Kimi K2 Turbo
Kimi K2 Turbo is Moonshot AI (Kimi)'s language model with a 256K context window and up to 16K output tokens. A high-throughput variant of Kimi K2 delivering up to 100 tokens per second, optimized for speed-critical tool-use and conversational applications.
| Specifications | |
|---|---|
moonshot-kimi-k2-turbo | |
| Language | |
| Active | |
| Moonshot AI (Kimi) | |
| 256K tokens | |
| 16K tokens | |
| Text | |
| Text | |
| · 10 months ago | |
Capabilities
Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities1/13
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 | |
| $1.15 | $8.00 | $0.15 | |
Cost Calculator
US Dollar ($)
Preset:
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Kimi K2.7 Code High Speed | 262K | $1.90 | $8.00 | Available | |
| Kimi K2 Thinking Turbo | 262K | $1.15 | $8.00 | Deprecated | |
| Kimi K2 Turbo | 256K | — | — | Current | |
| Kimi K2.5 Non-Reasoning | — | — | — | — | Available |
| Kimi K2 Instruct V0 | — | — | — | — | Available |
| Kimi K2 Preview | — | 262K | $0.600 | $2.50 | Deprecated |
| Kimi K2 Turbo Preview | — | 262K | $1.15 | $8.00 | Deprecated |
| Kimi K2.5 Thinking | — | — | $0.600 | $3.00 | Available |
| Kimi K2.6 Thinking | — | — | $0.950 | $4.00 | Available |
| Kimi | 262K | $0.680 | $3.41 | Deprecated | |
| Kimi Linear 48B A3B Instruct | — | — | — | — | Available |