Kimi K3.1 Pro
Moonshot AIUpdated October 2026. Kimi K3.1 Pro by Moonshot AI: $2.00/M cache-miss input, $10.00/M output tokens. Cached input: $0.2/M. Explicit cache writes: $2.00/M. 1.0M context. Vision & Function Calling. Free calculator + compare 40+ models.
Input Price
$2.00
cache miss / 1M tokens
Cached Input
$0.2
per 1M tokens
Output Price
$10.00
per 1M tokens
Context Window
1.0M
tokens
Kimi K3.1 Pro price history
Per 1M cache-miss input / output tokens. See all AI API price changes
- 2026-10-23Launch price$2.00 / $10.00
One third cheaper than Kimi K3 ($3/$15). A Highspeed endpoint costs $4/$20. Kimi API pricing
Cheaper ways to use Kimi K3.1 Pro
Current free credits and discounts that apply to Moonshot AI models.
- 🌋火山方舟（豆包）Free Tier— Up to 5M free inference tokens per day for developers (check the console for the exact allowance)
- 💧硅基流动 SiliconFlowFree Credits— ¥16 voucher after real-name verification; referrer and new user each get ¥16; several small models are freeends 2026-12-31
Specifications
| Provider | Moonshot AI |
| Model ID | kimi-k3.1-pro |
| Input Price | $2.00 / 1M cache-miss tokens |
| Cached Input Price | $0.2 / 1M tokens |
| Explicit Cache Write Price | $2.00 / 1M tokens |
| Output Price | $10.00 / 1M tokens |
| Context Window | 1.0M tokens |
| Max Output | Not published by provider |
| Capabilities | textvisionfunction_callingstructured_output |
| Release Date | 2026-10-23 |
| Pricing Source | Official Moonshot AI pricing |
| Price Verified | 2026-10-25 · Kimi K3 is $3/M input, $0.30/M cached input, and $15/M output. Cache writes are $3/M for the default 5-minute TTL or $6/M for 1 hour; K2.7 Code and K2.6 prices remain unchanged. Kimi K3.1 Pro (2026-10-23) is $2/$10. K2 models close to new users on 2026-10-31 and retire by end of December 2026. |
| Notes | Newest Kimi flagship, cheaper than Kimi K3 ($3/$15). A separate Highspeed endpoint costs $4/$20 per 1M tokens. Cache hits cost $0.20/M; K3-series cache writes are billed by TTL. |
Monthly Cost Estimates
Estimated monthly costs based on different daily usage levels (assuming 50% input / 50% output split). Input estimates use cache-miss pricing, so cache-heavy workloads can be lower.
| Daily Tokens | Monthly Cost | Annual Cost |
|---|---|---|
| 10K | $1.80 | $21.60 |
| 50K | $9.00 | $108.00 |
| 100K | $18.00 | $216.00 |
| 500K | $90.00 | $1080.00 |
| 1.0M | $180.00 | $2160.00 |
About Kimi K3.1 Pro
Kimi K3.1 Pro is a large language model by Moonshot AI. It features a 1.0M token context window; the provider does not publish a separate maximum-output limit. The model supports 4 capabilities: text, vision, function_calling, structured_output.
At $2.00 per million cache-miss input tokens and $10.00 per million output tokens, Kimi K3.1 Pro is positioned as a mid-range option in the Moonshot AI lineup. Repeated prefix input can be charged at $0.2 per million cached tokens. Use our Token Counter to estimate how many tokens your prompts use, and our Pricing Calculator to compare costs across all models.
Kimi K3.1 Pro Key Details
- Pricing: $2.00/M cache-miss input tokens, $0.2/M cached input tokens, $2.00/M explicit cache writes, $10.00/M output tokens
- Context window: 1.0M tokens — one of the largest available
- Max output: not separately published by the provider
- Capabilities: text, vision, function_calling, structured_output
- Highlights: Newest Kimi flagship, cheaper than Kimi K3 ($3/$15). A separate Highspeed endpoint costs $4/$20 per 1M tokens. Cache hits cost $0.20/M; K3-series cache writes are billed by TTL.
- Released: 2026-10-23
Other Moonshot AI Models
Similar Price Range
Related Tools
FAQ
How much does Kimi K3.1 Pro cost?
Kimi K3.1 Pro costs $2.00 per million cache-miss input tokens and $10.00 per million output tokens. Cached input costs $0.2 per million tokens. For a typical workload of 100K input tokens/day and 50K output tokens/day, expect approximately $21.00/month before cache-hit savings.
What is Kimi K3.1 Pro's context window?
Kimi K3.1 Pro supports a context window of 1.0M tokens. This means your combined input prompt and output response can be up to 1.0M tokens. Moonshot AI does not publish a separate maximum-output limit for this model.
Is Kimi K3.1 Pro good for my use case?
Kimi K3.1 Pro supports text, vision, function_calling, structured_output. As a mid-range model, it balances capability and cost for most production use cases. Use our Pricing Calculator to compare with alternatives.