Kimi K3.1 Pro

PRICE / USD

Not verified

Per 1 million uncached input tokens · output billed separately

Input / 1M tokens

Not verified

Output / 1M tokens

Not verified

Cached input / 1M tokens

Not verified

Cache write / 1M tokens

Not verified

The launch post lists kimi-k3.1-pro at ¥1.3 per million cache-hit input tokens, ¥13 cache-miss input and ¥68 output. No verified USD listing was available at the October 23, 2026 check, so no USD figure is shown.

SPEED & CAPABILITIES

Not benchmarked

No speed classification verified for this version and serving tier. This does not mean it is slow.

Our own output-speed measurement

Not measured

Context window

1,048,576

API model ID

kimi-k3.1-pro

No reviewed Intelligence Index score for this exact model version and setting.

K3.1 Pro is a post-training of the K3 base model and a separate version from the K2.6 historical evaluation.

No third-party Artificial Analysis index score exists for this version yet; launch-post benchmark figures are vendor-reported.

Suggested starting role: complex planning. The documented focus on long-horizon software engineering and reasoning carries over from the K3 base model, and the launch post highlights coding, 3D creation, financial research, and long-horizon agent work. Its large context is not itself evidence of higher accuracy. This is editorial guidance, not a benchmark score.