MoonshotAI: Kimi K2.6
moonshotai/kimi-k2-6Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration.
Modalities
In / out per 1M$0.65 / $3.41
Context256K
ReleasedApr 20, 2026
Providers
17 providers serve this model upstream.
| Provider | Input /M | Output /M | Cache read /M | Latency P50 | Throughput P50 | Uptime |
|---|---|---|---|---|---|---|
| $0.43 | $1.82 | $0.07 | 1.05s | 50 tps | 100% | |
| $0.75 | $3.50 | $0.16 | 1.06s | 68 tps | 100% | |
| $0.95 | $4.00 | $0.16 | 3.33s | 27 tps | 99.97% | |
| $0.43 | $2.45 | $0.13 | 0.43s | 68 tps | 99.95% | |
 SiliconFlowfp8 | $0.77 | $3.40 | $0.14 | 1.24s | 25 tps | 99.9% |
| $0.45 | $1.95 | $0.04 | 1.90s | 46 tps | 99.8% | |
 DigitalOcean | $0.57 | $2.40 | $0.11 | 1.48s | 30 tps | 99.78% |
| $0.70 | $3.50 | $0.35 | 0.39s | 61 tps | 99.52% | |
| $0.80 | $3.40 | $0.16 | 2.77s | 29 tps | 99.25% | |
| $1.09 | $4.60 | $0.37 | 2.54s | 22 tps | 99.09% | |
| $0.95 | $4.00 | $0.16 | 2.57s | 35 tps | 99.08% | |
 CoreWeavefp4 | $0.65 | $3.41 | $0.15 | 0.63s | 123 tps | 98.9% |
| $0.95 | $4.00 | $0.16 | 1.19s | 37 tps | 98.53% | |
| $0.60 | $2.52 | $0.10 | 1.50s | 35 tps | 95.71% | |
 DeepInfraus · fp4 | $0.75 | $3.50 | $0.15 | 2.19s | 11 tps | 93.56% |
| $0.75 | $3.50 | $0.16 | 1.78s | 39 tps | 77.82% | |
| $0.85 | $3.60 | $0.14 | — | — | — |
Market-wide measurements, refreshed every 15 minutes. They describe who serves Kimi K2.6 in general, not how ProjectCOZY routes your requests.
Pricing
List rates per 1M tokens — what Kimi K2.6 costs pay-as-you-go elsewhere, not what you pay here.
Input
$0.65
per 1M tokens
Output
$3.41
per 1M tokens
Cache read
$0.15
per 1M cached tokens
Included in every pass
Kimi K2.6 is included in every ProjectCOZY pass at no extra cost — one flat rate, no per-token metering. The rates above are there for comparison.
Performance
Time to first token and output speed across every provider, over the last 3 days.
0.0s20.0s40.0s60.0s80.0s
Oct 11, 12 AMOct 11, 8 AMOct 11, 4 PMOct 12, 12 AMOct 12, 8 AMOct 12, 4 PMOct 13, 12 AMOct 13, 8 AMOct 13, 4 PMOct 14, 12 AMOct 14, 8 AM
Baidu Qianfan CoreWeave SiliconFlow StreamLake Venice DigitalOcean Inceptron (eu) Cloudflare DeepInfra (us) Moonshot AI AtlasCloud Parasail Phala Crusoe NovitaAI Chutes
0 tok/s250 tok/s500 tok/s750 tok/s1000 tok/s
Oct 11, 12 AMOct 11, 8 AMOct 11, 4 PMOct 12, 12 AMOct 12, 8 AMOct 12, 4 PMOct 13, 12 AMOct 13, 8 AMOct 13, 4 PMOct 14, 12 AMOct 14, 8 AM
Baidu Qianfan CoreWeave SiliconFlow StreamLake Venice DigitalOcean Inceptron (eu) DeepInfra (us) Moonshot AI AtlasCloud Parasail Phala Crusoe NovitaAI Chutes Cloudflare
Uptime
100% of requests were served successfully over the last 3 days, across all providers.
Last 3 daysAvailability 99.77%
Oct 11, 2:00 PMNow
Availability over the last 24 hoursAvailability 99.73%
100% 98% 97% 95%
Oct 13, 2:40 PMNow
Apps
Tools that most often run Kimi K2.6, by tokens this week.
Activity
718.2B tokens processed market-wide in the last month.
010.0B20.0B30.0B40.0B
Sep 14Sep 19Sep 24Sep 29Oct 4Oct 9Oct 14
Tokens
FAQ
Which model id do I use for Kimi K2.6?
moonshotai/kimi-k2.6. Send it as the model field from any OpenAI-compatible client, against http://192.168.1.55/v1.
How much context does Kimi K2.6 hold?
262,144 tokens per request, of which up to 235,929 can be the response.
What can it accept and return?
Input: text, image. Output: text.
What does Kimi K2.6 cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $0.65 per 1M input tokens and $3.41 per 1M output tokens.
Who built Kimi K2.6?
MoonshotAI, in the Kimi family.
Explore
Other models your pass can call.
