BenchLeader
Moonshot AIOpen weightsReasoning modelAuto-detected

Kimi K2.7 Code HighSpeed

Not yet ranked: too few independent results so far. Released 12 Jun 2026.

Blended price
$3.42/M
$1.90 in · $8.00 out
Output speed
First answer
Context
262k

No independent quality benchmark results yet — only pricing and metadata.

What a task costs

Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache at $0.380 per 1M. Reasoning tokens are not modelled.

WorkloadTokens in / outCostWith cachingTime
Chat reply400 / 300$0.0032$0.0027
Summarise a 30-page report12,000 / 600$0.028$0.014
Code edit6,000 / 1,500$0.023$0.017
Agentic coding session60,000 / 4,000$0.146$0.078
Structured extraction2,000 / 200$0.0054$0.0031

See also

Data as of 9 Sept 2026. Compare with another model.