Kimi K2 0711
Moonshot AI · released Jul 11, 2025 · moonshotai/Kimi-K2-Instruct
- Type
- Open weightsCustom licence
- Params
- 1T
- Context
- 131K
32B active per word · about 98K words of context · download allowed, licence restricts use
Our take
Written Sep 1, 2026Kimi K2 0711 is a trillion-parameter mixture-of-experts model from Moonshot AI with 32 billion active per token. It resolves 65.4% of real GitHub issues on the SWE-bench Verified benchmark, making it a measured pick for software-engineering tasks.
Choose this when you need measured code-issue resolution, or long-context text work up to 131,072 tokens. Use it if you can accept a custom licence rather than Apache or MIT terms. Skip it if you need chat-quality scores, general reasoning benchmarks, or a permissive open licence.
The case for it
- Extreme scaling: 1,026.5 billion total parameters with only 32 billion active per token, a 32:1 ratio.
- Resolves 65.4% of SWE-bench Verified GitHub issues end-to-end, measured on real tasks.
- 131,072-token context length for code and document workloads.
The case against it
- Only one benchmark measured in our data; no chat, reasoning, or general capability scores held.
- Custom restricted licence, not Apache 2.0 or MIT.
- Output rate carries a steep premium over input, and throughput is unverified on two of three offers.
How good is it?
EverydayGeneral questions and everyday reasoning
Not yet scored on Arena Text (overall).
CodingWriting and fixing code on its own
Not yet scored on Arena Coding.
AgenticPlanning, calling tools, staying on task
Not yet scored on Arena Agent. It is on SWE-bench Verified, in 17th of 42 with 65.4.
WritingDrafting and rewriting prose
Not yet scored on Arena Creative Writing.
Every published score for this model1 scoreEvery figure we hold, from 1 board, 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 4 hours ago — each listing carries its own date.
- per 1M tokens
- $0.57 in / $2.30 out
- Context served
- 131K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $0.57 / $2.30checked 4 hours ago | 131K | not measured | Unknown | Unknown | Unknown |
| Novita AIfp8Direct and through OpenRouter | $0.57 / $2.30checked 4 hours ago | 131K98K max reply through OpenRouter | 39 tok/sthrough OpenRouter | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterConfirmed |
Novita AIAcross the 2 listings we hold: 1 says it does not train on prompts (only through OpenRouter), 0 say they do and 1 does not say. 1 appears in the zero-retention registry we check (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 |
|---|---|---|---|
| OpenRouterOpenRouter's own listing | ✓ | ✗ | ✗ |
| Novita AIfp8Direct and through OpenRouter | ✓ | ✗ | ✗ |
Tool calling: 2 of 2 listings say yes. JSON output: 0 of 2 listings say yes, 2 say no. Strict schema: 0 of 2 listings say yes, 2 say no.
Models people weigh against Kimi K2 0711
When we formed this view
Recent changes
What moved
first indexed by our pipelineEach 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.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 2 listings does not say whether it trains on prompts, and 1 answers only through OpenRouter, not for its own listing.
- We hold no cached-input rate for any of its listings.
- 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-Instruct
- Architecture
- Mixture of experts
- Takes in, gives back
- Text in, text out
- Catalogue slug
- moonshotai-kimi-k2-0711