All models
Moonshot AI
Kimi K3.1 Pro frontierruns locally
moonshot/kimi-k3-1-pro
Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window. It is built for long-horizon coding, 3D...
Input / 1M
$2.00
USD per million tokens
Output / 1M
$10.00
USD per million tokens
Est. cost / token
$0.000004
$4.00 per 1M, 3:1 mix
Context window
1.05M
max output 1.05M
Major features
VisionOpen weightsCachingReasoningJSON schemaTools
Task suitability (heuristic 1–5, not a benchmark)
- coding5
- reasoning5
- math5
- summarization5
- extraction5
- classification5
- chat5
- creative5
- translation5
- vision5
- long context5
- agentic5
Run it locally
Will it run on my machine? →| Quantization | Quality | Memory needed (8K ctx) |
|---|---|---|
| Q2_K | poor | 1236 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 | 3115 GB |
| F16 | lossless | 5851 GB |
Estimates.
Price history
| Recorded | Input | Output | Cached | Source |
|---|---|---|---|---|
| 2026-11-05 03:20 | $2.00 | $10.00 | $0.20 | litellm+openrouter |
A row is added whenever a sync detects a price change. Vendor pricing source
Pricing (USD per 1M tokens)
- Input
- $2.00
- Output
- $10.00
- Cached input
- $0.20
- Blended (3:1)
- $4.00
Details
- Company
- Moonshot AI
- Version
- 3.1
- Family
- Kimi
- Released
- 2026-10-23
- Parameters
- 2.78T
- Max output
- 1.05M
- Open weights
- Yes
- Inputs
- image, text, video
- Last synced
- 21 min ago