Fast, Cheap Agent Decisions TypeSafe launched Jev, a specialized "System One" model, on September 15, 2026 alongside disclosure of a $40 million seed round, claiming end-to-end response times of 70 ms to 500 ms versus 3 s to 329 s for frontier models. TypeSafe's own evaluations put Jev at 40x to 200x faster on System One queries, 0.114 s per workflow task versus 8.566 s for LLMs (193.6x slower), and $0.000081 per task versus $0.013880 (444.6x more expensive), with input tokens priced at $0.042 per million and free output tokens. TypeSafe reports 67.8% average accuracy across four workflows at $0.0004 per workflow, against GPT-5.6 Terra at 67.9% for $0.0304 and Claude Sonnet 5 at 67.8% for $0.1174, and says Jev returns a calibrated probability with every answer and zero hallucinations guaranteed by the output schema, a figure it did not measure. Fast, Cheap Agent Decisions This post was originally published on the Akka blog https://akka.io/blog/fast-cheap-agent-decisions . Jev has only been available to the public for about a week unveiled September 15th, 2026 , but it’s already created a ton of excitement and discussion within the AI community. TypeSafe https://typesafe.ai made Jev available through limited, early access at the same time they disclosed their $40 million seed round. Let’s strip away the hype and talk about what Jev is, and what it isn’t. When our agentic code submits a prompt to an LLM, it can include a description of available tools, context, and conversation history. The typical pattern is to stream text into a model and we get the answer streamed back out. If we want more structured replies, we can give these LLMs a schema and tell them that their output must conform to that schema. This structured output can be anything from data queried from a customer’s account to a set of product recommendations or an itinerary for a vacation based on weather forecasts and traveler preferences. Sometimes this output schema is extremely focused, like asking specific questions. Is there PII exposed anywhere in this text? Is the sentiment in the text negative or positive? Does the supplied context refer to a tech support issue or is it an account query? Narrowing down the potential output of an LLM to these extremely focused questions dramatically increases accuracy and reduces hallucinations. However, using a general-purpose LLM to answer these questions is extremely inefficient. While you could technically use a jumbo jet at runway taxi speed to commute from home to the office, it’s slow, inefficient, and costly. Overkill has a cost and many of us are using all-purpose LLMs when we could be using something more focused and efficient. This is where Jev comes in. It’s a special kind of model with its own interface style. It doesn’t stream text bi-directionally like LLMs. Instead, you ask it questions based on some state and it gives you answers and their probability scores. Performance and cost figures TypeSafe published for Jev TypeSafe published these figures with the Jev launch on September 15, 2026. All of them come from TypeSafe’s own evaluations and demos. | Claim | Jev | Comparison, as TypeSafe states it | |---|---|---| | End-to-end response time | 70 ms to 500 ms | 3 s to 329 s for frontier models | | Speed on System One queries | 40x to 200x faster | The same level of frontier intelligence | | Workflow evaluation, time per task | 0.114 s | 8.566 s for LLMs, 193.6x slower | | Workflow evaluation, cost per task | $0.000081 | $0.013880 for LLMs, 444.6x more expensive | | Accuracy, average of four workflows | 67.8% at $0.0004 per workflow | GPT-5.6 Terra 67.9% at $0.0304; Claude Sonnet 5 67.8% at $0.1174 | | Input token price | $0.042 per million $42 per billion | $0.20 to $10 per million | | Input price against Claude Fable 5.1 | 238x lower | $10 per million | | Output token price | Free | About 5x the input price | | Hallucinations and type errors | Zero, guaranteed by the output schema | LLMs hallucinate and make type errors | | Confidence | A calibrated probability with every answer | Overconfident and inconsistent, even when prompted for confidence | | Doom demo | 10 queries per second for about $7 per hour | None given | TypeSafe states that the 193.6x and 444.6x figures are on the higher end of real-world gains. The zero-hallucination figure follows from the output schema and was not measured. The LLM error rates TypeSafe compares against come from OpenRouter traffic. Sources: TypeSafe launch post https://typesafe.ai/blog/introducing-system-one-models-and-jev , typesafe.ai https://typesafe.ai , evals.typesafe.ai https://evals.typesafe.ai/ . Let’s take a look at a classic use case for the kind of interrogations Jev makes fast and cheap. The user’s original prompt looks like this: “Hi, I ordered the blue jacket on the 9th and it still hasn’t shipped. I’ve emailed twice already. If it’s not out the door by Friday I want a refund. Order 48213.” Using a traditional LLM, we might be able to get some actionable routing or planning decisions out of this. What we really want are some answers to discrete questions, and then our agent can take the right actions based on those answers with high confidence. | Question | Allowed Answers | Jev’s Answer | Probability | |---|---|---|---| | What is this about? | Shipping , returns, billing, product question, other | Shipping | 0.94 | | How is the customer feeling? | Calm, frustrated , angry | Frustrated | 0.81 | | Is this a repeat contact? | Yes , no | Yes | 0.97 | | Is the customer threatening to leave or dispute? | Yes , no | Yes | 0.88 | | Does this need a human, or can automation handle it? | Human , automation | Human | 0.76 | | Which queue? | Tier 1, tier 2, retention | Retention | 0.71 | | Is there an order number in the message? | Yes , no | Yes | 0.99 | | Priority | Low, medium, high | High | 0.83 | Jev does one thing: answer questions. It does this quickly and cheaply. If we want to interrogate a state based on a user’s input, then this kind of Q&A is the right optimization. Take a look at the question, “Is there an order number in the message?”. Jev-style interactions don’t let us extract the order number from the message. Instead, we can only ask questions with a fixed number of potential responses. That limited inference target area is what makes this kind of fast and cheap interrogation possible. A pretty popular pattern is to interrogate the state and message and, based on the answers we get, we decide whether we need to make a full relatively slow and costly call to an LLM. We might use this to extract an order ID only if our interrogation is confident there is one in the message. If we are going somewhere on a nice day, we can choose to ride a bike, otherwise, we can use the massive transport truck. Asking questions in Akka In the Akka SDK https://akka.io/platform/sdk , interaction with models is managed via an effects API. Sending a system prompt, user prompt, and other context to a model and getting a stream of text back is I/O and not a “pure” function. The same applies to asking Jev or technically anything that talks SystemOne, which isn’t yet a standardized protocol questions, though talking to Jev is always synchronous. Here’s how you can easily use the effects API available to the public soon in an upcoming SDK release to have your agent ask Jev questions: public Effect