# Jev > Run Jev by typesafe online or via API. $0.042/M input, output free, no setup. **URL:** https://inference.sh/apps/typesafe/jev **Last updated:** 2026-10-15 --- TypeSafe's System One model. Send text and images with typed questions (choice, score, noul); get calibrated, structured answers your code can act on directly. - app: `typesafe/jev` - maker: [typesafe](https://inference.sh/apps/typesafe.md) - category: [decision](https://inference.sh/apps/category/decision.md) - tasks: [classification](https://inference.sh/apps/tag/classification.md), [routing](https://inference.sh/apps/tag/routing.md), [moderation](https://inference.sh/apps/tag/moderation.md), [vision](https://inference.sh/apps/tag/vision.md) - price: $0.042/M input, output free - runs via: api, javascript and python sdk, belt cli, mcp ## jev API Guide ### About typesafe's system one model. send text and images with typed questions (choice, score, noul); get calibrated, structured answers your code can act on directly. ### Get an API Key Create one in [settings → api keys](https://app.inference.sh/settings/keys). The examples read it from `INFERENCE_API_KEY`. ```bash export INFERENCE_API_KEY="inf_your_key" ``` ### 1. Calling the API #### Install the Client ```bash pip install inferencesh ``` #### Run and Get Result Submit a request and wait for the final result. ```python import os from inferencesh import inference client = inference(api_key=os.environ["INFERENCE_API_KEY"]) ## version @60sdc5x7 pinned result = client.run({ "app": "typesafe/jev@60sdc5x7", "input": { "state": "Our API started returning 500 errors 20 minutes ago and we can't process any customer orders.", "choices": [ { "id": "choices_1", "instructions": "instructions", "options": [ { "name": "options_1" }, { "name": "options_2" } ] } ], "scores": [ { "id": "scores_1", "instructions": "instructions", "levels": [ "levels_1", "levels_2" ] } ], "nouls": [ { "id": "nouls_1", "instructions": "instructions" } ] } }) print(result["output"]) ``` #### Stream Live Updates Get real-time progress updates as the task runs. ```python import os from inferencesh import inference client = inference(api_key=os.environ["INFERENCE_API_KEY"]) ## version @60sdc5x7 pinned ## stream=True yields updates as they arrive for update in client.run({ "app": "typesafe/jev@60sdc5x7", "input": { "state": "Our API started returning 500 errors 20 minutes ago and we can't process any customer orders.", "choices": [ { "id": "choices_1", "instructions": "instructions", "options": [ { "name": "options_1" }, { "name": "options_2" } ] } ], "scores": [ { "id": "scores_1", "instructions": "instructions", "levels": [ "levels_1", "levels_2" ] } ], "nouls": [ { "id": "nouls_1", "instructions": "instructions" } ] } }, stream=True): if update.get("progress"): print(f"progress: {update['progress']}%") if update.get("output"): print(f"output: {update['output']}") ``` #### Run in the Background Start the task and get its id back right away, then check on it with `GET /tasks/{id}`. It is done when `status` is 10 (completed), 11 (failed) or 12 (cancelled). ```python import os from inferencesh import inference, TaskStatus client = inference(api_key=os.environ["INFERENCE_API_KEY"]) ## returns as soon as the task is created task = client.run({ "app": "typesafe/jev@60sdc5x7", "input": { "state": "Our API started returning 500 errors 20 minutes ago and we can't process any customer orders.", "choices": [ { "id": "choices_1", "instructions": "instructions", "options": [ { "name": "options_1" }, { "name": "options_2" } ] } ], "scores": [ { "id": "scores_1", "instructions": "instructions", "levels": [ "levels_1", "levels_2" ] } ], "nouls": [ { "id": "nouls_1", "instructions": "instructions" } ] } }, wait=False) ## later: read its current state state = client.tasks.get(task["id"]).data if state["status"] == TaskStatus.COMPLETED: print(state["output"]) ``` ### 2. Files #### Automatic Upload ```python ## local file paths are automatically uploaded result = client.run({ "app": "typesafe/jev@60sdc5x7", "input": { "image": "/path/to/local/image.png", # detected & uploaded "audio": "https://example.com/audio.mp3", # url passed through } }) ``` #### Manual Upload ```python ## upload and get a hosted URL file = client.files.upload("/path/to/file.png") print(file.uri) # https://cloud.inference.sh/... ``` ### 3. Schema #### Input - **model** (string): Model name or alias: `jev-latest`, `jev-preview`, or a pinned version such as `jev-1.13.0`. Pin a version if you tuned thresholds against it. - **state** (any): The content to evaluate: a string, or a JSON object / array of related context (messages, records, a policy). Every question sees the same state. May be empty when `images` carries the content. Send only what the questions need; unrelated detail costs accuracy. - **choices** (array): Choice questions: pick one option from a set. - **scores** (array): Score questions: place the state on ordered levels. - **nouls** (array): Noul questions: probability that the answer is yes. - **images** (array): Up to 8 images (PNG or JPEG, or any format Pillow reads) the questions are about. Sent as `{"images": [...], "text": state}`, so questions can name `images[0]`. Downsized to 1568 px on the long side; one under 280 x 280 is padded. Preview feature upstream: formats and accuracy may change. #### Output - **choices** (object): Choice answers by question id. - **input_tokens** (integer): Input tokens (billed). - **model** (string): The versioned model that answered, e.g. `jev-1.13.0`. - **nouls** (object): Noul answers by question id. - **output_tokens** (integer): Output tokens (free upstream). - **scores** (object): Score answers by question id. ## other decision apps - [Decision 3.0 d3 27B](https://inference.sh/apps/vllm-sr/d3.md): GPU time, billed per second - [Decision 3.0 d3-flash 9B](https://inference.sh/apps/vllm-sr/d3-flash.md): GPU time, billed per second - [Decision 3.0 d3-mini 4B](https://inference.sh/apps/vllm-sr/d3-mini.md): GPU time, billed per second - [Decision 3.0 d3-nano 2B](https://inference.sh/apps/vllm-sr/d3-nano.md): GPU time, billed per second - [Decision 3.0 d3-lite 0.8B](https://inference.sh/apps/vllm-sr/d3-lite.md): GPU time, billed per second ## faq ### how much does Jev cost? $0.042/M input, output free. you pay per run from your inference shell credits. no subscription is required. ### how do I run Jev via api? call typesafe/jev with the javascript or python sdk, the rest api, or `belt app run typesafe/jev` from a terminal. the api reference on this page lists every input. ### who makes Jev? Jev is made by typesafe and runs on inference shell. every typesafe app is listed at https://inference.sh/apps/typesafe. ### can my agent use Jev? yes. agents call it as a tool through the inference shell mcp server (https://api.inference.sh/mcp), the belt cli or the sdk, and pay per run like you do. ### what are the alternatives to Jev? other decision apps on inference shell include Decision 3.0 d3 27B, Decision 3.0 d3-flash 9B, Decision 3.0 d3-mini 4B, Decision 3.0 d3-nano 2B. they run through the same api, so switching is a one-line change.