Kimi K3
Moonshot AIkimi-k3
Released Jul 16, 2026
Providers
11
Context
1.0M
Input
$2.00/M
Output
$14.00/M
BAA-eligible on 2 of 11 providersPHI requires a signed BAA from Concentrate and HIPAA-enabled organization.
Aliases:k3kimi-k-3
Moonshot AI's K3 flagship model for long-horizon coding and end-to-end knowledge work, with a 1M-token context window.
novita/kimi-k3QuantUnspecified
- Input
- $3.00/M
- Output
- $15.00/M
- Context
- 1.0M
- Max out
- 131K
- Cache read
- $0.30/M
- Cache write
- $3.00/M
- Thinking out
- $15.00/M
FlexPriority / Fast
relace/kimi-k3Quantfp4
- Input
- $2.00/M
- Output
- $14.00/M
- Context
- 1.0M
- Max out
- 131K
- Cache read
- $0.30/M
- Cache write
- $2.00/M
- Thinking out
- $14.00/M
FlexPriority / Fast
runanywhere/kimi-k3Quantmxfp4
- Input
- $2.85/M
- Output
- $14.25/M
- Context
- 1.0M
- Max out
- 66K
- Cache read
- $0.28/M
- Cache write
- $2.85/M
- Thinking out
- $14.25/M
FlexPriority / Fast
modal/kimi-k3QuantUnspecified
- Input
- $3.00/M
- Output
- $15.00/M
- Context
- 1.0M
- Max out
- 131K
- Cache read
- $0.30/M
- Cache write
- $3.00/M
- Thinking out
- $15.00/M
FlexPriority / Fast
baseten/kimi-k3QuantUnspecified
- Input
- $3.00/M
- Output
- $15.00/M
- Context
- 1.0M
- Max out
- 262K
- Cache read
- $0.30/M
- Cache write
- $3.00/M
- Thinking out
- $15.00/M
FlexPriority / Fast
alibaba/kimi-k3QuantUnspecified
- Input
- $2.83/M
- Output
- $14.13/M
- Context
- 1.0M
- Max out
- 131K
- Cache read
- $0.28/M
- Cache write
- $2.83/M
- Thinking out
- $14.13/M
FlexPriority / Fast
deepinfra/kimi-k3QuantUnspecified
- Input
- $2.85/M
- Output
- $14.25/M
- Context
- 1.0M
- Max out
- 33K
- Cache read
- $0.28/M
- Cache write
- $2.85/M
- Thinking out
- $14.25/M
FlexPriority / Fast
fireworks/kimi-k3QuantUnspecified
- Input
- $3.00/M
- Output
- $15.00/M
- Context
- 1.0M
- Max out
- 131K
- Cache read
- $0.30/M
- Cache write
- $3.00/M
- Thinking out
- $15.00/M
Flex
moonshot/kimi-k3QuantUnspecified
- Input
- $3.00/M
- Output
- $15.00/M
- Context
- 1.0M
- Max out
- 131K
- Cache read
- $0.30/M
- Cache write cache_write_tokens
- $3.00/M
- Thinking out
- $15.00/M
FlexPriority / Fast
nebius/kimi-k3Quantfp4
- Input
- $3.00/M
- Output
- $15.00/M
- Context
- 1.0M
- Max out
- 131K
- Caching
- Not offered
- Thinking out
- $15.00/M
FlexPriority / Fast
wafer/kimi-k3QuantUnspecified
- Input
- $2.00/M
- Output
- $15.00/M
- Context
- 1.0M
- Max out
- 131K
- Cache read
- $0.25/M
- Cache write
- $2.00/M
- Thinking out
- $15.00/M
FlexPriority / Fast