All Models
Kimi K2
Kimi model for long-context chat, coding, and agentic reasoning
Benchmarks
Available Providers (19)
| Provider | Model ID | Input Cost | Output Cost | Context | Max Output | Docs |
|---|---|---|---|---|---|---|
 iFlow | kimi-k2 | $0/MTok | $0/MTok | 128K | 64K | |
 Nvidia | moonshotai/kimi-k2-instruct-0905 | $0/MTok | $0/MTok | 262.1K | 262.1K | |
 NanoGPT | moonshotai/Kimi-K2-Instruct-0905 | $0.40/MTok | $1.80/MTok | 262.1K | 100.4K | |
| NanoGPT | moonshotai/kimi-k2-instruct-0711 | $0.40/MTok | $1.80/MTok | 128K | 8.2K | |
 OpenCode Zen | kimi-k2 | $0.40/MTok | $2.50/MTok | 262.1K | 262.1K | |
 Helicone | kimi-k2-0905 | $0.50/MTok | $2/MTok | 262.1K | 16.4K | |
 FastRouter | moonshotai/kimi-k2 | $0.55/MTok | $2.20/MTok | 131.1K | 32.8K | |
 LLM Gateway | novita/kimi-k2 | $0.57/MTok | $2.30/MTok | 131.1K | 131.1K | |
 DevPass (LLM Gateway) | kimi-k2 | $0.57/MTok | $2.30/MTok | 256K | 16.4K | |
 Kilo Gateway | moonshotai/kimi-k2 | $0.57/MTok | $2.30/MTok | 131.1K | 98.3K | |
 OpenRouter | moonshotai/kimi-k2 | $0.57/MTok | $2.30/MTok | 131.1K | 98.3K | |
| Helicone | kimi-k2-0711 | $0.57/MTok | $2.30/MTok | 131.1K | 16.4K | |
 NovitaAI | moonshotai/kimi-k2-0905 | $0.60/MTok | $2.50/MTok | 262.1K | 262.1K | |
 Jiekou.AI | moonshotai/kimi-k2-0905 | $0.60/MTok | $2.50/MTok | 262.1K | 262.1K | |
| Kilo Gateway | moonshotai/kimi-k2-0905 | $0.60/MTok | $2.50/MTok | 262.1K | 98.3K | |
| OpenRouter | moonshotai/kimi-k2-0905 | $0.60/MTok | $2.50/MTok | 262.1K | 98.3K | |
 ZenMux | moonshotai/kimi-k2-0905 | $0.60/MTok | $2.50/MTok | 262K | 64K | |
 Qiniu | kimi-k2 | —/MTok | —/MTok | 128K | 128K | |
| Qiniu | moonshotai/kimi-k2-0905 | —/MTok | —/MTok | 256K | 100K |
Capabilities
Reasoning
Tool Calling
Attachments
Open Weights
Structured Output