Kimi K3.1 Pro
Moonshot AI’s flagship open-weight multimodal reasoning model, post-trained from Kimi K3 across hundreds of domains with a 1M-token context window.
- Released
- Oct 23 2026
- Modality
- Text + Image + Video
- Context
- 1M tokens
- Price in / cached input / out
- $1.90 / $0.19 / $9.50per 1M tokens
Quickstart
OpenAI-compatible: change the base URL, and the setup is complete.
from openai import OpenAI
import os
client = OpenAI(
base_url="https://api.you.com/v1",
api_key=os.environ["YDC_API_KEY"],
)
response = client.chat.completions.create(
model="kimi-k3.1-pro",
messages=[{"role": "user", "content": "Summarize this support ticket in two sentences."}],
)
print(response.choices[0].message.content)Specifications
Technical details, capabilities, pricing, and data handling.
Model info
- Input Modality
- Text, Image, Video
- Output Modality
- Text
- Context Window
- 1M
- Parameters
- 2.8T total / 104B active
- License
- Kimi K3.1 Pro License
Capabilities
- Reasoning
- Supported
- Function calling
- Supported
- Structured outputs
- Supported
- Web search grounding
- Not supported
Pricing
- Input
- $1.90
- Cached input
- $0.19
- Output
- $9.50
Data handling
- Zero data retention
- Supported
- No training on customer data
- Supported
- Regions
- US
Providers
Access models through multiple providers with automatic routing and built-in failover.
| Provider | ZDR | No training | Region |
|---|---|---|---|
| Wafer | Yes | Yes | US |
When to use Kimi K3.1 Pro
Guidance based on the specifications and benchmarks on this page.
Best for
- Long-horizon agentic codingScores 65.7% on Terminal-Bench 4.0, just behind Claude Opus 5.5, and 75.5% on DeepSWE v1.1, per Moonshot.
- Finance and document-heavy researchTops Moonshot's OfficeQA Pro v2 comparison at 64.4 and cuts its hallucination rate on hard factual prompts from 23.4% to 8.3% versus K3.
- 3D, CAD, and parametric modelingScores 92.7% on BenchCAD with tools and writes Blender and CAD scripts to build and refine 3D assets.
Consider alternatives for
- You need the hardest expert-level reasoningIt scores 39.4 on HLE-Diamond, where Moonshot's own table shows GPT-6 Astra at 65.8 and Claude Opus 5.5 at 60.9.
- You need low-cost, high-volume inferenceSmaller models such as DeepSeek V4.1 Flash or GPT-OSS 120B fit simple, high-volume workloads at lower cost.
- You need audio input or outputLike Kimi K3, it handles text, images, and video; audio is not a supported modality.
Benchmarks
Kimi K3.1 Pro results alongside comparable models
| Benchmark | Kimi K3.1 ProMoonshot AI | Kimi K3Moonshot AI | Qwen3.8 MaxAlibaba | DeepSeek V4 ProDeepSeek | DeepSeek V4.1 FlashDeepSeek | Beam 501B-A23BReflection AI |
|---|---|---|---|---|---|---|
| GPQA Diamond | 94.2% | 93.5% | 92.6% | 90.1% | 90.9% | 90.6% |
| Humanity's Last Exam | 51.1% | 43.5% | 43.6% | 37.7% | 36.8% | 36% |
| Humanity's Last Exam (with tools) | 70% | 56% | 56.2% | 48.2% | 63.9% | 51.1% |
Scores are self-reported by each model’s developer, so settings may vary between models. Sources: Kimi K3.1 Pro (release post), Kimi K3 (Hugging Face), Qwen3.8 Max (Hugging Face), Qwen3.8 Max (release post), DeepSeek V4 Pro (Hugging Face), DeepSeek V4.1 Flash (Hugging Face), Beam 501B-A23B (Hugging Face).
Give Kimi K3.1 Pro access to the live web
Ground responses with fresh web information and cited sources using You.com Search, without changing models or adding another integration.
What error do I get installing psycopg2 on Python 3.13?
LLM + You.com Web Search
psycopg2 on Python 3.13
Short answer:
psycopg2 installs fine today. 2.9.10 added 3.13 support in Oct 2024. 12
The error you hit is almost certainly missing build step:
pg_config executable not found
Fix:
pip install -U psycopg2-binary
LLM (LLM only)
When trying to install psycopg2 on Python 3.13, you will most likely hit one of these errors:
1. No pre-built wheel available
pip cannot find a binary wheel because the psycopg2 project hasn’t yet published wheels for Python 3.13.
What you should do
Downgrade Python — use Python 3.12 or earlier until psycopg2 officially supports 3.13.
Explore popular models
Explore all modelsMuse Wonder is a frontier multimodal reasoning model from Meta for personal and professional agents, long-horizon coding, and computer use. It combines Active Memory, which carries relevant context across conversations, with Active Focus, which keeps it working through blockers toward a goal.
Sparse mixture-of-experts reasoning model with 23B active parameters for coding and agentic workflows
DeepSeek V4.1 Flash model for reasoning and agentic coding
Build with Inference Router
Share a few details and a solutions engineer will reach out to show you what your workloads cost on open-weight models.