Kimi K3.1 Pro
- In Input modalities: TextImageVideo Out Output modalities: Text
- Reasoning· low, high, max
- Tool use
- Structured output
- Open weights
Prices
8 offerings · prices as listedkimi-k3.1-pro| Conditions/ 1M tokens | Input | Cache read | Cache write | Output | |
|---|---|---|---|---|---|
| 5-minute cache | 1-hour cache | ||||
| Standard | $2.00 | $0.20 | $2.00 | $4.00 | $10.00 |
Prices from Moonshot AI platform pricing (opens in a new tab) (checked Nov 8, 2026)
kimi-k3.1-pro| Conditions/ 1M tokens | Input | Cache read | Cache write | Output | |
|---|---|---|---|---|---|
| 5-minute cache | 1-hour cache | ||||
| Standard | ¥13.00 | ¥1.30 | ¥13.00 | ¥26.00 | ¥68.00 |
Prices from Kimi API 开放平台：模型推理价格 (opens in a new tab) (checked Nov 8, 2026)
kimi-k3.1-pro| Conditions/ 1M tokens | Input | Cache read | Output |
|---|---|---|---|
| Standard | ¥13.00 | ¥1.30 | ¥68.00 |
Prices from 火山方舟：模型价格 (opens in a new tab) (checked Nov 8, 2026)
kimi/kimi-k3.1-pro| Conditions/ 1M tokens | Input | Output |
|---|---|---|
| Standard | ¥13.00 | ¥68.00 |
Prices from 阿里云百炼：模型价格 (opens in a new tab) (checked Nov 4, 2026)
kimi-k3.1-pro| Conditions/ 1M tokens | Output |
|---|---|
| Standard | ¥68.00 |
Prices from 阿里云百炼：模型价格 (opens in a new tab) (checked Nov 4, 2026)
kimi-k3.1-pro| Conditions/ 1M tokens | Input | Cache read | Output |
|---|---|---|---|
| Standard | $1.837 | $0.184 | $9.611 |
Prices from Alibaba Cloud Model Studio pricing (opens in a new tab) (checked Nov 6, 2026)
kimi-k3.1-pro| Conditions/ 1M tokens | Input | Cache read | Output |
|---|---|---|---|
| Standard | $2.00 | $0.20 | $10.00 |
Prices from Alibaba Cloud Model Studio pricing (opens in a new tab) (checked Nov 6, 2026)
Standard: the price a request with no conditions pays (the headline price elsewhere on the site).
Details
- Family
- kimi-k-pro
- Model ID
Not stated on Moonshot AI’s pages: max input, reasoning can be off, max thinking budget, built-in tools, knowledge cutoff, licence, aliases.
Run locally
Weights: moonshotai/Kimi-K3.1-Pro- Parameters 2.78T
- Active not stated · 896 experts, 16 per token
- Native precision BF16
- Layers 93
- KV cache per token 105 KB
- Config positions 1024K (config.json max_position_embeddings)
- API context 977K (maker’s API)
- Needs
- ≈ 1445.1 GB (weights 1375.5 + KV cache 0.8 + overhead 68.8)
- 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 |
|---|---|---|---|---|
| BF16 (native)maker’s file | 1454.1 GB | ≈ 1527.6 | ✕Doesn’t fit | — |
| Q8_0 | 2751.0 GB | ≈ 2889.4 | ✕Doesn’t fit | — |
| FP8 | 2589.2 GB | ≈ 2719.5 | ✕Doesn’t fit | — |
| Q6_K | 2126.4 GB | ≈ 2233.5 | ✕Doesn’t fit | — |
| Q5_K_M | 1841.6 GB | ≈ 1934.4 | ✕Doesn’t fit | — |
| Q5_0 | 1780.1 GB | ≈ 1869.9 | ✕Doesn’t fit | — |
| Q4_K_M | 1572.9 GB | ≈ 1652.4 | ✕Doesn’t fit | — |
| Q4_0 | 1456.4 GB | ≈ 1530.1 | ✕Doesn’t fit | — |
| IQ4_XS | 1375.5 GB | ≈ 1445.1 | ✕Doesn’t fit | — |
| Q3_K_Mquality drops | 1265.5 GB | ≈ 1329.6 | ✕Doesn’t fit | — |
| IQ3_XXSquality drops | 990.4 GB | ≈ 1040.7 | ✕Doesn’t fit | — |
| Q2_Kquality drops | 970.9 GB | ≈ 1020.3 | ✕Doesn’t fit | — |
| IQ2_XXSquality drops | 666.7 GB | ≈ 700.9 | ✕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 (Q4_K_M, 8K): no single listed machine; about 23 × 80 GB GPUs.
