Kimi K3 pricing and specs

Pricing per 1M tokens

Note: platform.moonshot.ai/docs/pricing/chat now redirects to platform.kimi.ai. Flat pricing with no tiering by context length (K3 quickstart FAQ). Cache writes are billed per TTL: $3.00 for 5 min (the default) and $6.00 for 1h. A cache hit is billed only at the cached input price and refreshes the TTL with no new write charge. The Batch API page lists only kimi-k2.7-code and kimi-k2.6, so batch prices are blank. max output is the documented max_completion_tokens ceiling (default 131072, up to 1048576), and input plus output must fit in the 1M context. Thinking is always on, with reasoning_effort set to low, high or max (default max). Takes text, image and video input. Unlocked after a top-up of at least $1. The release date is left blank because the changelog says only 'July 2026' and the launch blog gives no explicit date. The gateway also lists moonshotai/kimi-k3-fast, which has no first-party price and is not included.

Specs

Context window

1,048,576 tokens

Max output

1,048,576 tokens

Provider

Moonshot AI

API model id

kimi-k3

Vercel AI Gateway id

moonshotai/kimi-k3

Weights

Open weights

License

Kimi K3 License (Hugging Face license tag: other)

Weights download

huggingface.co

What Kimi K3 costs in practice

Worked from the standard list rates above, with the math shown so you can swap in your own token counts.

Compare with

Compare

Side-by-side pages with both models' prices, specs, cost examples and like-for-like benchmark rows.

• Kimi K3 vs Gemini 4 ArgonSimilar price, same tier
• Kimi K3 vs GPT-6.1 SolSimilar price, same tier
• Kimi K3 vs Claude Sonnet 5.5Similar price, same tier
• Kimi K3 vs Claude Opus 5.5Similar price, same tier
• Kimi K3 vs Grok 4.7Similar price, same tier
• Kimi K3 vs Qwen3.8-2.4T-A95BSimilar price, same tier
• Kimi K3 vs Qwen3.8-MaxSimilar price, same tier
• Kimi K3 vs Kimi K2.6Same provider, successor

Related reading

• Kimi K3 Is GA in GitHub Copilot: Pricing, Rollout, and What It Means for Model ChoiceKimi K3 is GA in GitHub Copilot at $3/$15 per million tokens, off by default for Business and Enterprise. Rollout details and what it means for model choice.
• AMD MI355X vs NVIDIA B200 vs B300 for Open-Weight ServingAMD MI355X vs NVIDIA B200 vs B300 for serving Kimi K3's about 1.5TB of open weights: verified specs, the Wafer benchmark, and cost per token for each.
• Kimi K3 Weights Land on HuggingFace: 2.8T Open Frontier Model You Can Actually DownloadKimi K3 open weights are on HuggingFace: 2.8T parameters, 1M context, native MXFP4 and a ~1.63TB download. The specs, license terms and HN reaction.
• Kimi K3 in 10 Minutes: Moonshot AI's 2.8T Open Model, API Setup, Pricing, and BenchmarksKimi K3 from Moonshot AI is a 2.8T open model with a 1M-token context and an OpenAI-compatible API. How to call it, what it costs, and how it benchmarks.
• Where to Access Kimi K3: Every Provider and Price Compared (2026)Where to access Kimi K3: Moonshot's API at $3 input and $15 output per million tokens, OpenRouter hosts, inference clouds, and open weights.
• Kimi K3 Developer Guide: What the 2.8T Open Model ChangesKimi K3 developer guide: the 2.8T-parameter model's 1M-token context, native vision, API pricing and open-weights timing, and how it fits coding agents.

FAQ