Meta Model API
Everruns runs Muse models through Meta Model API. The
dedicated meta driver uses Meta’s OpenAI-compatible Responses API at
https://api.meta.ai/v1, including streaming, parallel tool calls, reasoning
replay, message phases, hosted tool search, and server-managed response history.
Configure in Everruns
Section titled “Configure in Everruns”- Create an API key in the Meta Model API dashboard.
- Go to Settings → Providers and click Add provider.
- Choose Meta Model API, paste the key, and save.
- Sync models to import the Muse models available to your team.
The hosted endpoint is used by default. An optional base URL can point the driver at a compatible proxy; model discovery is disabled for non-Meta hosts.
Muse Spark 1.2 tiers
Section titled “Muse Spark 1.2 tiers”Both 1.2 model IDs have a 1,048,576-token context window and accept text, images, audio, video, and PDFs while producing text.
| Model | Data use | Input / cached input / output per million tokens |
|---|---|---|
muse-spark-1.2 | Prompts and completions are not used to train Meta models | $1.25 / $0.15 / $4.25 |
muse-spark-1.2-contributor | Prompts and completions may be used to train future Meta models | $0.10 / $0.002 / $0.20 |
Choose the Contributor model only when the organization accepts its data-use terms. The distinction is part of the model ID, so changing tiers is an explicit model selection rather than a hidden provider setting.