Kimi K2.7 Code
Moonshot AI · released Jun 11, 2026 · moonshotai/Kimi-K2.7-Code
- Type
- Open weightsCustom licence
- Params
- 1.1T
- Context
- 262K
32B active per word · about 197K words of context · download allowed, licence restricts use
Our take
Written Aug 4, 2026Moonshot's very large coding model can be downloaded. At over a trillion parameters it is an unusually large model to be downloadable at all, aimed at agentic coding workloads where scale matters.
Choose this for agentic coding workloads where frontier-scale capability matters and provider portability is useful. Skip it if your licence cannot tolerate custom restricted terms, or if you need to self-host on standard hardware.
The case for it
- Over one trillion total parameters — among the largest models you can actually download.
- More than a dozen hosts serve it at near-identical prices, which keeps the market competitive.
The case against it
- Custom restricted licence; legal review is needed before commercial fine-tuning or redistribution.
- Over a trillion parameters. Even compressed, it is far beyond any single consumer GPU or Mac.
How good is it?
An open-weights coding model built for writing code and calling tools to carry out requests.
- calling tools to carry out requestsArena Agent · Tool use · 2nd of 55
- changing course when you give new instructionsArena Agent · Steerability · 10th of 55
EverydayGeneral questions and everyday reasoning
Not yet scored on Arena Text (overall). It is on LiveBench Reasoning, in 35th of 58 with 82.81.
CodingWriting and fixing code on its own
Not yet scored on Arena Coding. It is on Arena Code (WebDev), in 45th of 95 with 1473.
AgenticPlanning, calling tools, staying on task
Arena Agent25th of 55 · 0.008
WritingDrafting and rewriting prose
Not yet scored on Arena Creative Writing. It is on LiveBench Language, in 34th of 58 with 77.91.
Placings on Arena's agent boards, from live sessions people ran themselves. A model can lead on one of these and sit mid-field on the others.
Boards this model appears on that none of the ratings above are built on.
Every published score for this model14 scoresEvery figure we hold, from 14 boards, with who ran it and a link to the source — including the boards no rating above is built on.
Can you run it yourself?
GeForce RTX 4090 · 24 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Apple M1 Pro (16-core GPU) · 32 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Radeon RX 7900 XT · 20 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Memory use by level
Against a 24 GB card.
What is quantisation? →This model on every device we track71 devicesThe Q4 build most people download, on each device: what the weights come to, how much context the memory leaves, and whether it runs. Smallest device that runs it first.
Check against your own machine → · Where to rent it hosted →
Or rent it from someone else
Prices checked between 4 hours and 9 days ago — each listing carries its own date.
Some hosts sell this model at two prices: on their own price list (“direct”) and on their OpenRouter listing (“through OpenRouter”). Where the two differ, the row shows both, each with the date we last read it.
Cheapest of the 2 listings we can compare like for like — at 262K of context, out of 14 in the table below. One cheaper row there is outside that comparison: a different context length.
- per 1M tokens
- $0.67 in / $3.35 out
- Context served
- 262K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| StreamLakeThrough OpenRouter | $0.71 / $3.00checked 4 hours ago | 256K32K max reply | 77 tok/s | No | Yesunknown period | Unknown |
| OpenRouterOpenRouter's own listing | $0.67 / $3.35checked 4 hours ago | 262K | not measured | Unknown | Unknown | Unknown |
| Inceptronint4Through OpenRouter | $0.67 / $3.35checked 4 hours ago | 262K236K max reply | 56 tok/s | No | No | Confirmed |
| DeepInfrafp4Direct | $0.68 / $3.40checked 9 days ago | 262K | not measured | Unknown | Unknown | Unknown |
| CoreWeaveint4Through OpenRouter | $0.71 / $3.50checked 4 hours ago | 262K236K max reply | 111 tok/s | No | No | Confirmed |
| Venice AIint4Through OpenRouter | $0.75 / $3.50checked 4 hours ago | 256K66K max reply | 7 tok/s | No | No | Confirmed |
