moonshot:moonshot/kimi-k3.1-pro

Common Name: Kimi K3.1 Pro

Moonshot
Released on Oct 23 12:00 AMSupportedTool InvocationSupportedReasoning
CompareTry in Chat

Moonshot AI's flagship 3T-class open-weight model with 1M context, strong coding, 3D creation, and financial research.

Specifications

Context
1048.6K
Maximum Output
1048.6K
Inputtext, image, video
Outputtext

Performance (7-day Average)

Collecting…
Collecting…
Collecting…

Availability Trend (24h)

Pricing

Input$2.20/MTokens
Cached Input$0.22/MTokens
Cache Creation$2.20/MTokens
text.input.cache creation 1h$4.40/MTokens
Output$11.00/MTokens

Performance Metrics (24h)

Similar Models

$4.40/$22.00/M
ctx1.0Mmax1.0Mavail—tps—
InOutCap

Kimi K3.1 Pro served at 2-3x output speed for latency-sensitive workloads.

$2.09/$8.80/M
ctx262Kmax262Kavail—tps—
InOutCap

Kimi K2.7 Code served at ~180 tokens/s for latency-sensitive coding agents.

$1.045/$4.40/M
ctx262Kmax262Kavail—tps—
InOutCap

Moonshot AI's multimodal Kimi K2.6 model for long-horizon coding and agentic work.

$1.045/$4.40/M
ctx262Kmax262Kavail—tps—
InOutCap

Moonshot AI's multimodal reasoning model optimized for coding and agentic software engineering.