API & Modelsp95 latencyTail latency
Latency percentiles
Reporting round-trip time as p50, p95, and p99 rather than an average, because the tail is what a control loop feels.
- Category
- API & Models
- Also known as
- p95 latency, Tail latency
- Related terms
- 5
- Directory entries
- 15
- Docs
- docs.typesafe.ai
- Added
- 2026-10-12
Definition
An average latency hides the slow tail a caller actually experiences, so decision-system write-ups report percentiles: p50 for the typical case, p95 and p99 for the ones that hurt. A median that fits a loop says nothing about the requests that exceed its budget.
For Jev the number is dominated by input size, since there are no output tokens to generate, so the percentiles move with the state and the question set. Measure them on your own states; a published median is a different traffic mix.
Tagsapievaluation
Related terms
Definitions that connect to this one.
UsageThe response field reporting input and output token counts for a request, used for cost tracking.API & ModelsRate limitThe throughput caps — 250,000 tokens per second and 1,200 requests per minute — that return 429 when exceeded.API & ModelsBenchmark claimsTypeSafe's headline multipliers — 193.6x faster, 444.6x cheaper, a 238x lower input price — come from its own workflow comparisons.Evaluation & TrainingRepeatabilityHow stable answers are across repeated evaluations, measured separately from accuracy and reported as probability standard deviation.Evaluation & TrainingContext windowThe 64k-token budget covering state plus all questions, with a 32k sub-budget for state plus the longest question.API & Models
From the Jev directory
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
The model card for jev-1.13.0: $42 per billion input tokens with free output, a 64k context, 250k tokens per second, and how to list the models your account can call.
Jev Guides & ArticlesDocs#official#docs#models
Official
A zero-shot text classification service over plain HTTP: send text and a list of labels, get the best-fitting label and a calibrated probability per label, with Jev as the default and fast tier.
Jev Integrations & Adapters#community#api#classification
Community
A router playground that serves several System One decision models from one place: Jev, Perplexity's Decider, Bespoke Nimble, Mercury Decide, Clef, Kev 4B, and Decider 2B, with three of them free.
Jev Integrations & Adapters#community#router#api
Community
A third-party developer reference for the Jev API: primitives, quickstart curl, SDK pointers, and published latency and pricing figures.
Jev Tools & CLIsDocs#community#docs#api
Community
A public Jev API funded by creator fees from a token, with a playground, docs, use cases, and a smart treasury dashboard.
Jev Tools & CLIsPlayground#community#playground#api
Community
9 more matching entries in the full directory.
From the Jev community
Posts from builders shipping with Jev right now.