Baseten
99.68%Context256K
Max output32.8K
p50 latency727 ms
Throughput265.0 t/s
Input price$0.95
Output price$4
Zero retentionNo trainingCaching
moonshotai/kimi-k2.7-code
Kimi-K2.7-Code is a coding model from Moonshot AI. It has improved coding & agent performance over K2.6, more reasoning efficiency with less overthinking, and improved instruction following for long-horizon coding.
USD per one million tokens, using current provider data.
Last-hour p50 in milliseconds; lower is better.
Reported availability over the last 24 hours; not a contractual SLA.
Compare current pricing, performance, and privacy across every available provider.
| Provider | Maximum context | Max output | p50 latency | p50 throughput | 24h uptime | Input / 1M tokens | Output / 1M tokens | Privacy |
|---|---|---|---|---|---|---|---|---|
Baseten | 256K | 32.8K | 727 ms | 265.0 t/s | 99.679% | $0.95 | $4 | |
Deepinfra | 262.1K | 32.8K | 86,310 ms | 6.0 t/s | 97.971% | $0.74 | $3.5 | |
Fireworks | 262K | 32.8K | 867 ms | 96.0 t/s | 100.000% | $0.95 | $4 | |
Moonshotai | 256K | 32.8K | 988 ms | 37.0 t/s | 100.000% | $0.95 | $4 |
Available modalities and capabilities across inference providers.
moonshotai/kimi-k2.7-codeMore options from the same creator or model category.