Jev glossary
API & ModelsRetryPolicy
Retry policy
The SDK configuration for retrying failed requests: attempt count, retryable statuses, backoff, and retry-header handling.
- Category
- API & Models
- Also known as
- RetryPolicy
- Reading time
- 1 min
- Related terms
- 4
- Directory entries
- 2
- Docs
- docs.typesafe.ai
- Added
- 2026-09-24
Definition
Both official SDKs retry automatically with a default policy and expose a RetryPolicy type for tuning attempts, retryable statuses, and backoff. The docs point at 429 and 529 as the statuses worth retrying.
Using a default policy is the recommended path for rate limits, because it already implements the exponential backoff the API expects and reads the retry-after header when the response carries one.
Tagsapisdk
Related terms
Definitions that connect to this one.
Exponential backoffThe retry strategy the docs recommend for 429 and 529 responses: wait longer after each attempt instead of retrying immediately.API & ModelsRate limitThe throughput caps (250,000 tokens per second and 1,200 requests per minute) that return 429 when exceeded.API & ModelsAPI errorThe four documented failure statuses (401, 422, 429, and 529), with retry guidance for the last two.API & ModelsClient SDKThe official typed clients for the API (Python and JavaScript/TypeScript), with retries and inferred answer types.API & Models
From the Jev directory
Directory entries that go deeper on this term.
Usage guide for typesafe-sdk: sync and async clients, uv and pip installs, and one request mixing Noul, Choice, and Score questions with answers grouped by type.
Jev Repos & SDKsDocs#official#docs#sdk
Official
Quickstart for @typesafe-ai/sdk on Node 20+: answer types inferred from your questions, a choice() helper, and one systemOne call to classify a support ticket.
Jev Repos & SDKsDocs#official#docs#sdk
Official
From the Jev AI model community
Posts from builders shipping with Jev right now.