Muse Spark Open now available on AI Gateway
Quick Answer
Meta's Muse Spark Open is now accessible via AI Gateway, supporting coding workflows with a 1M-token context window for text and image inputs.
Quick Take
It integrates seamlessly with various APIs and coding agents, requiring no separate provider accounts and offering zero data retention.
Key Points
- Muse Spark Open is designed for coding tasks like refactoring and debugging.
- Supports both text and image inputs in a single request.
- Available across multiple APIs including OpenAI and Anthropic-compatible formats.
- No platform fees on inference, including Bring Your Own Key requests.
- AI Gateway offers unified API for model calls, usage tracking, and performance optimizations.
DeepSignal Analysis
What happened
Meta's Muse Spark Open is now accessible through AI Gateway, designed for coding workflows. It features a 1M-token context window for both text and image inputs, facilitating tasks like debugging and multi-file refactoring.
Key evidence
- Muse Spark Open supports a 1M-token context window for text and image inputs, allowing for simultaneous processing of code and screenshots.
- The model is available without requiring separate provider accounts and offers zero data retention, enhancing user privacy.
- AI Gateway provides a unified API for various coding agents, reflecting provider pricing without markup and including features like custom reporting and budget management.
Why it matters
The integration of Muse Spark Open into AI Gateway could streamline coding workflows by allowing developers to work with both text and images in a single request. This capability may improve efficiency in debugging and understanding complex codebases. Additionally, the zero data retention policy may appeal to users concerned about privacy, while the unified API simplifies interactions with multiple coding agents.
What to watch
📖 Reader Mode
~2 min readMuse Spark Open from Meta is now available on AI Gateway. The open-weight reasoning model is designed for coding and agentic workflows, including multi-file refactoring, debugging, and understanding large codebases.
Muse Spark Open supports text and image input with a 1M-token context window, allowing agents to work with code and screenshots in the same request. It is available with ZDR and no training, without creating separate provider accounts.
Use meta/muse-spark-open as the model name across all API formats and coding agents. The model is available across the AI SDK, the OpenAI-compatible Chat Completions and Responses APIs, the Anthropic-compatible Messages API, and coding agents connected to AI Gateway.
To use it in Claude Code, Codex, Cursor, and more, install the latest Vercel CLI and run setup:
# Upgrade to the latest version of the Vercel CLI
pnpm i -g vercel@latest
# Run coding agents setup command
vercel ai-gateway coding-agents setup
Then select meta/muse-spark-open in the agent. See the coding agents guide for details.
Try Muse Spark Open in the model playground.
AI Gateway provides a unified API for calling models, tracking usage and cost, and configuring retries, failover, and performance optimizations for higher-than-provider uptime. It includes built-in custom reporting, Zero Data Retention support, budgets for API keys, routing rules, and more.
AI Gateway reflects provider pricing with no markup and does not charge a platform fee on inference, including on Bring Your Own Key (BYOK) requests.
You can view all language models available on AI Gateway.
— Originally published at vercel.com
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from Vercel AI
See more →
The Agent Stack
The Agent Stack by Vercel AI provides essential building blocks for creating production-grade agents, enabling seamless integration across multiple AI models and secure operations. It features components like AI Gateway for model routing, Workflow SDK for durable execution, and Vercel Connect for scoped access, streamlining agent development and deployment across various platforms.
