# Kimi API pricing, every Moonshot AI model per million tokens

On 25 September 2026, Moonshot AI models on this list cost from $0.45 per million input tokens (Kimi K2.5) to $3.00 (Kimi K3), and from $2.25 per million output tokens (Kimi K2.5) to $15.00 (Kimi K3).

Prices checked 25 September 2026 at 06.00 UTC . Source OpenRouter public model list . US dollars per million tokens

Input tokens per call

Output tokens per call

Calls a day

Search models

| Model | Input | Output | Cached input | Batch in / out | Context | Your month | Listed |
|---|---|---|---|---|---|---|---|
| Kimi K3 | $3.00 | $15.00 | $0.30 | $2.28 / $11.40 | 1.04858M | $405.00 | 2026-07-16 |
| Kimi K2.7 Code | $0.6562 | $3.30 | $0.18 |  | 262K | $88.87 | 2026-06-12 |
| Kimi K2.6 | $0.95 | $4.00 | $0.16 |  | 262K | $117.00 | 2026-04-20 |
| Kimi K2.5 | $0.45 | $2.25 | $0.07 |  | 262K | $60.75 | 2026-01-27 |
| Kimi K2 Thinking | $0.60 | $2.50 | $0.15 |  | 262K | $73.50 | 2025-11-06 |
| Kimi K2 0905 | $0.60 | $2.50 |  |  | 262K | $73.50 | 2025-09-04 |
| Kimi K2 0711 | $0.57 | $2.30 |  |  | 131K | $68.70 | 2025-07-11 |

[Compare Moonshot AI with every other provider](https://shurco.ai/tools/llm-api-pricing/)

## Common questions

### How much does the Kimi API cost?

On 25 September 2026, Moonshot AI models on this list cost from $0.45 per million input tokens (Kimi K2.5) to $3.00 (Kimi K3), and from $2.25 per million output tokens (Kimi K2.5) to $15.00 (Kimi K3).

### What is the cheapest Kimi model?

For a typical mix of three input tokens to every output token, the cheapest is Kimi K2.5 at $0.45 per million input tokens and $2.25 per million output tokens.

### What is the newest Kimi model on the list?

Kimi K3, listed on 16 July 2026, at $3.00 per million input tokens and $15.00 per million output tokens.

### Which Kimi model has the largest context window?

Kimi K3, with 1.04858M tokens of context.

### Does Moonshot AI offer batch pricing?

Yes, 1 of its models on this list show a batch price, with batch input at a median of 76 percent of the standard price. Batch suits work that can wait for its answer.

## Other providers

[GPT](https://shurco.ai/tools/llm-api-pricing/openai/)[Claude](https://shurco.ai/tools/llm-api-pricing/anthropic/)[Gemini](https://shurco.ai/tools/llm-api-pricing/google/)[DeepSeek](https://shurco.ai/tools/llm-api-pricing/deepseek/)[Mistral](https://shurco.ai/tools/llm-api-pricing/mistral/)[Llama](https://shurco.ai/tools/llm-api-pricing/meta/)[Grok](https://shurco.ai/tools/llm-api-pricing/xai/)[Qwen](https://shurco.ai/tools/llm-api-pricing/qwen/)[GLM](https://shurco.ai/tools/llm-api-pricing/zai/)[Command](https://shurco.ai/tools/llm-api-pricing/cohere/)[Nova](https://shurco.ai/tools/llm-api-pricing/amazon/)[MiniMax](https://shurco.ai/tools/llm-api-pricing/minimax/)

## Choosing a model for a production agent

Price is one input. Quality on your own cases, latency and the cost of retries decide the rest. [Tell me what you are building.](https://shurco.ai/#contact)

Web version https://shurco.ai/tools/llm-api-pricing/moonshot/