Kimi K3 Launch Recap: What Moonshot Shipped on July 16
Everything confirmed about the Kimi K3 release: 2.8T parameters, 1M context, $3/$15 pricing, Elo 1547, and the July 27 open-weights promise.
· news
Kimi K3 is Moonshot AI's 2.8-trillion-parameter open-weight model, released July 16, 2026. The API costs $3 per million input tokens and $15 per million output tokens, with a 1M-token context window. This site turns those numbers into decisions: count your tokens, forecast your bill, compare alternatives.
Last verified: · source
Paste text, get an exact Kimi token count plus input/output cost — runs the real tokenizer in your browser.
Model a real workload — coding agent, RAG bot, batch research — into a monthly Kimi K3 API bill with cache savings.
What actually fits in 1M tokens? Pages, codebases and transcripts translated into concrete numbers.
| Model | Input / 1M tokens | Output / 1M tokens | Context | License |
|---|---|---|---|---|
| Kimi K3 | $3.00 | $15.00 | 1,048.576K | open-weight |
| Kimi K2.6 | $0.95 | $4.00 | 262.144K | open-weight |
| DeepSeek V4 Pro | $1.10* | $4.40* | 262.144K | open-weight |
| GPT-5.5 | $2.50* | $20.00* | 400K | proprietary |
| Claude Sonnet | $3.00* | $15.00* | 1,000K | proprietary |
* listed price at time of verification; check the linked source for the vendor's current rate.
Full breakdown, cache math and channel comparison on the pricing page.
Everything confirmed about the Kimi K3 release: 2.8T parameters, 1M context, $3/$15 pricing, Elo 1547, and the July 27 open-weights promise.
· news
What will it take to run Kimi K3's 2.8T MoE locally? Storage per quantization level, why MoE sparsity doesn't cut memory, and realistic setups.
· local
Kimi K3 prompt caching explained: what gets cached, the 60-80% effective savings reports, worked examples, and how to structure prompts for hits.
· api, pricing
Legit ways to use Kimi K3 free: kimi.com's free tier, router trials and what they limit — plus what 'free' actually costs in quotas and privacy.
· guide
Kimi K3 costs $3 per million input tokens and $15 per million output tokens on the official Moonshot API (verified July 21, 2026). Cached input is discounted; the official cached rate has not been published yet.
Kimi K3 is announced as an open-weight model. Moonshot AI has promised to release the weights by July 27, 2026. Until then it is available through the Kimi app, kimi.com and the API.
Kimi K3 supports a 1,048,576-token (1M) context window with text and image input, per the model listing on OpenRouter and Moonshot's platform documentation.