Run commands
The maker publishes no files at this precision. Choose its native precision or one of its own builds, or quantise it yourself with llama.cpp.
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 2026-11-11. How it’s estimated
Cited scores
From third-party leaderboards, not measured by us- EQ-Bench Creative Writing v3 2,173
#2 of 94 listed models
- EQ-Bench Longform Writing 79.9
#16 of 92 listed models
- LMArena WebDev 1,687
#9 of 94 listed models · max effort · CI 1,677–1,697 · 4,651 votes
- EQ-Bench by Samuel J. Paech (eqbench.com; EQ-bench/EQ-bench-site on GitHub), MIT License. · License · as of Oct 28, 2026
- LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Nov 8, 2026
- changes we made
Included in coding plans
- 5× the usage of the Lite plan
- Kimi Code (Kimi membership) Plus ¥99.00 / monthFor new members, the weekly quota limit is removed, and only the rolling 5-hour rate window remains.Both groups share the Kimi membership monthly total quota
- Kimi Code (Kimi membership) Pro ¥199.00 / monthFor new members, the weekly quota limit is removed, and only the rolling 5-hour rate window remains.Both groups share the Kimi membership monthly total quota
- Kimi Code (Kimi membership) Max ¥699.00 / monthFor new members, the weekly quota limit is removed, and only the rolling 5-hour rate window remains.Both groups share the Kimi membership monthly total quota
News
All news →- Oct 31, 2026Capability Moonshot AI adds Kimi K3.1 Pro and K3 to Batch API Batch API now supports kimi-k3.1-pro and kimi-k3 on both the CN and Global platforms. Batch inference costs 60% of standard rates; these models also incur Cache Write fees, and cache hits are best-effort.
- Oct 23, 2026Release Moonshot AI releases Kimi K3.1 Pro models Kimi K3.1 Pro and Kimi K3.1 Pro Highspeed are available today through the Kimi API and Kimi products. K3.1 Pro has a 1-million-token context window; full weights are scheduled for release by Nov. 4, 2026.
Changes
All changes →- 2 new prices on Alibaba Cloud Model Studio, International Input $2.00 · Cache read $0.20
- 2 new prices on Alibaba Cloud Model Studio, US Input $2.00 · Cache read $0.20
- 2 new prices on Alibaba Cloud Model Studio Input $1.837 · Cache read $0.184
- Now priced on Alibaba Cloud Model Studio, International Output $10.00
- Now priced on Alibaba Cloud Model Studio, US Output $10.00
- Now priced on Alibaba Cloud Model Studio Output $9.611
- Now priced on Alibaba Cloud Model Studio, China Output ¥68.00
- Now priced on Alibaba Cloud Model Studio, China Input ¥13.00 · Output ¥68.00
- Now priced on Volcengine Ark, China Input ¥13.00 · Cache read ¥1.30 · Output ¥68.00
- New language model
Sources
- Kimi K3.1 Pro (opens in a new tab) kimi.com · checked Nov 6, 2026
- Kimi K3.1 Pro - Kimi API Platform (opens in a new tab) platform.kimi.ai · checked Nov 6, 2026
- Moonshot AI platform pricing (opens in a new tab) platform.moonshot.ai · checked Nov 8, 2026
- Kimi API 开放平台：模型推理价格in Chinese (opens in a new tab) platform.moonshot.cn · checked Nov 8, 2026
- Kimi API chat completions reference (opens in a new tab) platform.kimi.ai · checked Nov 6, 2026
- models.dev: moonshotai/kimi-k3.1-pro (community data, MIT) (opens in a new tab) github.com · checked Oct 24, 2026
- 火山方舟：模型价格in Chinese (opens in a new tab) docs.volcengine.com · checked Nov 8, 2026
- 阿里云百炼：模型价格in Chinese (opens in a new tab) help.aliyun.com · checked Nov 4, 2026
- moonshotai/Kimi-K3.1-Pro config.json (opens in a new tab) huggingface.co · checked Nov 4, 2026
- moonshotai/Kimi-K3.1-Pro model card (opens in a new tab) huggingface.co · checked Nov 4, 2026
- Alibaba Cloud Model Studio pricing (opens in a new tab) alibabacloud.com · checked Nov 6, 2026
- moonshotai/Kimi-K3.1-Pro files (opens in a new tab) huggingface.co · checked Nov 5, 2026
- Alibaba Cloud Model Studio: text generation models (opens in a new tab) docs.modelstudio.console.alibabacloud.com · checked Nov 6, 2026
- 模型上下架与更新-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 7, 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