Kimi K2 Thinking
- In Input modalities: Text Out Output modalities: Text
- Reasoning
- Tool use
- Structured output
- Open weights
Prices
3 offerings · prices as listedkimi-k2-thinking| Conditions/ 1M tokens | Input | Output |
|---|---|---|
| Standard no longer listed since Oct 11, 2026 | ¥4.00 | ¥16.00 |
Prices from 阿里云百炼:模型价格 (opens in a new tab) (checked Oct 8, 2026)
kimi-k2-thinking| Conditions/ 1M tokens | Input | Cache read | Output |
|---|---|---|---|
| Standard past price, from the vendor’s page archived Mar 30, 2026 | $0.60 | $0.15 | $2.50 |
Prices from Moonshot AI platform pricing (opens in a new tab) (checked Oct 23, 2026)
kimi-k2-thinking| Conditions/ 1M tokens | Input | Cache read | Output |
|---|---|---|---|
| Standard past price, from the vendor’s page archived Feb 17, 2026 | ¥4.00 | ¥1.00 | ¥16.00 |
Prices from Kimi API 开放平台:模型推理价格 (opens in a new tab) (checked Oct 23, 2026)
Standard: the price a request with no conditions pays (the headline price elsewhere on the site).
Details
- Max input
- 229.38K
- Built-in tools
- Web search
- Knowledge cutoff
- Aug 2024
- Family
- kimi-k-thinking
- Model ID
Not stated on Moonshot AI’s pages: reasoning efforts, reasoning can be off, max thinking budget, aliases.
Run locally
Weights: moonshotai/Kimi-K2-Thinking- Parameters 1.03T
- Active 32B · 384 experts, 8 per token
- Native precision INT4 (AWQ / GPTQ)
- Layers 61
- KV cache per token 69 KB
- Config positions 256K (config.json max_position_embeddings)
- API context 250K (maker’s API)
- Needs
- ≈ 581.6 GB (weights 553.4 (maker’s file) + KV cache 0.5 + overhead 27.7)
- Usable
- 21.6 GB (90% of its memory)
- Try
- it’s too large for this hardware; see the smallest that runs it below
| Precision | Weights | Needs at 8K | On your hardware | Longest context |
|---|---|---|---|---|
| INT4 (AWQ / GPTQ) (native)maker’s file | 553.4 GB | ≈ 581.6 | ✕Doesn’t fit | — |
| Q3_K_Mquality drops | 467.2 GB | ≈ 491.1 | ✕Doesn’t fit | — |
| IQ3_XXSquality drops | 365.6 GB | ≈ 384.5 | ✕Doesn’t fit | — |
| Q2_Kquality drops | 358.5 GB | ≈ 376.9 | ✕Doesn’t fit | — |
| IQ2_XXSquality drops | 246.1 GB | ≈ 259.0 | ✕Doesn’t fit | — |
Click a row to choose a precision. “Maker’s file” sizes are the maker’s own files; others are parameters × bits per weight.
Compared with other hardware
Each at the highest precision it runs. Click one for details.
Smallest that runs it (INT4 (AWQ / GPTQ) (native), 8K): no single listed machine; about 9 × 80 GB GPUs.
Run commands
vllm serve moonshotai/Kimi-K2-Thinking --max-model-len 8192
Memory to fine-tune
Batch 1, 2,048-token sequences, gradient checkpointing; LoRA and QLoRA train rank-16 adapters on the attention projections.
Estimates; facts from the maker’s Hugging Face repositories, as of 2026-11-21. How it’s estimated
Cited scores
From third-party leaderboards, not measured by us- Epoch Capabilities Index 145.5
#78 of 123 listed models · CI 143.7–147.3
- EQ-Bench Creative Writing v3 1,631
#38 of 95 listed models
- EQ-Bench Longform Writing 69
#41 of 93 listed models
- Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks'. Licensed CC BY 4.0. · License · as of Nov 14, 2026
- EQ-Bench by Samuel J. Paech (eqbench.com; EQ-bench/EQ-bench-site on GitHub), MIT License. · License · as of Oct 28, 2026
- changes we made
Changes
All changes →- Now priced on Moonshot AI Platform, China Cache read ¥1.00 · Input ¥4.00 · Output ¥16.00
- Now priced on Moonshot AI Platform Cache read $0.15 · Input $0.60 · Output $2.50
- Now priced on Moonshot AI Platform, China Cache read ¥1.00 · Input ¥4.00 · Output ¥16.00
- Now priced on Moonshot AI Platform Cache read $0.15 · Input $0.60 · Output $2.50
- Now priced on Alibaba Cloud Model Studio, China Input ¥4.00 · Output ¥16.00
- Context window 256K → 262.14K
Sources
- Text generation models - Qwen, DeepSeek, GLM | Model Studio - Alibaba Cloud Model Studio - Alibaba Cloud Documentation Center (opens in a new tab) docs.modelstudio.console.alibabacloud.com · checked Oct 4, 2026
- kimi-k2-thinking model (opens in a new tab) alibabacloud.com · checked Oct 2, 2026
- kimi-k2-thinking (opens in a new tab) docs.modelstudio.console.alibabacloud.com · checked Oct 2, 2026
- 阿里云百炼:模型价格in Chinese (opens in a new tab) help.aliyun.com · checked Oct 8, 2026
- Moonshot AI platform pricing (opens in a new tab) platform.moonshot.ai · checked Oct 23, 2026
- Kimi API 开放平台:模型推理价格in Chinese (opens in a new tab) platform.moonshot.cn · checked Oct 23, 2026
- Platform Changelog (opens in a new tab) platform.kimi.ai · checked Nov 9, 2026
- 模型上架与更新-大模型服务平台百炼-阿里云_大模型服务平台百炼(Model Studio)-大模型服务平台百炼(Model Studio)-阿里云帮助中心in Chinese (opens in a new tab) help.aliyun.com · checked Nov 16, 2026
- 1. Model Introduction (opens in a new tab) huggingface.co · checked Nov 7, 2026
- moonshotai/Kimi-K2-Thinking model card (opens in a new tab) huggingface.co · checked Nov 6, 2026
- moonshotai/Kimi-K2-Thinking config.json (opens in a new tab) huggingface.co · checked Nov 8, 2026
- moonshotai/Kimi-K2-Thinking files (opens in a new tab) huggingface.co · checked Nov 6, 2026
- moonshotai/Kimi-K2-Thinking README.md (opens in a new tab) huggingface.co · checked Nov 6, 2026
- models.dev: moonshotai/kimi-k2-thinking (community data, MIT) (opens in a new tab) github.com · checked Oct 28, 2026
Moonshot AI’s official policies: data use, privacy, terms →
Some values on this page are still waiting to be checked against official pages: a filled dot is verified, a hollow one is not yet (with or without a source on file). How we verify data
Moonshot AI · China · moonshot.ai
Related models
Snapshots, the same family and other models from this provider