Jev glossary
API & Models
Exponential backoff
The retry strategy the docs recommend for 429 and 529 responses: wait longer after each attempt instead of retrying immediately.
- Category
- API & Models
- Also known as
- None
- Reading time
- 1 min
- Related terms
- 3
- Directory entries
- 2
- Docs
- docs.typesafe.ai
- Added
- 2026-09-24
Definition
When a request hits a rate limit or an overloaded service, retrying immediately makes the problem worse. The API reference says to back off and retry after a short delay, and the SDKs do this automatically.
Handling backoff yourself is only necessary when calling the HTTP API directly, in which case the docs point at the same policy the SDKs use.
Tagsapireliability
Related terms
Definitions that connect to this one.
Retry policyThe SDK configuration for retrying failed requests: attempt count, retryable statuses, backoff, and retry-header handling.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 & Models
From the Jev directory
Directory entries that go deeper on this term.
The raw HTTP contract behind every SDK: POST a state plus typed noul, choice, and score questions to /v1/systemone, and get one answer per question, with error codes and retry guidance.
Jev Guides & ArticlesDocs#official#docs#api
Official
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
From the Jev AI model community
Posts from builders shipping with Jev right now.