MoonshotAI: Kimi K2.6

moonshotai/kimi-k2.6

Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and...

Prompt $/1M

$0.684

Completion $/1M

$3.420

Context

262,144 tok

Best provider

136 tok/s · BaseTen

Specs

Model id: moonshotai/kimi-k2.6
Display name: MoonshotAI: Kimi K2.6
Modality: text+image->text
Tokenizer: Other
Instruct type: —
Context length: 262,144
Max completion: 262,144
Prompt $/1M: $0.684
Completion $/1M: $3.420
Free tier: no

Capabilities

Function callingno
JSON modeno
System promptno
Visionyes
Moderatedno

Benchmark scores

Each axis is one benchmark, normalized to the best model in the field.

No benchmark data for this model.

Speed by provider

Provider	tok/s	TTFT	Total latency
BaseTenfastest	136	944 ms	1,108 ms
ModelRun	117	120 ms	204 ms
WandB	114	565 ms	636 ms
Nebius	97	915 ms	1,057 ms
AkashML	89	848 ms	1,276 ms
Together	74	537 ms	734 ms
Fireworks	64	576 ms	912 ms
Cloudflare	57	876 ms	1,103 ms
Artificial Analysis	52	1,065 ms	—
Phala	49	1,260 ms	1,433 ms
Io Net	45	1,477 ms	1,918 ms
Ambient	42	871 ms	1,325 ms
Decart	41	9,802 ms	11,355 ms
Venice	37	1,052 ms	1,184 ms
DeepInfra	36	609 ms	711 ms
AtlasCloud	36	1,638 ms	1,811 ms
StreamLake	33	1,781 ms	2,210 ms
Chutes	32	2,311 ms	2,957 ms
Novita	31	1,325 ms	1,556 ms
Parasail	31	591 ms	891 ms
DigitalOcean	30	1,072 ms	1,489 ms
Baidu	29	1,606 ms	2,180 ms
Moonshot AI	25	2,714 ms	3,646 ms
SiliconFlow	24	1,861 ms	2,083 ms
Inceptron	19	1,684 ms	2,661 ms