Kimi K2.6

Kimi K2.6 demonstrates particularly strong performance in long-horizon coding tasks and produces professional-grade design with code and vision.

Input / 1M tokens$0.95

Output / 1M tokens$4

Maximum context262.1K

Inference providers4

Price comparison

USD per one million tokens, using current provider data.

Provider latency

Last-hour p50 in milliseconds; lower is better.

Provider uptime

Reported availability over the last 24 hours; not a contractual SLA.

Inference providers

Compare current pricing, performance, and privacy across every available provider.

Baseten

99.24%

Context262K

Max output262K

p50 latency277 ms

Throughput88.0 t/s

Input price$0.95

Output price$4

Zero retentionNo trainingCaching

Fireworks

99.97%

Context262K

Max output262K

p50 latency601 ms

Throughput79.5 t/s

Input price$0.95

Output price$4

Zero retentionNo trainingCaching

Moonshotai

99.98%

Context262K

Max output262K

p50 latency3,244 ms

Throughput35.0 t/s

Input price$0.95

Output price$4

Zero retentionNo trainingCaching

Novita

100.00%

Context262.1K

Max output262.1K

p50 latency1,292 ms

Throughput145.5 t/s

Input price$0.95

Output price$4

No trainingCaching

Provider	Maximum context	Max output	p50 latency	p50 throughput	24h uptime	Input / 1M tokens	Output / 1M tokens
Baseten	262K	262K	277 ms	88.0 t/s	99.244%	$0.95	$4
Fireworks	262K	262K	601 ms	79.5 t/s	99.966%	$0.95	$4
Moonshotai	262K	262K	3,244 ms	35.0 t/s	99.979%	$0.95	$4
Novita	262.1K	262.1K	1,292 ms	145.5 t/s	100.000%	$0.95	$4