# JEV-9B > Run JEV-9B by autotrust online or via API. from $0.00055833/sec, no setup. **URL:** https://inference.sh/apps/autotrust/jev-9b **Last updated:** 2026-11-06 --- AutoTrust's small open decision model with vision. Send text and up to 8 images with typed questions (choice, score, yes/no); get a calibrated probability for every answer. - app: `autotrust/jev-9b` - maker: [autotrust](https://inference.sh/apps/autotrust.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), [open weights](https://inference.sh/apps/tag/open-weights.md) - price: from $0.00055833/sec - runs via: api, javascript and python sdk, belt cli, mcp ## jev-9b API Guide ### About autotrust's small open decision model with vision. send text and up to 8 images with typed questions (choice, score, yes/no); get a calibrated probability for every answer. ### 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 @74fsma5a pinned result = client.run({ "app": "autotrust/jev-9b@74fsma5a", "input": { "state": "Seller title: wireless earbuds, barely used", "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 @74fsma5a pinned ## stream=True yields updates as they arrive for update in client.run({ "app": "autotrust/jev-9b@74fsma5a", "input": { "state": "Seller title: wireless earbuds, barely used", "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": "autotrust/jev-9b@74fsma5a", "input": { "state": "Seller title: wireless earbuds, barely used", "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": "autotrust/jev-9b@74fsma5a", "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 - **state** (any): The text to evaluate: a string, or a JSON object / array of related context (messages, records, a policy). Every question sees the same state and images. May be empty when `images` carries the content. Input over the model's token limit is rejected, never truncated. - **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 the questions are about, placed before the state. Large images cost more tokens and time; about 448 px on the long side is enough for most decisions. #### Output - **choices** (object): Choice answers by question id. - **input_tokens** (integer): Prompt tokens, summed over the questions. Image tokens are included. - **model** (string): The model that answered: `autotrust/JEV-9B`. - **nouls** (object): Noul answers by question id. - **scores** (object): Score answers by question id. ## other decision apps - [AutoTrust-JEV-27B v1.1](https://inference.sh/apps/autotrust/jev-27b-v1-1.md): from $0.00055833/sec - [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 ## faq ### how much does JEV-9B cost? from $0.00055833/sec. you pay per run from your inference shell credits. no subscription is required. ### how do I run JEV-9B via api? call autotrust/jev-9b with the javascript or python sdk, the rest api, or `belt app run autotrust/jev-9b` from a terminal. the api reference on this page lists every input. ### who makes JEV-9B? JEV-9B is made by autotrust and runs on inference shell. every autotrust app is listed at https://inference.sh/apps/autotrust. ### can my agent use JEV-9B? 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-9B? other decision apps on inference shell include AutoTrust-JEV-27B v1.1, Decision 3.0 d3 27B, Decision 3.0 d3-flash 9B, Decision 3.0 d3-mini 4B. they run through the same api, so switching is a one-line change.