Kimi K2 Thinking Turbo
MoonshotText
Kimi K2 Thinking Turbo is a text model from Moonshot with a context window of 262K tokens and max output of 262K tokens. Pricing starts at $1.15 per million input tokens and $8.00 per million output tokens.
Specifications
| Model Key | moonshot/kimi-k2-thinking-turbo |
| Provider | Moonshot |
| LiteLLM Provider | moonshot |
| Mode | Text |
| Canonical Name | kimi-k2-thinking-turbo |
| Context Window | 262K tokens |
| Max Output | 262K tokens |
Capabilities
✗ Vision✓ Function Calling✗ Reasoning✗ JSON Schema✗ System Messages✓ Web Search✗ Prompt Caching✗ Audio Input✗ Audio Output
Pricing
| Type | Per 1K Tokens | Per 1M Tokens |
|---|---|---|
| Input Tokens | $0.0011 | $1.15 |
| Output Tokens | $0.0080 | $8.00 |
| Cache Read (Input) | $0.000150 | $0.150 |
Similar Models
Models with similar capabilities and context window size.
Model | Provider | Mode | Input Price | Output Price | Context | Max Output | Vision | Functions |
|---|---|---|---|---|---|---|---|---|
| Devstral 2512:free | OpenRouter | Text | N/A | N/A | 262K | 262K | no | yes |
| Mimo V2 Flash | Novita | Text | $0.100 | $0.300 | 262K | 32K | no | yes |
| Mimo V2 Flash | OpenRouter | Text | $0.090 | $0.290 | 262K | 16K | no | yes |
| Qwen3 1p7b Fp8 Draft | Fireworks AI | Text | $0.100 | $0.100 | 262K | 262K | no | no |
| Qwen3 235B A22b 2507 | OpenRouter | Text | $0.071 | $0.100 | 262K | 262K | no | yes |
| Qwen3 235B A22B Instruct 2507 | Deepinfra | Text | $0.090 | $0.600 | 262K | 262K | no | no |
| Qwen3 235B A22b Thinking 2507 | OpenRouter | Text | $0.110 | $0.600 | 262K | 262K | no | yes |
| Qwen3 4B Instruct 2507 GGUF | Lemonade | Text | N/A | N/A | 262K | 33K | no | yes |
| Qwen3 Coder 30B A3B Instruct GGUF | Lemonade | Text | N/A | N/A | 262K | 33K | no | yes |
| Qwen3 Coder:480B Cloud | Ollama | Text | N/A | N/A | 262K | 262K | no | yes |