Kimi K2 Instruct
Kimi K2 Instruct is Moonshot AI (Kimi)'s language model with a 262K context window and up to 33K output tokens, available from 9 providers, starting at $0.5 / 1M input and $2.00 / 1M output. The instruction-tuned version of Kimi K2, a 1T-parameter MoE LLM optimized for following user instructions and agentic tool-use tasks.
| Specifications | |
|---|---|
moonshot-kimi-k2-instruct | |
| Language | |
| Active | |
| Moonshot AI (Kimi) | |
| 262K tokens | |
| 33K tokens | |
| Text | |
| Text | |
| 1.03T | |
| 2,352 | |
| 276,135 | |
| 2,074,036 | |
Capabilities
Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities3/13
Reasoning·
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling✓
Structured Outputs✓
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·
Pricing by Provider
US Dollar ($)
Per 1M tokens
| Provider | Standard | ||
|---|---|---|---|
| Input $ / 1M | Output $ / 1M | Cache Read $ / 1M | |
| $0.6 | $2.50 | N/A | |
| $0.5 | $2.00 | N/A | |
| N/A | N/A | $0.4 | |
| $0.6 | $2.50 | N/A | |
| $1.00 | $3.00 | $0.5 | |
| $0.57 | $2.30 | N/A | |
| $2.00 | $2.00 | N/A | |
| $0.57 | $2.30 | N/A | |
| $1.00 | $3.00 | N/A | |
| $0.6 | $2.50 | N/A | |
Cost Calculator
US Dollar ($)
Preset:
Cheapest Instances to Run It
Cloud GPU instances that can host Kimi K2 Instruct, ranked by cheapest on-demand price. The model needs about 2464 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 Instruct at FP16 precision — try a lower precision such as INT4.
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| DeepSeek V3.1 | 164K | $0.250 | $0.950 | Available | |
| DeepSeek V3 0324 | 164K | $0.270 | $1.12 | Available | |
| Kimi K2 Instruct | — | 262K | $0.500 | $2.00 | Current |