Beam 501B-A23B
Sparse mixture-of-experts reasoning model with 23B active parameters for coding and agentic workflows
- Released
- Oct 5 2026
- Modality
- Text
- Context
- 1M tokens
- Price in / cached input / out
- $0.00 / $0.00 / $0.00per 1M tokensNew prices start Nov 9
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="beam-501b-a23b",
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
- 501B total / 23B active
- License
- Apache 2.0
Capabilities
- Reasoning
- Supported
- Function calling
- Supported
- Structured outputs
- Supported
- Web search grounding
- Not supported
Pricing
- Input
- $0.00
- Cached input
- $0.00
- Output
- $0.00
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 |
|---|---|---|---|
| Reflection AI | Yes | Yes | US |
When to use Beam 501B-A23B
Guidance based on the specifications and benchmarks on this page.
Best for
- Token-efficient reasoningReflection reports quality comparable to leading open models using about 3x fewer reasoning tokens.
- Agentic codingScores 81.6% on SWE-bench Verified and 80.1% on Terminal-Bench 2.1, per Reflection.
- Long-horizon tool useBuilt for multi-step MCP workflows, scoring 80.8% on MCP-Atlas with a 1M-token context window.
Consider alternatives for
- You need image, audio, or video inputBeam takes text in and produces text out only.
- You need the strongest long-horizon software engineeringBeam scores 43.3% on DeepSWE v1.1, where Muse Wonder 1.0 (78.8%) and Kimi K3 (67.5%) lead.
- You work mainly in languages other than EnglishReflection says Beam was developed predominantly for English.
Benchmarks
Beam 501B-A23B results alongside comparable models
| Benchmark | Beam 501B-A23BReflection AI | DeepSeek V4 ProDeepSeek | Kimi K3Moonshot AI | Qwen3.8 MaxAlibaba | DeepSeek V4.1 FlashDeepSeek | Kimi K3.1 ProMoonshot AI |
|---|---|---|---|---|---|---|
| GPQA Diamond | 90.6% | 90.1% | 93.5% | 92.6% | 90.9% | 94.2% |
| Humanity's Last Exam | 36% | 37.7% | 43.5% | 43.6% | 36.8% | 51.1% |
| Humanity's Last Exam (with tools) | 51.1% | 48.2% | 56% | 56.2% | 63.9% | 70% |
| AIME 2026 | 97.7% | Not evaluated | Not evaluated | Not evaluated | Not evaluated | Not evaluated |
| IFBench | 79.6% | Not evaluated | Not evaluated | 82.8% | Not evaluated | Not evaluated |
Scores are self-reported by each model’s developer, so settings may vary between models. Sources: Beam 501B-A23B (Hugging Face), DeepSeek V4 Pro (Hugging Face), Kimi K3 (Hugging Face), Qwen3.8 Max (Hugging Face), Qwen3.8 Max (release post), DeepSeek V4.1 Flash (Hugging Face), Kimi K3.1 Pro (release post).
Give Beam 501B-A23B 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 modelsMoonshot AI’s flagship open-weight multimodal reasoning model, post-trained from Kimi K3 across hundreds of domains with a 1M-token context window.
Muse 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.
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.