Tasks and inputs
Jev is listed for Structured Decisions. It accepts text and produces text. Use the publisher’s input format and preprocessing for your chosen deployment.
TypeSafe’s Jev evaluates many questions against shared text state through a System One interface; the latest alias currently resolves to Jev 1.13.
Pricing conditions: Input tokens are billed; output tokens are free. The source lists a 64K request budget and a 32K state-plus-longest-question budget.
Recorded modality support shows what this model can accept and produce. An undocumented modality is shown as unknown rather than assumed to be unsupported.
Accepts
Produces
Jev is TypeSafe’s System One model for evaluating questions against shared state. Text, JSON objects and arrays of text values can provide that state. Images, audio and video need preprocessing before they fit this interface. Its structured answer workflow should be evaluated as a decision component, not as a general conversational writer.
The current models page identifies Jev 1.13 and the pinned model ID jev-1.13.0. This directory entry follows jev-latest, so the selected version can change. For reproducible evaluations, record the returned version together with the state and questions. Check migration guidance before relying on an alias in a workflow with fixed acceptance criteria.
The documentation describes a 64K-token budget for the complete request and a separate 32K budget for state plus the longest question. Jev ingests the shared state once and evaluates questions in parallel. Packing questions into a request therefore needs to respect both limits.
The listed price is $0.042 per million input tokens, with free output tokens. This does not mean that a whole request is free. Published throughput and request limits can change, so measure capacity on your own account and handle rate-limit responses.
Test the same question at different state lengths and inspect the quality of the returned probability or decision. Include contradictory evidence and cases that should fall back to human review. Compare false-positive and false-negative costs at your chosen operating threshold. The linked TypeSafe page is the source for the current version, billing and limits.
Compare the model on the work you need to complete.
Jev is listed for Structured Decisions. It accepts text and produces text. Use the publisher’s input format and preprocessing for your chosen deployment.
Documented limits: 64K context. The listed route has starting rates of $0.042 input and $0.00 output per million tokens. Measure a completed task using the prompts, documents and tools your application will use. Include reasoning and retries in the result.
Use the model identifier and account requirements for the selected API route. Confirm its request limits and output format with one complete task before connecting a larger workflow.
These records share a directory category. Check the source card, output type and deployment requirements before treating a model as a replacement.
phocinae
Phocinae Largha 150M v1 from phocinae: Encoder decision model that answers typed questions (noul, choice, score) over text with calibrated probabilities, on CPU and GPU.
Nace AI
Drex 2.0 scores typed questions over text and returns probabilities. Its hosted route uses 2.0 for short states and falls back to 1.5 for longer requests.
Liquid AI
Liquid d1 returns typed binary decisions, class distributions or scores through Liquid AI’s decision API.
Nace AI
Drex 1.5 evaluates typed questions against a shared state and returns calibrated probabilities through the System One API.