Meta Model API
An API service introduced by Meta that allows developers to integrate model capabilities such as Muse and Spark into programming toolchains, IDE plugins, or code assistant products. It follows an API-first strategy to compete for the developer ecosystem.
Core Facts
Muse Wonder is offered through the Meta Model API and Muse Code; Muse Wonder Full is for Muse Code subscribers.
Meta officially released the MuseWonder series of models, including the standard MuseWonder and the more powerful MuseWonder Full.
Timeline (last 90 days)
The availability of the API and Muse Code depends on the region, which is an account-level regional restriction, and a VPN cannot reliably solve the problem of billed API access.
On the Chat Completions endpoint, reasoning content is not persisted across turns, causing inconsistency before and after in multi-turn agent conversations; the fix is to switch to the Responses API.
On the Chat Completions endpoint, `reasoning_effort` accepts values from `minimal` to `max`, does not support `none`, and sending `none` returns a 400 error.
The rate limits set by the Meta Model API for the Muse Wonder model are 3000 requests per minute (RPM) and 4 million Tokens per minute (TPM)
Muse Wonder's rate limits are shared per team and per model, rather than calculated independently per API key; all keys within a team consume the same quota pool.
Muse Wonder's rate limits on the Meta Model API are 3,000 RPM and 4 million TPM per team, per model.
Muse Wonder's rate limits are calculated per team and per model, and all API keys within the same organization share the same RPM/TPM quota pool.
Meta officially released the MuseWonder series of models, including the standard MuseWonder and the more powerful MuseWonder Full.
Muse Wonder is offered through the Meta Model API and Muse Code; Muse Wonder Full is for Muse Code subscribers.
The Meta Model API does not offer Muse Wonder Full—that is exclusive to Muse Code subscribers.
4 more timeline events
All Facts (13)
Muse Wonder is offered through the Meta Model API and Muse Code; Muse Wonder Full is for Muse Code subscribers.
80%UnverifiedMuse Wonder's rate limits are shared per team and per model, rather than calculated independently per API key; all keys within a team consume the same quota pool.
60%UnverifiedMuse Wonder's rate limits on the Meta Model API are 3,000 RPM and 4 million TPM per team, per model.
60%UnverifiedThe availability of the API and Muse Code depends on the region, which is an account-level regional restriction, and a VPN cannot reliably solve the problem of billed API access.
50%UnverifiedOn the Chat Completions endpoint, `reasoning_effort` accepts values from `minimal` to `max`, does not support `none`, and sending `none` returns a 400 error.
50%UnverifiedOn the Chat Completions endpoint, reasoning content is not persisted across turns, causing inconsistency before and after in multi-turn agent conversations; the fix is to switch to the Responses API.
50%UnverifiedThe rate limits set by the Meta Model API for the Muse Wonder model are 3000 requests per minute (RPM) and 4 million Tokens per minute (TPM)
50%UnverifiedMuse Wonder's rate limits are calculated per team and per model, and all API keys within the same organization share the same RPM/TPM quota pool.
50%UnverifiedThe model ID for the Meta Model API is muse-wonder-1.0.
50%UnverifiedThe Meta Model API does not offer Muse Wonder Full—that is exclusive to Muse Code subscribers.
50%UnverifiedThe Meta Model API is a model access interface layer provided by Meta that allows external tools and agents to communicate with the underlying model via standardized API calls, without going through the application UI layer.
50%UnverifiedClaude Code and Codex can be run on Muse Spark 1.3 via the Meta Model API.
50%Partially VerifiedMeta officially released the MuseWonder series of models, including the standard MuseWonder and the more powerful MuseWonder Full.
65%