kimi-k3Moonshot Kimi K3 is Kimi's most capable flagship model — 2.8 trillion parameters, built on KDA (Kimi Delta Attention) hybrid linear attention with Attention Residuals, native vision understanding, and a 1M-token context window. It is the world's first open-source 3-trillion-scale model, designed for long-horizon coding, knowledge work, and reasoning. Served via the OpenAI-compatible /v1/chat/completions endpoint; supports prompt caching, with cache hits billed at $0.36 / 1M input tokens.
Kimi's most capable flagship — the first open-source 3-trillion-scale model
Understands images natively alongside text
1,000,000-token context window for long-horizon coding and knowledge work
Call via the /v1/chat/completions endpoint
Cache hits billed at $0.36 / 1M input tokens
View complete API reference with all parameters and examples.
View complete API reference with streaming, thinking, and more.
Billing: Cost = (input_tokens * input_price + output_tokens * output_price) / 1,000,000
Kimi K3 is a Large Language Model API provided by Moonshot. Moonshot Kimi K3 is Kimi's most capable flagship model — 2.8 trillion parameters, built on KDA (Kimi Delta Attention) hybrid linear attention with Attention Residuals, native vision understanding, and a 1M-token context window. It is the world's first open-source 3-trillion-scale model, designed for long-horizon coding, knowledge work, and reasoning. Served via the OpenAI-compatible /v1/chat/completions endpoint; supports prompt caching, with cache hits billed at $0.36 / 1M input tokens. Through API Models platform, you can access this model via a unified API with transparent pay-as-you-go pricing. Current pricing: Input: $3.6, Output: $18 per 1M tokens.
Build intelligent conversational systems to automatically answer user queries and improve service efficiency.
Automatically write articles, emails, ad copy, and other text content to boost productivity.
Assist with code writing, debugging, and code review to accelerate software development.
Understand and analyze unstructured data, extract key insights, and generate summary reports.
Kimi K3 is available through API Models at: Input: $3.6, Output: $18 per 1M tokens. Billing is pay-as-you-go — you only pay for what you generate.
Sign up at API Models, get your API key, and call our unified API endpoint. We provide detailed API documentation with code examples in cURL, Python, and Node.js.
API Models offers the same Kimi K3 model through our aggregation platform. We provide a unified API interface so you do not need separate accounts for each provider - one API key to access all models.
On API Models, Kimi K3 runs alongside 60+ models on one API key and one balance, so choosing is about fit, not lock-in. It supports Vision, 1M Context, Reasoning, OpenAI-compatible, Prompt Cache, and you can weigh it on price and capability against other Large Language Model models, then switch by changing a single model-name string — no new account or integration. Browse every Large Language Model option with live pricing at apimodels.app/models.
Kimi K3 supports: Vision, 1M Context, Reasoning, OpenAI-compatible, Prompt Cache. See the API Models docs for full parameters and call examples.
Yes. API Models exposes Kimi K3 through a single unified API and one key — no separate provider accounts, and no need to handle each provider's regional network access yourself.
We support Stripe (Visa, Mastercard, and other international cards) and Alipay. Credits are available instantly after payment.