M
Anthropic: Claude Sonnet 5.5$2.00$10.00977K
OpenAI: GPT-6 Sol Pro$2.00$10.001.0013580322265625M
OpenAI: GPT-6 Sol$2.00$10.001.0013580322265625M
Anthropic: Claude Opus 5.5 (batch)$2.00$10.00977K

Source: OpenRouter listing via the public models API · LiteLLM price map (MIT). Prices checked Nov 17, 2026. Model ID moonshotai/kimi-k3, listed Jul 16, 2026. Report an error.