typesafe-ai
Jev
TypeSafe AI System One decision model. Accepts shared state and typed questions, returning choices, scores, and boolean probabilities. Limits: 64,000 tokens total per request; 32,000 tokens for the state plus the longest question. No streaming or output-token limit.
text
Overview
- Type
- evaluation
- Context
- 32K
- Max output
- —
- Input / output
- text / text
API
Model identifier
typesafe-ai/jevProviders and live performance
Rolling Gateway metrics. Latency is time to first token; throughput is output tokens per second.
| Provider | Status | Latency | Throughput | Uptime 15m / 1h / 1d | Input | Output | Cache read / write | Discount | Regions | ZDR | No training |
|---|---|---|---|---|---|---|---|---|---|---|---|
| digitalocean | Operational | — | — | 100.00% / 100.00% / 100.00% | $0.04/M | $0.00/M | — / — | — | — | No | Yes |
| typesafe-ai | Operational | — | — | 100.00% / 100.00% / 99.99% | $0.04/M | $0.00/M | — / — | — | — | Yes | Yes |
Pricing
input
0.000000042
output
0
Capabilities
text
Supported parameters
No details published for this model.
Reasoning options
No details published for this model.
Metadata
type
evaluation
context window
32K
max output
—
released
Sep 15, 2026
zero data retention
some
no training
all
api specifications
v4