Kimi K3 pricing, context window, and cost calculator
Moonshot AI's flagship reasoning model with source-tracked token pricing, native visual input, and a 1,048,576-token context window.
Verified fields
Quick facts
kimi-k3Supported capabilities
- Streaming
- Function calling
- Structured outputs
- Prompt caching
- Reasoning
Only capabilities explicitly tracked from provider documentation are shown.
Source-tracked rates
Verified pricing profiles
Amounts are USD per 1M tokens unless the column states an hourly storage unit.
| Profile | Input / 1M | Cached input / 1M | Output / 1M | Notes |
|---|---|---|---|---|
| standardDefault | $3.00 USD | $0.30 USD | $15.00 USD | Used for default estimates. |
Workload estimate
Kimi K3 cost calculator
Change the workload assumptions. The calculator uses the same shared pricing resolver as StackLens Compare.
Estimated monthly total$105.00
- Monthly input cost
- $30.00
- Monthly output cost
- $75.00
- Per 1,000 requests
- $10.50
- Active profile
- standard
Estimate excludes untracked provider-specific charges.
Explicit assumptions
Common workload examples
1M input tokens
$3.00 under the standard profile, excluding output and other charges.
1M output tokens
$15.00 under the standard profile, excluding input and other charges.
10,000 monthly requests
At 1,000 input and 500 output tokens per request: $105.00 under standard.
50% cached input
The same default workload with 50% cached input is estimated at $91.50. Cache savings apply only to the tracked cached-input rate.
Tracked relationships
Related models
StackLens relationship map based on model families and published decision comparisons. Find a workload match → Open relationship map → Open price map →
Featured comparisons
- Kimi K3 vs Kimi K2.7 Code cost
- Kimi K3 vs Kimi K2.7 Code High-Speed cost
- Kimi K3 vs Grok 4.5 cost
- Kimi K3 vs GPT-5.6 Sol cost
- Kimi K3 vs DeepSeek V4 Pro cost
- Kimi K3 vs Claude Sonnet 4.6 cost
Continue your research
Verification
Sources and methodology
Pricing and limits are source-tracked and may change. Verify current values with the provider before making production purchasing decisions.
Calculator profile rule: standard is the verified default. Kimi does not currently publish a separate maximum-output figure for K3, so StackLens leaves that field unverified.