Get Pass

MoonshotAI: Kimi K2.7 Code

moonshotai/kimi-k2-7-code
CompareAPITry this model

MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts.

Modalities
In / out per 1M$0.67 / $3.35
Context256K
ReleasedJun 12, 2026

Providers

13 providers serve this model upstream.

Providers serving this model
ProviderInput /MOutput /MCache read /MLatency P50Throughput P50Uptime
Inceptroneu · int4$0.67$3.35$0.181.00s60 tps100%
CoreWeaveint4$0.71$3.50$0.150.55s172 tps100%
StreamLake$0.71$3.00$0.141.82s36 tps100%
Veniceint4$0.75$3.50$0.162.38s36 tps100%
SiliconFlowfp8$0.86$3.80$0.181.90s36 tps100%
NovitaAIint4$0.91$3.84$0.183.21s31 tps100%
Phala$0.95$4.00$0.192.90s44 tps100%
GMICloudfp8$0.95$4.00$0.195.48s36 tps100%
Cloudflare$0.95$4.00$0.192.66s35 tps100%
Moonshot AIint4$0.95$4.00$0.191.90s34 tps100%
Moonshot AI Highspeedint4$1.90$8.00$0.382.08s112 tps100%
Alibaba Cloud Int.fp8$0.95$4.00$0.191.40s49 tps99.68%
Nebius Token Factoryfp4$0.95$4.00Variable1.24s93 tps98.13%

Market-wide measurements, refreshed every 15 minutes. They describe who serves Kimi K2.7 Code in general, not how ProjectCOZY routes your requests.

Pricing

List rates per 1M tokens — what Kimi K2.7 Code costs pay-as-you-go elsewhere, not what you pay here.

Input
$0.67
per 1M tokens
Output
$3.35
per 1M tokens
Cache read
$0.18
per 1M cached tokens
Included in every pass
Kimi K2.7 Code 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.

0.0s10.0s20.0s30.0s40.0s
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
CoreWeave StreamLake Alibaba Cloud Int. Inceptron (eu) Nebius Token Factory Moonshot AI NovitaAI Cloudflare SiliconFlow Moonshot AI Highspeed Venice GMICloud Phala
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
CoreWeave StreamLake Alibaba Cloud Int. Inceptron (eu) Nebius Token Factory Moonshot AI Cloudflare SiliconFlow NovitaAI Moonshot AI Highspeed Venice GMICloud Phala

Uptime

100% of requests were served successfully over the last 3 days, across all providers.

Last 3 daysAvailability 98.79%
Oct 11, 2:00 PMNow
Availability over the last 24 hoursAvailability 99.38%
100% 97% 93% 90%
Oct 13, 2:40 PMNow

Apps

Tools that most often run Kimi K2.7 Code, by tokens this week.

Claude CodeCli Agent · 37.2% of tokens20.4BJanitor AIRoleplay · 21.6% of tokens11.8BHermes AgentPersonal Agent · 20.7% of tokens11.3BOpenClawPersonal Agent · 11.6% of tokens6.4BpiCli Agent · 8.8% of tokens4.8B

Activity

246.4B tokens processed market-wide in the last month.

05.0B10.0B15.0B20.0B
Sep 14Sep 19Sep 24Sep 29Oct 4Oct 9Oct 14
Tokens

FAQ

Which model id do I use for Kimi K2.7 Code?
moonshotai/kimi-k2.7-code. Send it as the model field from any OpenAI-compatible client, against http://192.168.1.55/v1.
How much context does Kimi K2.7 Code 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 K2.7 Code cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $0.67 per 1M input tokens and $3.35 per 1M output tokens.
Who built Kimi K2.7 Code?
MoonshotAI, in the Kimi family.

Explore

Other models your pass can call.

Aion 3.5aion-labs/aion-3.5256KAionAion 3.5 Miniaion-labs/aion-3.5-mini256KAionAion-2.0aion-labs/aion-2.0128KAionAion-3.0aion-labs/aion-3.0128KAionAion-3.0-Miniaion-labs/aion-3.0-mini128KAionAion-RP 1.0 (8B)aion-labs/aion-rp-llama-3.1-8b32KAion