Kimi APIStableChecked 2026-07-17Official source ↗

Kimi K2.7 Code High-Speed pricing, context window, and cost calculator

The higher-throughput Kimi K2.7 Code API variant with separate source-tracked token rates and the same 262,144-token context window.

Verified fields

Quick facts

API access providerKimi API
Model creatorMoonshot AI
API model IDkimi-k2.7-code-highspeed
Default input / 1M$1.90
Default output / 1M$8.00
Context window262,144
Default profilestandard
Acceptstext
Producestext
StatusStable

Supported 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.

ProfileInput / 1MCached input / 1MOutput / 1MNotes
standardDefault$1.90 USD$0.38 USD$8.00 USDUsed for default estimates.
Workload estimate

Kimi K2.7 Code High-Speed cost calculator

Change the workload assumptions. The calculator uses the same shared pricing resolver as StackLens Compare.

Estimated monthly total$59.00
Monthly input cost
$19.00
Monthly output cost
$40.00
Per 1,000 requests
$5.90
Active profile
standard

Estimate excludes untracked provider-specific charges.

Explicit assumptions

Common workload examples

Input only

1M input tokens

$1.90 under the standard profile, excluding output and other charges.

Output only

1M output tokens

$8.00 under the standard profile, excluding input and other charges.

Default workload

10,000 monthly requests

At 1,000 input and 500 output tokens per request: $59.00 under standard.

Cache scenario

50% cached input

The same default workload with 50% cached input is estimated at $51.40. Cache savings apply only to the tracked cached-input rate.

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 publish a separate maximum-output figure for the Highspeed endpoint, so StackLens leaves that field unverified.