Kimi K2.6

by Moonshot

Moonshot's Kimi K2.6 — large open-weight model with strong long-context performance.

ReasoningVisionToolsStructured output
Context window
262K
Max output
Input price
$0.75 /1M
Output price
$3.50 /1M

Benchmarks

Independent benchmark scores — composite indices for reasoning, coding, and math, plus individual eval scores where available.

Global rank#7 of 505 LLMs
TierFrontier
Output speed38 tok/s
First token1.46s
Intelligence Index53.9
Coding Index47.1
GPQA Diamond
91%
Humanity's Last Exam
36%
SciCode
54%
IFBench
76%
Long-context reasoning
70%
Terminal-Bench Hard
44%
τ²-Bench Telecom
96%

Available routes

The same Kimi K2.6 runs on 4 different routes through the Opper gateway. Each route has its own data-handling posture.

ProviderRegionZero data retentionTrainingLoggingContractInputOutput
DeepInfraUSNo
Pending verification
PAYG$0.75$3.50
FireworksUSDefaultNo
None for open models by default — does not log or store prompt or generation data without explicit opt-in.
PAYG$0.95$4.00
InceptronEUOpt-inNo
7–30 days default with per-workspace overrides
PAYG$0.80$3.50
NovitaUSNone
Not published; appendix available upon request.
PAYG$0.95$4.00

Human review: Abuse-flagged only

Other models from Moonshot

Start building with 300+ models

One API key. Every major provider. Up and running in minutes.

Get startedView Documentation
Kimi K2.6 by Moonshot — pricing, benchmarks, hosting routes | Opper AI