TypeSafe / typesafe/jev
Jev - access through LLMTR
Jev evaluates typed questions against a state you supply and returns a structured answer for each one: a choice from your options, a score along your levels, or the probability that a statement is true. It generates no free text, so there is nothing to parse, and every answer arrives with its own probability distribution. The Structured Decisions documentation covers the request shape, the three question types and the limits.
Technical specifications
| Canonical ID | typesafe/jev |
|---|---|
| Provider | TypeSafe |
| Context window | 32,000 tokens |
| Operations | SYSTEM_ONE |
| Modalities | text |
Pricing
An 8% platform margin applies to credit top-ups; model usage prices are not separately marked up.
| Operation | Metric | Unit | Price |
|---|---|---|---|
| SYSTEM_ONE | INPUT_TEXT | PER_1M_TOKENS | $0.042000 |
| SYSTEM_ONE | OUTPUT_TEXT | PER_1M_TOKENS | Not available |
Example usage
With existing OpenAI SDK flows, change only the base URL and model identifier.
curl https://llmtr.com/v1/chat/completions -H "Authorization: Bearer llmtr-your_key" -H "Content-Type: application/json" -d '{"model":"typesafe/jev","messages":[{"role":"user","content":"Hello"}]}'Guides about this model
- What is Jev? TypeSafe's choice-based decision model for browser agents - How TypeSafe's Jev model makes choice-based decisions, how jev-ultrafast applies that to browser agents, and the speed difference measured in the source project's own documentation, limits included.
- Running jev-ultrafast's text-generation step through LLMTR - Environment variable configuration, the actual request shape, and model-selection criteria for running jev-ultrafast's TYPE_TEXT step through LLMTR.
Related models
- Gemma 4 llmtr/gemma-4
- Qwen 3.6 35B-A3B llmtr/qwen3-6-35b
- Trendyol Asure 12B llmtr/trendyol-asure-12b
- Magibu 11B v8 llmtr/magibu-11b-v8
- Muse Glimmer 30B (Turkey) llmtr/muse-glimmer-30b-tr
- EmbeddingGemma 300M llmtr/embeddinggemma-300m
- Qwen 3.5 4B llmtr/qwen3-5-4b
- GPT-6 Astra openai/gpt-6-astra