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 Aug 2, 2026Kimi K2 0711 is a trillion-parameter mixture-of-experts coding model from Moonshot AI with a custom licence and 131,072-token request limit. Its weights can be downloaded, though the licence carries redistribution restrictions, and its measured coding performance dropped sharply between two summer 2025 evaluations.
Choose this for coding tasks where the July 2025 evaluation's 65.4% SWE-bench Verified score is relevant — but verify which score reflects current behaviour, as the August re-evaluation fell to 43.8%. Use it when you need 131K tokens in a single request and can accept a custom licence with redistribution restrictions. Skip it if you need image or video input, a permissive Apache or MIT licence, or confidence that the headline score is stable.
The case for it
- Over one trillion total parameters with only 32 billion active per token — roughly 32× parameter scaling without proportional compute cost.
- Strong coding performance in the earlier evaluation: 65.4% on SWE-bench Verified (July 2025).
- Input pricing below one dollar per million tokens for a trillion-scale model.
The case against it
- SWE-bench Verified fell from 65.4% to 43.8% between July and August 2025 — a 21.6 percentage point drop that raises questions about score stability.
- Custom licence, not Apache 2.0 or MIT; redistribution and commercial use are likely constrained, and the model is text-only with no image or video input.
- Only three tracked offers from two providers, and throughput is measured at 35 tokens per second on just one endpoint.
How good is it?
IntelligencePuzzles, maths, exam questions
Nobody we watch has scored Kimi K2 0711 for this. We would take the rating from Arena Text (overall).
CodingWriting and fixing code on its own
Nobody we watch has scored Kimi K2 0711 for this. We would take the rating from Arena Coding.
AgenticPlanning, calling tools, staying on task
Kimi K2 0711 is not on Arena Agent (IPS), which is where the rating would come from, so there is no rating here. It is on SWE-bench Verified, in 17th of 39 with 65.4.
WritingWe do not rate this
Nobody we watch has scored this model for writing. Two boards come close and neither tests writing: Arena Creative Writing asks people which of two replies they prefer, and LiveBench Language tests whether a model understood a passage.
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?
- Fits in memory
- weights load entirely on the card
- Spills to system RAM
- some weights offload; much slower
- Too large
- will not load even with offload
- est
- size is calculated; the verdict could change by 10%
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.
All 3 sizes here are calculated, not measured. We hold no measured file for this model, so each size comes from the parameter count and every verdict above inherits that uncertainty.
Check against your own machine → · All 71 devices, with every size →
Or rent it from someone else
Cheapest of 3 live listings. Picked at the widest standard context we hold, within one quantisation slice, so the numbers beside it are a price one host actually charges.
- 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 |
|---|---|---|---|---|---|---|
| OpenRouter | $0.57 / $2.30 | 131K | not measured | Unknown | Unknown | Unknown |
| Novita AI | $0.57 / $2.30 | 131K | not measured | Unknown | Unknown | Unknown |
| Novita AIfp8 | $0.57 / $2.30 | 131K | 7 tok/s | No | No | Confirmed |
Novita AIAcross the 3 listings we hold: 1 say they do not train on prompts, 0 say they do and 2 do not say. 1 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
- ✓
- Supported
- ✗
- Not supported
- Not published
- host gave no parameter list
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouter | ✓ | ✗ | ✗ |
| Novita AI | |||
| Novita AIfp8 | ✓ | ✗ | ✗ |
Tool calling: 2 of 3 listings say yes, 1 publishes no parameter list. JSON output: 0 of 3 listings say yes, 2 say no, 1 publishes no parameter list. Strict schema: 0 of 3 listings say yes, 2 say no, 1 publishes no parameter list.
Models people weigh against Kimi K2 0711
When we formed this view
Dates behind this page
Prices last checked 14h ago
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 3 listings publish no parameter list, so what their API accepts is unknown to us.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 2 of 3 listings do not say whether they train on prompts.
- We hold no cached-input rate for any of its listings.
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
- Modality record
- text->text
- Catalogue slug
- moonshotai-kimi-k2-0711