DevTk.AI

Kimi K3

Moonshot AI

Kimi K3 by Moonshot AI: $3.00/M cache-miss input, $15.00/M output tokens. Cached input: $0.3/M. Explicit cache writes: $3.00/M. 1.0M context, 1.0M max output. Vision & Video. Price verified 2026-11-16.

Input Price

$3.00

cache miss / 1M tokens

Cached Input

$0.3

per 1M tokens

Output Price

$15.00

per 1M tokens

Context Window

1.0M

tokens

Kimi K3 price history

No price changes recorded for Kimi K3 in our AI API price change log (earliest entry: 2026-05-27). Current rates last verified against the official Moonshot AI pricing page on 2026-11-16. See all AI API price changes

Cheaper ways to use Kimi K3

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
See all AI deals and free credits →

Specifications

ProviderMoonshot AI
Model IDkimi-k3
Input Price$3.00 / 1M cache-miss tokens
Cached Input Price$0.3 / 1M tokens
Explicit Cache Write Price$3.00 / 1M tokens
Output Price$15.00 / 1M tokens
Context Window1.0M tokens
Max Output1.0M tokens
Capabilities
textvisionvideofunction_callingstructured_output
Release Date2026-07-16
Pricing SourceOfficial Moonshot AI pricing
Price Verified2026-11-16 · Kimi K3 is $3/M input, $0.30/M cached input, and $15/M output.
NotesKimi K3 global USD API rates. Automatic prefix caching uses a default 5-minute TTL with $3/M cache writes; one-hour writes cost $6/M. Cache hits cost $0.30/M and refresh the TTL without another write charge. Full model weights are available.

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 TokensMonthly CostAnnual Cost
10K $2.70 $32.40
50K $13.50 $162.00
100K $27.00 $324.00
500K $135.00 $1620.00
1.0M $270.00 $3240.00

How Kimi K3 Pricing Compares

Standard cache-miss input / output prices per 1M tokens, compared with active, price-verified models priced in USD. Cached, batch and long-context rates are not included.

  • Within Moonshot AI: 1 of 1 other active Moonshot AI models has a lower input price, and 1 has a lower output price.
  • Similar context window: among the 55 active models with a 524K–2.1M token context window, Kimi K3 ranks #43 from cheapest at a 50/50 input/output mix. Cheapest: Tencent Hy4 Flash ($0.07/$0.281). Most expensive: GPT-5.5 Pro ($30.00/$180.00).
  • Versus the previous release: compared with Kimi K2.6 (released 2026-04, $0.95/$4.00), input is +216% and output is +275%.

Use our Token Counter to estimate how many tokens your prompts use, and our Pricing Calculator to compare costs across all models.

Kimi K3 Key Details

  • Pricing: $3.00/M cache-miss input tokens, $0.3/M cached input tokens, $3.00/M explicit cache writes, $15.00/M output tokens
  • Context window: 1.0M tokens — 11 of 85 active models we track have a larger window
  • Max output: 1.0M tokens per response
  • Capabilities: text, vision, video, function_calling, structured_output
  • Highlights: Kimi K3 global USD API rates. Automatic prefix caching uses a default 5-minute TTL with $3/M cache writes; one-hour writes cost $6/M. Cache hits cost $0.30/M and refresh the TTL without another write charge. Full model weights are available.
  • Released: 2026-07-16

Other Moonshot AI Models

Similar Price Range

Related Tools

FAQ

How much does Kimi K3 cost?

Kimi K3 costs $3.00 per million cache-miss input tokens and $15.00 per million output tokens. Cached input costs $0.3 per million tokens. For a typical workload of 100K input tokens/day and 50K output tokens/day, expect approximately $31.50/month before cache-hit savings.

What is Kimi K3's context window?

Kimi K3 supports a context window of 1.0M tokens. This means your combined input prompt and output response can be up to 1.0M tokens. The maximum output per response is 1.0M tokens.

Is Kimi K3 good for my use case?

Kimi K3 supports text, vision, video, function_calling, structured_output. We track pricing and limits, not output quality, so test it on your own prompts before committing. The price comparison above lists cheaper and pricier models with a similar context window, and the Pricing Calculator estimates your monthly cost across all of them.