Kimi K2 Thinking
Moonshot AI · released Nov 4, 2025 · moonshotai/Kimi-K2-Thinking
- 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 Jul 31, 2026Moonshot AI's Kimi K2.5 is a large mixture-of-experts reasoning model with 32 billion active parameters drawn from over one trillion total. It excels at coding and mathematics, with measured leaderboard scores placing it well ahead of its own general chat and creative writing performance.
Choose this for coding or mathematical reasoning tasks where its measured scores lead its own benchmark suite. Use it for long-context text work at up to 262,144 tokens, or when you need mixture-of-experts efficiency. Skip it if you need multimodal input, a standard permissive licence, or strong creative writing.
The case for it
- Strongest measured skill is coding — 51.7 points above its overall text score on the same leaderboard.
- Mathematical reasoning outperforms general chat and creative writing by 21.9 and 47.8 points respectively.
- Over one trillion total parameters with only 32 billion active per token, a 33.1× compression ratio.
- Identical pricing across all four tracked offers, so provider choice comes down to throughput rather than cost.
The case against it
- Creative writing is the weakest of its six measured skills, 77.6 points below its coding score.
- Custom licence with restrictions — not a standard open licence; terms are undisclosed in our data.
- Throughput varies sharply by provider: one identical-priced offer is roughly twice as slow as another.
How good is it?
IntelligencePuzzles, maths, exam questions
Arena Text (overall)35th of 143 · 1450.2via Thinking
CodingWriting and fixing code on its own
Arena Coding34th of 143 · 1501.1via Thinking
AgenticPlanning, calling tools, staying on task
Kimi K2 Thinking 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 19th of 39 with 63.4.
WritingWe do not rate this
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. So we show where Kimi K2 Thinking placed and give it no mark out of five.
These tests check whether a model follows instructions — a precondition for all the work above, but not a measure of how well that work is done, which is why they get no rating.
Every published score for this model8 scoresEvery figure we hold, from 8 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?
- 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 4 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
- $0.60 in / $2.50 out
- Context served
- 262K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $0.60 / $2.50 | 262K | not measured | Unknown | Unknown | Unknown |
| Novita AI | $0.60 / $2.50 | 262K | not measured | Unknown | Unknown | Unknown |
| Novita AIbf16 | $0.60 / $2.50 | 262K | 32 tok/s | No | No | Confirmed |
| Google Vertex AI | $0.60 / $2.50 | 262K | 24 tok/s | No | No | Confirmed |
Novita AI
Google Vertex AIAcross the 4 listings we hold: 2 say they do not train on prompts, 0 say they do and 2 do not say. 2 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 AIbf16 | ✓ | ✓ | ✓ |
| Google Vertex AI | ✓ | ✓ | ✓ |
Tool calling: 3 of 4 listings say yes, 1 publishes no parameter list. JSON output: 3 of 4 listings say yes, 1 publishes no parameter list. Strict schema: 3 of 4 listings say yes, 1 publishes no parameter list.
When we formed this view
Dates behind this page
Prices last checked 35h 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 4 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 4 listings do not say whether they train on prompts.
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-Thinking
- Architecture
- Mixture of experts
- Modality record
- text->text
- Catalogue slug
- moonshotai-kimi-k2-thinking