| SiliconFlowfp8Through OpenRouter | $0.86 / $3.80checked 4 hours ago | 262K236K max reply | 29 tok/s | No | No | Confirmed |
| Novita AIint4Direct and through OpenRouter | $0.95 / $4.00directchecked 4 hours ago$0.91 / $3.84through OpenRouterchecked 4 hours ago | 262K236K max reply through OpenRouter | 77 tok/sthrough OpenRouter | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterConfirmed |
| Moonshot AIint4Through OpenRouter | $0.95 / $4.00checked 4 hours ago | 262K236K max reply | 82 tok/s | No | No | Confirmed |
| Alibaba Cloudfp8Through OpenRouter | $0.95 / $4.00checked 4 hours ago | 262K16K max reply | 39 tok/s | No | Yesunknown period | Unknown |
| GMICloudfp8Through OpenRouter | $0.95 / $4.00checked 4 hours ago | 262K236K max reply | 70 tok/s | No | Yesunknown period | Unknown |
| Cloudflare Workers AIThrough OpenRouter | $0.95 / $4.00checked 4 hours ago | 262K236K max reply | 47 tok/s | No | Yesunknown period | Unknown |
| Nebius AI Studiofp4Through OpenRouter | $0.95 / $4.00checked 4 hours ago | 262K236K max reply | 17 tok/s | No | No | Confirmed |
| Moonshot AIhighspeed tierint4Through OpenRouter | $1.90 / $8.00checked 4 hours ago | 262K236K max reply | 144 tok/s | No | No | Unknown |
DeepInfra
Novita AI
Cloudflare Workers AI
Nebius AI StudioAcross the 14 listings we hold: 12 say they do not train on prompts (1 of them only through OpenRouter), 0 say they do and 2 do not say. 7 appear in the zero-retention registry we check (1 of them only through OpenRouter); the rest are unknown to us.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| StreamLakeThrough OpenRouter | ✓ | ✓ | ✓ |
| OpenRouterOpenRouter's own listing | ✓ | ✓ | ✓ |
| Inceptronint4Through OpenRouter | ✓ | ✓ | ✓ |
| DeepInfrafp4Direct | |||
| CoreWeaveint4Through OpenRouter | ✓ | ✓ | ✓ |
| Venice AIint4Through OpenRouter | ✓ | ✓ | ✓ |
| SiliconFlowfp8Through OpenRouter | ✓ | ✗ | ✗ |
| Novita AIint4Direct and through OpenRouter | ✓ | ✓ | ✓ |
| Moonshot AIint4Through OpenRouter | ✓ | ✓ | ✓ |
| Alibaba Cloudfp8Through OpenRouter | ✓ | ✓ | ✓ |
| GMICloudfp8Through OpenRouter | ✓ | ✓ | ✓ |
| Cloudflare Workers AIThrough OpenRouter | ✓ | ✓ | ✓ |
| Nebius AI Studiofp4Through OpenRouter | ✓ | ✓ | ✓ |
| Moonshot AIhighspeed · int4Through OpenRouter | ✓ | ✓ | ✓ |
Tool calling: 13 of 14 listings say yes, 1 publishes no parameter list. JSON output: 12 of 14 listings say yes, 1 says no, 1 publishes no parameter list. Strict schema: 12 of 14 listings say yes, 1 says no, 1 publishes no parameter list.
Models people weigh against Kimi K2.7 Code
When we formed this view
Recent changes
What moved
input +2% ($0.66 → $0.67 per 1M tokens), output +2% ($3.30 → $3.35 per 1M tokens)What moved
input −7% ($0.71 → $0.66 per 1M tokens)What moved
output +3% ($3.21 → $3.30 per 1M tokens)What moved
input +7% ($0.660 → $0.706 per 1M tokens), output −6% ($3.40 → $3.21 per 1M tokens)Each date is the day we first saw the change, or the day the maker announced it.
What we do not know about this model yet
- We hold no measured file for it, so all 3 sizes on this page are calculated from the parameter count.
- 1 of 14 listings publishes no parameter list, so what its API accepts is unknown to us.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 2 of 14 listings do not say whether they train on prompts, and 1 answers only through OpenRouter, not for its own listing.
- We hold no batch or off-peak rate for any of its listings.
- We hold a decode speed for it, but no prompt-processing (prefill) figure, so how long the input side of a job takes is unknown to us.
Licence and identifiers
What the licence allowsCustom licence, what it allows commercially, and the identifiers you need to pull this model — its Hugging Face repo, our slug and a machine-readable card.
Licence
Custom licence
This model ships custom license terms that don't map to a known template. We haven't parsed them, so commercial use, redistribution and derivatives are unverified — review the original terms before shipping.
Identifiers
- Hugging Face
- moonshotai/Kimi-K2.7-Code
- Architecture
- Mixture of experts
- Takes in, gives back
- Text and images in, text out
- Catalogue slug
- moonshotai-kimi-k2-7-code