Qwen3.8 Max
2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows
- Released
- Aug 3 2026
- Modality
- Text + Image + Document + Video
- Context
- 1M tokens
- Price in / cached input / out
- $1.85 / $0.23 / $5.55per 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["YOU_API_KEY"],
)
response = client.chat.completions.create(
model="qwen3.8-max",
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, Document, Video
- Output Modality
- Text
- Context Window
- 1M
- Parameters
- 2.4T total / 95B active
- License
- Qwen3.8-Max License
Capabilities
- Reasoning
- Supported
- Function calling
- Supported
- Structured outputs
- Supported
- Web search grounding
- Available with You.com Search
Pricing
- Input
- $1.85
- Cached input
- $0.23
- Output
- $5.55
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 |
|---|---|---|---|
| You Inference | Yes | Yes | US |
| Alibaba | Yes | Yes | US |
When to use Qwen3.8 Max
Guidance based on the specifications and benchmarks on this page.
Best for
- Multi-day autonomous coding projectsQwen showed it running autonomously for over 10 days to build a self-evolving harness, with 265 commits and 127 PRs.
- Research reproduction and ML engineeringScores 93.0% on PaperBench; Qwen showed it reproducing a paper over about 125 hours and improving on its result.
- Professional and computer-use workHandles legal, finance, and health tasks, and scores 86.1% on OSWorld-Verified for computer use.
Consider alternatives for
- You need the best SWE-bench ProIn Qwen's own table, Claude Fable 5 scores 80.0% on SWE-bench Pro versus 67.7% for Qwen3.8 Max.
- You need lower-cost multimodal agentsQwen3.7 Plus is Alibaba's cost-effective tier and also accepts image and video input.
- You need audio inputQwen3.8 Max accepts text, image, and video input and returns text only.
Benchmarks
Qwen3.8 Max results alongside comparable models
| Benchmark | Qwen3.8 MaxAlibaba | Kimi K3Moonshot AI | DeepSeek V4.1 FlashDeepSeek | GLM 5.3Z.ai | DeepSeek V4 ProDeepSeek | GPT-OSS 120BOpenAI |
|---|---|---|---|---|---|---|
| GPQA Diamond | 92.6% | 93.5% | 90.9% | Not evaluated | 90.1% | 80.1% |
| Humanity's Last Exam | 43.6% | 43.5% | 36.8% | Not evaluated | 37.7% | 14.9% |
| Humanity's Last Exam (with tools) | 56.2% | 56% | 63.9% | 62.5% | 48.2% | 19% |
| IFBench | 82.8% | Not evaluated | Not evaluated | Not evaluated | Not evaluated | Not evaluated |
Scores are self-reported by each model’s developer, so settings may vary between models. Sources: Qwen3.8 Max (Hugging Face), Qwen3.8 Max (release post), Kimi K3 (Hugging Face), DeepSeek V4.1 Flash (Hugging Face), GLM 5.3 (Hugging Face), DeepSeek V4 Pro (Hugging Face), GPT-OSS 120B (model card).
Give Qwen3.8 Max 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 modelsFlagship GLM model for long-horizon coding, agents, and complex project delivery
Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work
DeepSeek V4.1 Flash model for reasoning and agentic coding
Open MoE flagship with million-token context for coding and long agent runs
Build with Inference Router
Tell us what you run today, and a solutions engineer will show you what it costs on open-weight models.