| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| marketplace | Token | ¥3.65 | ¥18.27 | ¥0.3654 | - |
Moonshot AI
Kimi K3
Kimi flagship model with 2.8T parameters, native vision, and a 1M context window
Kimi K3 is Moonshot AI's most capable flagship model, with 2.8 trillion parameters, Kimi Delta Attention, Attention Residuals, sparse MoE, native vision, and a 1,048,576-token context window. It targets long-horizon coding, knowledge work, and reasoning, with tool calling, structured output, Partial Mode, and automatic context caching.
Moonshot AI Official Pricing
CNYInput
Official flat pricing with no context-length tiers: CNY 20 uncached input, CNY 2 cached input, and CNY 100 output per 1M tokens; the context window is 1,048,576 tokens.
Output
Official flat pricing with no context-length tiers: CNY 20 uncached input, CNY 2 cached input, and CNY 100 output per 1M tokens; the context window is 1,048,576 tokens.
Cache read
Official flat pricing with no context-length tiers: CNY 20 uncached input, CNY 2 cached input, and CNY 100 output per 1M tokens; the context window is 1,048,576 tokens.
Official flat pricing with no context-length tiers: CNY 20 uncached input, CNY 2 cached input, and CNY 100 output per 1M tokens; the context window is 1,048,576 tokens.
Relay Comparison
Compare token, per-request, or per-second pricing by relay channel.
Price range ¥6.5 / 1M tokens
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| 国产Token计划 | Token | ¥6.5 | ¥27 | ¥1.3 | - |
Price range ¥10.2 / 1M tokens
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| 中国模型-企业级 | Token | ¥10.2 | ¥51 | ¥1.02 | - |
| 中国模型-企业级[openai协议] | Token | ¥10.2 | ¥51 | ¥1.02 | - |
Price range ¥16 / 1M tokens
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| kimi-officially | Token | ¥16 | ¥80 | ¥1.6 | - |
Price range ¥10 / 1M tokens
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| sale | Token | ¥10 | ¥50 | - | - |
Price range ¥15 / 1M tokens
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| Kimi | Token | ¥15 | ¥75 | ¥1.5 | - |
Price range ¥18 / 1M tokens
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| default | Token | ¥18 | ¥90 | ¥1.8 | - |
Price range ¥20 - ¥30 / 1M tokens
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| default | Token | ¥20 | ¥100 | - | - |
| 企业级高可用大模型 | Token | ¥20 | ¥100 | - | - |
| 纯AZ | Token | ¥30 | ¥150 | - | - |
How should Kimi K3 relay pricing be compared?
This Kimi K3 pricing page compares official pricing with public prices from 8 listed AI gateways. Token prices are shown in CNY per 1M tokens, while per-request, per-second, and per-character rows use the unit shown in the table. Last updated: 07/17/2026, 10:12.
- Data sources
- Public price catalogs, official pricing records, and monitoring results.
- Metric definitions
- Uptime means successful probe response rate, fake-rate signals possible model mismatch or abnormal output risk, and latency is average API response time.
- Risk note
- Relay gateways are third-party services. Pricing, billing, privacy, and stability can change; start with a small top-up and verify reliability before continued use.