Kimi K2.6
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.
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%
See full leaderboard →Benchmarks via Artificial Analysis · View on AA
Available routes
The same Kimi K2.6 runs on 4 different routes through the Opper gateway. Each route has its own data-handling posture.
| Provider | Region | Zero data retention | Training | Logging | Contract | Input | Output |
|---|---|---|---|---|---|---|---|
| DeepInfra | US | — | No | Pending verification | PAYG | $0.75 | $3.50 |
| Fireworks | US | Default | No | None for open models by default — does not log or store prompt or generation data without explicit opt-in. | PAYG | $0.95 | $4.00 |
| Inceptron | EU | Opt-in | No | 7–30 days default with per-workspace overrides | PAYG | $0.80 | $3.50 |
| Novita | US | None | — | Not published; appendix available upon request. | PAYG | $0.95 | $4.00 |
Human review: Abuse-flagged only