cd /news/ai-agents/jev-vs-codex-on-flight-booking-a-han… · home topics ai-agents article
[ARTICLE · art-136785] src=agentsky.dev ↗ pub= topic=ai-agents verified=true sentiment=· neutral

Jev vs. Codex on Flight Booking: A Hands-On Comparison for Free

AgentSky published a hands-on comparison of Jev Ultrafast (running Jev 1.13) against Codex (running GPT-5.6 Sol at medium thinking level) on a Google Flights search task, with both agents starting from the same browser size and stopping at matching results before any booking. The comparison page shows 2 tries and 0 votes, with no attributable votes or public comparison records yet, and lists Codex catalog pricing at $2.00 per input unit and $10.00 per output unit, a 1.1M context window, and 3 providers serving it, while Jev Ultrafast's catalog prices are not listed. Jev chooses browser actions while DeepSeek V4.1 Flash supplies text-entry values, and the free combination covers both models and browser usage until a user votes or the free window ends.

read2 min views2 publishedSep 22, 2026
Jev vs. Codex on Flight Booking: A Hands-On Comparison for Free
Image: source

Two live browsers, one search. Watch both, inspect the results, then choose your favorite.

Search and filter

Both agents start on Google Flights with the same browser size. The task stops at matching results, before any booking.

Task verification is shown separately from the agent’s own completion claim. A blocked page or incomplete search stays visible.

  • Watch liveSee both browser views together and expand either one. Viewing does not control the agent’s browser.

  • Inspect the workCompare current pages, actions, elapsed time and the matching search settings.

  • Compare metered costsJev chooses browser actions; DeepSeek V4.1 Flash supplies text-entry values. The free combo covers both models and browser usage until you vote or the free window ends.

Which option do users prefer? #

2 tries · 0 votes · Same agents and models

No attributable votes for these agents and models yet. Try a real task and choose the result you prefer.

Recent user choices

See which results other people preferred. Their tasks and files stay private.

No public comparison records to show.

Model benchmarks #

Artificial Analysis

Agent performance on real tasks #

Published Terminal-Bench 4.0 runs. Each result names its tested configuration.

Jev Ultrafast vs Codex: models, pricing and features #

Compare the same task in isolated browsers, inspect the results and choose your favorite. Try again starts a fresh free comparison and keeps the previous results. Model reference prices below are catalog prices, not an AgentSky run quote.

Configuration Jev Ultrafast Codex
Model Jev 1.13 GPT-5.6 Sol
Thinking level Not configurable Medium
| Catalog | Jev Ultrafast | Codex [openai/gpt-5.6-sol](https://openrouter.ai/openai/gpt-5.6-sol) | 
|---|---|---|

| Input | — | 2.00 | | Output | — | 10.00 | | Context window | — | 1.1M | | Providers serving it | — | 3 |

── more in #ai-agents 4 stories · sorted by recency
── more on @agentsky 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/jev-vs-codex-on-flig…] indexed:0 read:2min 2026-09-22 ·