Meshy Motion Swift generates standalone character motion from text. Swift exports BVH at 3 credits per task. Clips can be retargeted to rigged characters.
Value for mode, not an ai_model field or immutable checkpoint.
Access
POST https://api.meshy.ai/openapi/v1/text-to-motion with Bearer API key, prompt, duration and mode=swift. The selector is a mode field, not ai_model. Poll GET /:id or status SSE; download the completed motion_url.
General retention documentation permits indefinite Enterprise storage. Confirm the account contract.
Request quotas
Account-wide: Pro/Premium/Ultra/Studio 20 requests/sec; queue limits 10/30/100/20 respectively. Enterprise 100 requests/sec and default queue 100, customizable. Web tasks share the queue.Source for Request quotas (opens in a new tab)
API output is deleted after three days for non-Enterprise customers. Enterprise defaults to indefinite output storage, configurable to 1–30 days or contract-specific terms. This is output retention, not a guarantee about logs or all customer data.
No model selector: this operation applies an existing motion task to an existing rig.
Access
POST https://api.meshy.ai/openapi/v1/animations with Bearer key, rig_task_id and motion_task_id. This is a downstream application operation, not a separate generation model.
API output is deleted after three days for non-Enterprise customers. Enterprise defaults to indefinite output storage, configurable to 1–30 days or contract-specific terms. This is output retention, not a guarantee about logs or all customer data.
Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.
01 / INITIAL INPUTProcess & retain
The system processes eligible input and retains reusable state.
02 / LATER REQUESTCheck available state
Reuse depends on matching input, session state and the cache policy.
03 / CACHE HITReuse & generate
Reusing state can reduce repeated work. Any charges follow the billing rules below.
Meshy API · text to motion
swift
Not verified
No model-specific prompt-cache contract or discounted cache rate documented.
How it works
Not collected
No model-specific prompt-cache contract or discounted cache rate documented.
Minimum reusable input
Not collected
No model-specific prompt-cache contract or discounted cache rate documented.
Lifetime & refresh
Not collected
No model-specific prompt-cache contract or discounted cache rate documented.
How to enable it
Not collected
No model-specific prompt-cache contract or discounted cache rate documented.
Usage fields
Not collected
No model-specific prompt-cache contract or discounted cache rate documented.
Billing rules
Not collected
No model-specific prompt-cache contract or discounted cache rate documented.
Limits & data boundaries
Not collected
No model-specific prompt-cache contract or discounted cache rate documented.
No verified cache rate for this endpoint. An empty rate is not a zero charge.
Caching reviewed 14 Oct 2026
Meshy API · apply motion
Not verified
No model-specific prompt-cache contract or discounted cache rate documented.
How it works
Not collected
No model-specific prompt-cache contract or discounted cache rate documented.
Minimum reusable input
Not collected
No model-specific prompt-cache contract or discounted cache rate documented.
Lifetime & refresh
Not collected
No model-specific prompt-cache contract or discounted cache rate documented.
How to enable it
Not collected
No model-specific prompt-cache contract or discounted cache rate documented.
Usage fields
Not collected
No model-specific prompt-cache contract or discounted cache rate documented.
Billing rules
Not collected
No model-specific prompt-cache contract or discounted cache rate documented.
Limits & data boundaries
Not collected
No model-specific prompt-cache contract or discounted cache rate documented.
No verified cache rate for this endpoint. An empty rate is not a zero charge.
Caching reviewed 14 Oct 2026
What the measurements say
No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.
Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.
The record behind the model
Why it is included
Qualified inference: the provider names two proprietary hosted motion models, exposes only mode selectors, and restricts deriving its service code. Reviewed official repositories do not expose corresponding weights. The exact checkpoint relationship and weight license are not publicly documented.
