kimi-for-coding-highspeed

Kimi for Coding HighSpeed API — price per token

The faster tier of the coding SKU, priced at exactly double the base model on every leg — input, cached input and output alike.

Pricing per 1M tokens

RateOfficial MoonshotHere (−50%)
Input$1.9$0.95
Cached input$0.38$0.19
Cache write$1.9$0.95
Output$8$4

Input

Official Moonshot
$1.9
Here (−50%)
$0.95

Cached input

Official Moonshot
$0.38
Here (−50%)
$0.19

Cache write

Official Moonshot
$1.9
Here (−50%)
$0.95

Output

Official Moonshot
$8
Here (−50%)
$4

Every request is metered at the official rate first, then the flat 50% B2C discount is subtracted before it touches your prepaid balance. Context window: 256K tokens. Max output: not published.

Best for

  • Interactive sessions where latency matters more than token price.
  • Short agent turns that are dominated by time to first token.

Good to know

  • Cached input bills at 10% of input — caching is automatic on repeated prefixes.
  • KIMI publishes no separate cache-write rate: a write is a cache miss and bills at the input rate.

How to use Kimi for Coding HighSpeed

Create a free account, generate one key, and point any Anthropic-compatible tool at https://router.apitoken.sale with model ID kimi/kimi-for-coding-highspeed, authenticated with x-api-key. Kimi speaks the Anthropic Messages protocol, so the catalogue namespace in the model ID is what selects it — the base URL is the same one Claude uses. Eligible new accounts include $5 of platform bonus credit — enough to test the model before topping up.

Frequently asked questions

How much more does HighSpeed cost?

Exactly 2× the base coding SKU on every leg: $1.90/$8.00 officially against $0.95/$4.00, and the same doubling on cached input.

Is it a different model?

It is the faster tier of the same coding SKU. The rate card is the only thing that differs by a fixed factor.

Run Kimi for Coding HighSpeed on the Anthropic Messages API at a flat 50% off — instant key, prepaid balance, card or crypto.