# Kimi K3

> Moonshot's 2.8T open-weight multimodal reasoning model. Successor to K2.7 — 1M context, vision input, built for long-horizon agentic work.

Human version: https://kymaapi.com/models/kimi-k3
Live JSON: `GET https://kymaapi.com/v1/models` (no auth required)

## Facts

- **Model ID**: `kimi-k3` — pass this as `model` in the request body
- **Creator**: Moonshot AI
- **Released**: 2026-07-16
- **Context window**: 1M tokens
- **Max output**: 33K tokens per response — a hard ceiling, not a default
- **Price**: $4.05 in / $20.25 out per 1M, cached input 10%
- **Capabilities**: tools, vision, reasoning, caching

## Call it

```bash
curl https://kymaapi.com/v1/chat/completions \
  -H "Authorization: Bearer $KYMA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "kimi-k3", "messages": [{"role": "user", "content": "Hello"}]}'
```

## Positioning

Kimi K3 is a 2.8T open-weight reasoning model built for long-horizon agentic workflows and large-repo analysis. Developers should reach for it when they need a million-token context window with vision input and reliable tool execution.

## About

Kimi K3 is Moonshot’s 2.8T open-weight multimodal model, designed as a successor to K2.7. It accepts text and image inputs and outputs text, with native support for structured outputs, tool calling, and explicit reasoning steps. The model operates with a 1,048,576-token context window and a maximum output length of 32,768 tokens.

On Kyma, the model runs through an OpenAI-compatible endpoint with automatic request failover and exact cost reporting in the usage.cost field. Prompt caching is supported, reducing repeated prefix costs to 10% of the standard input rate. The platform serves it at a medium speed tier, averaging around 12 tokens per second in production.

The 32,768-token output cap means it is not suited for generating extremely long documents in a single pass. As a premium-tier model, it carries higher per-token costs than lighter alternatives, and its medium throughput requires planning for latency-sensitive applications.

## Use cases

- **Agentic Workflow Execution** — Handles multi-step coding and tool execution across extended sessions without losing context.
- **Large Repository Analysis** — Ingests entire codebases or documentation sets within its million-token window for cross-file reasoning.
- **Vision-Enabled Document Review** — Processes image inputs alongside text to extract and reason over multimodal data.
- **Structured Data Extraction** — Outputs strictly formatted JSON or XML for reliable downstream parsing and API integration.

## Not ideal for

It is not the right choice for high-throughput, low-latency chat or generating outputs longer than 32,768 tokens.

## Pick something else when

- You need faster response times and lower costs for simple chat → `deepseek-v4-flash`, `qwen3.7-flash`
- You require outputs exceeding 32,768 tokens for long-form drafting → `gpt-5.6-terra`, `gemini-3.6-flash`
- You want a cheaper open-weight model for basic code completion → `qwen-3-32b`, `deepseek-v3`

## See also

- All models: https://kymaapi.com/models.md
- Pricing: https://kymaapi.com/pricing.md
- Other models by Moonshot AI: https://kymaapi.com/models?q=Moonshot%20AI