Muse Spark 1.3
Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It improves long-horizon agent collaboration, instruction following, and coding efficiency relative to Muse Spark 1.2.
- Released
- Sep 2 2026
- Modality
- Text + Image + Document + Audio + Video
- Context
- 1M tokens
- Price in / cached input / out
- $1.25 / $0.15 / $4.25per 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="muse-spark-1.3",
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, Audio, Video
- Output Modality
- Text
- Context Window
- 1M
Capabilities
- Reasoning
- Supported
- Function calling
- Supported
- Structured outputs
- Not supported
- Web search grounding
- Not supported
Pricing
- Input
- $1.25
- Cached input
- $0.15
- Output
- $4.25
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 |
| Meta | Yes | Yes | US |
When to use Muse Spark 1.3
Guidance based on the specifications and benchmarks on this page.
Best for
- Long-horizon agentic codingMeta tuned it for long coding workflows; it scores 75.4% on DeepSWE v1.1 and 88.8% on Terminal-Bench 2.1 at max reasoning.
- Retrieval across very long contextMeta reports 98% or higher on MRCR v2 needle retrieval at 256K–1M tokens.
- Multi-step agent workflowsSustains long threads, gathers context from conflicting sources, corrects gaps in its plan, and asks for clarification when stuck.
Consider alternatives for
- You need maximum agentic capabilityMeta says Muse Wonder builds on larger, stronger base models and handles unfamiliar tasks better.
- You need open weightsMuse Spark 1.3 weights are closed; Meta offers Muse Spark Open for self-hosting.
Benchmarks
Muse Spark 1.3 results alongside comparable models
| Benchmark | Muse Spark 1.3Meta | Kimi K3Moonshot AI | DeepSeek V4.1 FlashDeepSeek | GLM 5.3Z.ai | Qwen3.8 MaxAlibaba | Muse WonderMeta |
|---|---|---|---|---|---|---|
| Terminal-Bench 2.1 | 88.8% | 88.3% | 90.6% | 88.2% | 86.6% | Not evaluated |
| DeepSWE v1.1 | 75.4% | 67.5% | 74.2% | 66.9% | 56.6% | 78.8% |
Scores are self-reported by each model’s developer, so settings may vary between models. Sources: Muse Spark 1.3 (release post), Kimi K3 (Hugging Face), DeepSeek V4.1 Flash (Hugging Face), GLM 5.3 (Hugging Face), Qwen3.8 Max (Hugging Face), Qwen3.8 Max (release post), Muse Wonder (release post).
Give Muse Spark 1.3 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.