Kimi K2.7 Code

Kimi K2.7 Code is Moonshot AI's coding-focused agentic model built on Kimi K2.6. It improves real-world long-horizon coding task completion, instruction following, and token efficiency while reducing thinking-token usage by approximately 30% versus Kimi K2.6.

MCP-Mark

81.1%

i
MCP Atlas

76.0%

i
Kimi Code Bench v2

62.0%

i
Program Bench

53.6%

i
Kimi Claw 24/7 Bench

46.9%

i
MLS-Bench Lite

35.1%

i

Pricing, uptime, and speed via OpenRouter — updated Jul 17, 2026, 04:19 AM.

Provider	Status	Input	Output	Limits	Uptime	Speed	Notes
Inceptron	available	$0.72/Mtok cache $0.15/Mtok	$3.50/Mtok	262K tokens context 262K tokens max output	100.0% 5m 100.0%	1,588 ms p50 TTFT 30 tok/s p50	int4
DeepInfra	available	$0.74/Mtok cache $0.15/Mtok	$3.50/Mtok	262K tokens context 16K tokens max output	100.0% 5m 100.0%	641 ms p50 TTFT 84 tok/s p50	fp4
Ambient	available	$0.75/Mtok cache $0.16/Mtok	$3.50/Mtok	262K tokens context 262K tokens max output	100.0% 5m 100.0%	1,198 ms p50 TTFT 44 tok/s p50	int4
Venice	available	$0.75/Mtok cache $0.16/Mtok	$3.50/Mtok	256K tokens context 66K tokens max output	—	1,983 ms p50 TTFT 73 tok/s p50	int4
Parasail	available	$0.76/Mtok cache $0.16/Mtok	$3.50/Mtok	262K tokens context 262K tokens max output	—	942 ms p50 TTFT 58 tok/s p50	int4
ModelRun	available	$0.85/Mtok cache $0.16/Mtok	$3.75/Mtok	262K tokens context 262K tokens max output	100.0% 5m 100.0%	213 ms p50 TTFT 188 tok/s p50	fp4
SiliconFlow	available	$0.86/Mtok cache $0.18/Mtok	$3.80/Mtok	262K tokens context 262K tokens max output	100.0% 5m 100.0%	1,182 ms p50 TTFT 39 tok/s p50	fp8
Novita	available	$0.91/Mtok cache $0.18/Mtok	$3.84/Mtok	262K tokens context 262K tokens max output	100.0%	2,313 ms p50 TTFT 36 tok/s p50	int4
WandB	available	$0.94/Mtok cache $0.19/Mtok	$4.00/Mtok	262K tokens context 262K tokens max output	—	576 ms p50 TTFT 225 tok/s p50	int4
AtlasCloud	available	$0.95/Mtok cache $0.16/Mtok	$4.00/Mtok	262K tokens context 262K tokens max output	—	910 ms p50 TTFT 34 tok/s p50	int4
Cloudflare	available	$0.95/Mtok cache $0.19/Mtok	$4.00/Mtok	262K tokens context 262K tokens max output	—	537 ms p50 TTFT 86 tok/s p50
Together	available	$0.95/Mtok cache $0.19/Mtok	$4.00/Mtok	262K tokens context 262K tokens max output	—	577 ms p50 TTFT 208 tok/s p50
Moonshot AI	available	$1.90/Mtok cache $0.38/Mtok	$8.00/Mtok	262K tokens context 262K tokens max output	—	2,245 ms p50 TTFT 113 tok/s p50	int4
Fireworks	-2	$0.95/Mtok cache $0.19/Mtok	$4.00/Mtok	262K tokens context 262K tokens max output	94%	1,175 ms p50 TTFT 87 tok/s p50