Kimi K3 (batch)
moonshotai/kimi-k3:batch
Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.
Key facts
- Input price
- $2.28 / 1M tokens
- Output price
- $11.40 / 1M tokens
- Context window
- 1M tokens
- Max output
- 16K tokens
- Accepts
- Text, Images, Video
- Returns
- Text
Example: 1,000 requests with 1,000 input and 500 output tokens each would cost about $7.98 (1M input tokens × $2.28 + 0.5M output tokens × $11.40). Estimate your own usage.
Prices are the provider’s own per-token rates with zero markup, from our price list as of Oct 18, 2026. If a call has extra provider charges (images, audio, web search, cached prompts), you pay the reported cost.
Call it from your code
curl https://api.tokenctr.com/v1/chat/completions \
-H "Authorization: Bearer $TOKENCENTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "moonshotai/kimi-k3:batch", "messages": [{"role": "user", "content": "Hello!"}]}'Works with any OpenAI-compatible SDK: set the base URL to https://api.tokenctr.com/v1. Quickstart
Benchmarks
Artificial Analysis
- Intelligence index
- 43.6
- Coding index
- 76.2
- Agentic index
- 50
Design Arena
| Category | Rank | Elo | Win rate |
|---|---|---|---|
| Agents: Full-stack | 2 | 1315 | 61.8% |
| Agents: HTML slides | 2 | 1256 | 59.6% |
| Agents: Agentic game dev | 3 | 1252 | 55% |
| Agents: Mobile apps | 4 | 1264 | 57% |
| Agents: Slides (python-pptx) | 4 | 1273 | 59.2% |
| Agents: Web apps | 4 | 1285 | 59% |
| Models: Code | 4 | 1363 | 62.4% |
| Models: Data visualization | 4 | 1352 | 63.2% |
| Models: Websites | 4 | 1336 | 59.2% |
| Agents: Android native | 5 | 1262 | 55.4% |
| Models: SVG | 6 | 1299 | 59.2% |
| Models: UI components | 6 | 1346 | 60.3% |
| Models: Game dev | 7 | 1364 | 60.9% |
| Models: 3D | 8 | 1389 | 67.3% |
| Agents: Godot game dev | 14 | 1223 | 48.2% |
Source: Artificial Analysis indexes and Design Arena results as published in OpenRouter’s model data, fetched Oct 15, 2026. Higher is better. Not measured by TokenCenter. See all rankings.