All models
Moonshot AI
Kimi K3 balancedruns locally
moonshot/kimi-k3
Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...
Input / 1M
$3.00
USD per million tokens
Output / 1M
$15.00
USD per million tokens
Est. cost / token
$0.000006
$6.00 per 1M, 3:1 mix
Context window
1.05M
max output 1.05M
Major features
VisionOpen weightsCachingReasoningJSON schemaToolsVideo in
Task suitability (heuristic 1–5, not a benchmark)
- coding4
- reasoning4
- math4
- summarization4
- extraction4
- classification4
- chat4
- creative4
- translation4
- vision4
- long context5
- agentic4
Run it locally
Will it run on my machine? →| Quantization | Quality | Memory needed (8K ctx) |
|---|---|---|
| Q2_K | poor | 1235 GB |
| Q3_K_M | fair | 1440 GB |
| Q4_K_Mrecommended | good | 1797 GB |
| Q5_K_M | very good | 2089 GB |
| Q6_K | excellent | 2407 GB |
| Q8_0 | near-lossless | 3114 GB |
| F16 | lossless | 5851 GB |
Estimates.
Price history
| Recorded | Input | Output | Cached | Source |
|---|---|---|---|---|
| 2026-11-05 03:20 | $3.00 | $15.00 | $0.30 | litellm+openrouter |
A row is added whenever a sync detects a price change. Vendor pricing source
Pricing (USD per 1M tokens)
- Input
- $3.00
- Output
- $15.00
- Cached input
- $0.30
- Blended (3:1)
- $6.00
Details
- Company
- Moonshot AI
- Version
- 3
- Family
- Kimi
- Released
- 2026-07-16
- Parameters
- 2.78T
- Max output
- 1.05M
- Open weights
- Yes
- Inputs
- image, text, video
- Last synced
- 21 min ago