Kimi (Moonshot AI) API Pricing 2026
Moonshot AI's Kimi API supports Kimi K3, K2.7 Code, and K2.6 for long-horizon coding, multimodal understanding, reasoning, and agent tasks. K3 has a 1M-token context window.
Pricing verified 2026-08-03. Sourced from platform.moonshot.cn/docs/pricing.
Get Kimi (Moonshot AI) API access →Kimi (Moonshot AI) Model Pricing
Prices in USD per 1M tokens
| Model | Input / 1M | Output / 1M | Context |
|---|---|---|---|
Kimi K2.7 Code Coding-focused model; $0.19/1M cached input, 256K context, thinking and multimodal input | $0.95 | $4 | 262,144 |
Kimi K2.7 Code HighSpeed High-speed K2.7 Code variant; $0.38/1M cached input and approximately 180 tokens/sec output | $1.9 | $8 | 262,144 |
Kimi K3 Kimi flagship; $0.30/1M cached input, 1M context, native multimodal and reasoning | $3 | $15 | 1,048,576 |
Kimi K2.6 $0.16/1M cached input, 256K context, multimodal general-purpose model | $0.95 | $4 | 262,144 |
Kimi K2.5 Previous multimodal Kimi generation; verify availability before using in production | $0.95 | $4 | 262,144 |
How to read these estimates
The monthly table assumes 70% input tokens and 30% output tokens. It is a consistent comparison baseline, not a prediction of your workload. Actual bills can also include cached-input discounts, batch pricing, tool calls, minimum charges, regional differences, retries, and taxes.
The linked source is the provider's pricing documentation. Verify the current rate card and model availability before committing to a budget.
Estimated Monthly Cost (70% input / 30% output split)
| Model | 1M tokens/mo | 10M tokens/mo | 100M tokens/mo | 1B tokens/mo |
|---|---|---|---|---|
| Kimi K2.7 Code | $1.86 | $18.65 | $187 | $1,865 |
| Kimi K2.7 Code HighSpeed | $3.73 | $37.30 | $373 | $3,730 |
| Kimi K3 | $6.60 | $66.00 | $660 | $6,600 |
| Kimi K2.6 | $1.86 | $18.65 | $187 | $1,865 |
| Kimi K2.5 | $1.86 | $18.65 | $187 | $1,865 |
Frequently Asked Questions
How much does Kimi (Moonshot AI) LLM API cost?
Kimi (Moonshot AI) offers 5 models ranging from $0.950/1M to $3.00/1M input tokens. Moonshot AI's Kimi API supports Kimi K3, K2.7 Code, and K2.6 for long-horizon coding, multimodal understanding, reasoning, and agent tasks. K3 has a 1M-token context window.
Is Kimi (Moonshot AI) cheaper than self-hosting?
For low-volume workloads (under 100M tokens/month), cloud APIs like Kimi (Moonshot AI) are almost always cheaper than purchasing and maintaining GPU hardware. Use our calculator to find the exact break-even point for your usage.