Kimi K2
Kimi K2 is Moonshot AI (Kimi)'s language model with a 262K context window and up to 100K output tokens, available from 4 providers, starting at $0.57 / 1M input and $2.30 / 1M output. A large-scale mixture-of-experts LLM with 1 trillion total parameters and 32B active parameters, trained with the Muon optimizer for strong agentic and tool-use performance.
| Specifications | |
|---|---|
moonshot-kimi-k2 | |
| Language | |
| Active | |
| Moonshot AI (Kimi) | |
| 262K tokens | |
| 100K tokens | |
| ImagePDFText | |
| Text | |
| default | |
| 1.06T | |
| 145 | |
| 423 | |
| 423 | |
| · 1 year ago | |
| · 2 years ago | |
Capabilities
Input3/5
Text✓
Image✓
Audio·
Video·
PDF✓
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities6/13
Reasoning✓
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling✓
Structured Outputs✓
Native JSON Schema✓
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching✓
Assistant Prefill·
Pricing by Provider
US Dollar ($)
Per 1M tokens
| Provider | Standard | |
|---|---|---|
| Input $ / 1M | Output $ / 1M | |
| $0.6 | $2.50 | |
| $0.6 | $2.50 | |
| $0.57 | $2.30 | |
| $0.6 | $2.50 | |
| $0.57 | $2.30 | |
Cost Calculator
US Dollar ($)
Preset:
Cheapest Instances to Run It
Cloud GPU instances that can host Kimi K2, ranked by cheapest on-demand price. The model needs about 2541 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.
All clouds
FP16 (full precision)
US Dollar ($)
No GPU instances fit Kimi K2 at FP16 precision — try a lower precision such as INT4.
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Kimi K2 Thinking | 262K | $0.470 | $1.20 | Deprecated | |
| Kimi K2 | 262K | $0.570 | $2.30 | Current |