Morph · Rate Limits

Morph Labs Rate Limits

Morph enforces per-account rate limits that scale with the subscription tier. The Free tier has low rate limits; Starter, Pro, and Scale progressively raise them, with Scale described as having practically no rate limits. Limits are expressed as requests and tokens per minute against the OpenAI-compatible endpoints, and monthly credit allotments cap overall usage. Morph Cloud sandboxes have separate concurrency and resource limits. Specific per-tier values are not reconciled in this artifact.

Morph Labs Rate Limits is the machine-readable rate-limit profile for Morph on the APIs.io network, conforming to the API Commons Rate Limits specification.

It captures 4 rate-limit definitions, measuring requests, tokens, credits, and instances.

The profile also includes 2 backoff/retry policies defined and response codes documented for throttled.

Tagged areas include AI, Code Editing, Fast Apply, Embeddings, and Sandboxes.

4 Limits Throttle: 429
AICode EditingFast ApplyEmbeddingsSandboxesRate LimitingQuotasThrottling

Limits

Requests Per Minute (RPM) account
requests
see provider documentation
Scales with subscription tier (Free is low; Scale is practically unlimited).
Tokens Per Minute (TPM) account
tokens
see provider documentation
Scales with subscription tier.
Monthly Credits account
credits
250K Free / 3M Starter / 10M Pro / 80M Scale
Bundled monthly credit allotment caps overall usage across models.
Morph Cloud Sandboxes account
instances
see provider documentation
Separate concurrency and compute resource limits for Infinibranch instances.

Policies

Tiered Limits
Limits raise as accounts move from Free to Starter, Pro, and Scale subscriptions.
Backoff Strategy
Clients should implement exponential backoff with jitter and honor Retry-After.

Sources