anthropic
Jev Router vs Claude Fable 5.2
84.9 overall · $16.00 / 1M
// typesafe
Jev Router
typesafe/jev-router
reasoningtool callingaudio inputfile inputimage inputvideo input
Jev Router has no published list price with a 1M-token context window.
A reasoning, tool-calling model from typesafe, released Sep 25, 2026. LiveBench hasn't published a run for it, so this page carries measured price and specs only — no benchmark numbers.
- Input / 1M
- —
- Output / 1M
- —
- Context
- 1M
- LiveBench overall
- Not evaluated
Specs and pricing
| Input price USD per 1M prompt tokens | — |
|---|---|
| Output price USD per 1M completion tokens, reasoning included | — |
| Blended price 3:1 input:output | — |
| Cached input read Blank means not priced separately — not free | — |
| Cache write | — |
| Context window | 1,000,000 tokens |
| Max output | 64,000 tokens |
| Input modalities | audio, file, image, text, video |
| Tool calling | Yes |
| Extended reasoning | Yes |
| Knowledge cutoff | — |
| Listed | Sep 25, 2026 |
Compare Jev Router with
Benchmarked models at a similar price.
openai
Jev Router vs GPT-6.1 Terra
78.8 overall · $2.00 / 1M
moonshotai
Jev Router vs Kimi K3.1 Pro
68.7 overall · $4.00 / 1M
minimax
Jev Router vs MiniMax M3.1 Flash
63.7 overall · $0.131 / 1M
deepseek
Jev Router vs DeepSeek V4.1 Flash 1017
70.3 overall · $0.130 / 1M
meta
Jev Router vs Muse Spark Open
48.5 overall · $2.00 / 1M
Jev Router FAQ
What is the context window of Jev Router?
Jev Router accepts up to 1,000,000 tokens of context and can return up to 64,000 output tokens per response.
Does Jev Router support tool calling?
Yes — Jev Router supports tool (function) calling and exposes extended reasoning. It accepts audio, file, image, text, video input.
How does Jev Router score on benchmarks?
LiveBench has not published a run for Jev Router yet. Until it does, compare it on price and specs, or run your own evaluation on your own tasks.
What is the API model ID for Jev Router?
On OpenRouter the model ID is "typesafe/jev-router". It was listed on Sep 25, 2026.
How these numbers are produced
- Price and specs — provider list data from OpenRouter, refreshed every 15 minutes. “Blended” is a 3:1 input:output mix.
- Scores and ranks — LiveBench release 2026-11-06. Ranks count only models that have a published run; a blank means “not evaluated”, never “bad”.
- Cost per point — the measured dollars LiveBench spent on the run, divided by the score it earned.
Published benchmarks rank models on someone else's tasks. Before committing, see LLM & agent evaluation for building an eval on your own.