DeepSeek V4 Pro
Open MoE flagship with million-token context for coding and long agent runs
- Released
- Apr 24 2026
- Modality
- Text
- Context
- 1M tokens
- Price in / cached input / out
- $1.65 / $0.10 / $3.65per 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="deepseek-v4-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
- Output Modality
- Text
- Context Window
- 1M
- Parameters
- 1.6T total / 49B active
- License
- MIT
Capabilities
- Reasoning
- Supported
- Function calling
- Supported
- Structured outputs
- Supported
- Web search grounding
- Available with You.com Search
Pricing
- Input
- $1.65
- Cached input
- $0.10
- Output
- $3.65
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 |
| Parasail | Yes | Yes | US |
| Wafer | Yes | Yes | US |
When to use DeepSeek V4 Pro
Guidance based on the specifications and benchmarks on this page.
Best for
- Competitive coding and code generationDeepSeek reports top-tier coding results in Max mode, including 93.5% on LiveCodeBench and 80.6% on SWE-bench Verified.
- Knowledge-heavy reasoningDeepSeek calls its Max mode the strongest open model for knowledge, with 90.1% on GPQA Diamond and 87.5% on MMLU-Pro.
- Million-token context workloadsUses 10% of DeepSeek-V3.2's KV cache at 1M tokens, which makes very long inputs cheaper to process.
Consider alternatives for
- You need image understandingDeepSeek V4 Pro takes text only; DeepSeek V4.1 Flash natively accepts images alongside text.
- You need lower cost per tokenDeepSeek V4.1 Flash activates far fewer parameters per token and suits cost-sensitive, input-heavy agent work.
- You need frontier agentic performanceDeepSeek says V4 Pro narrows, but doesn't close, the gap to closed frontier models on reasoning and agentic tasks.
Benchmarks
DeepSeek V4 Pro results alongside comparable models
| Benchmark | DeepSeek V4 ProDeepSeek | Kimi K3Moonshot AI | GPT-OSS 120BOpenAI | Qwen3.8 MaxAlibaba | DeepSeek V4.1 FlashDeepSeek | GLM 5.3Z.ai |
|---|---|---|---|---|---|---|
| GPQA Diamond | 90.1% | 93.5% | 80.1% | 92.6% | 90.9% | Not evaluated |
| Humanity's Last Exam | 37.7% | 43.5% | 14.9% | 43.6% | 36.8% | Not evaluated |
| Humanity's Last Exam (with tools) | 48.2% | 56% | 19% | 56.2% | 63.9% | 62.5% |
| HMMT Feb 2026 | 95.2% | Not evaluated | Not evaluated | Not evaluated | Not evaluated | Not evaluated |
| IMOAnswerBench | 89.8% | Not evaluated | Not evaluated | Not evaluated | Not evaluated | Not evaluated |
| Apex | 38.3% | Not evaluated | Not evaluated | Not evaluated | Not evaluated | Not evaluated |
| MMLU-Pro | 87.5% | 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: DeepSeek V4 Pro (Hugging Face), Kimi K3 (Hugging Face), GPT-OSS 120B (model card), Qwen3.8 Max (Hugging Face), Qwen3.8 Max (release post), DeepSeek V4.1 Flash (Hugging Face), GLM 5.3 (Hugging Face).
Give DeepSeek V4 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 models2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows
Flagship 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
Build with Inference Router
Tell us what you run today, and a solutions engineer will show you what it costs on open-weight models.