OrcaRouter 发布 OrcaCyber Zero 1.5 安全模型，支持 1M 上下文

OrcaRouter has released OrcaCyber Zero 1.5, a model for authorized vulnerability research. The model is the successor to OrcaCyber Zero 1.0, which shipped on September 17, 2026. OrcaCyber Zero 1.5 is a post-trained Orca model for vulnerability reproduction, exploit development and penetration testing. It ships with a 1M-token context window, native function calling and structured outputs. For security teams, this model brings a simple message: fewer reports, more validated and fixed vulnerabilities.

TL;DR

Size: Parameter count not disclosed. 1M-token context, 128K max output, text in and text out; Runs on: Hosted API only through OrcaRouter. No weights, no quantized variants, hardware not disclosed; Performance: Vendor-reported scores are near ceiling on cyber benchmarks and strong on coding; Best: 100% on Cybench (39/39 tasks, unrestricted agent execution); Worst: 76.5% on SWE-bench Pro V2, its lowest published score; Bottom line (best): Top-tier cyber scores at $3.00 / $7.50 per 1M tokens; Bottom line (worst): Every number is self-reported, and CVE-Bench used only 24 evaluable tasks

What is OrcaCyber Zero 1.5?

OrcaCyber Zero 1.5 is a frontier cybersecurity model and the successor to Zero 1.0. Orca team states that it has post-trained for security research and authorized security engineering. Listed uses include vulnerability reproduction, exploit development, penetration testing, security auditing and cyber reasoning.

The 3 design goals:

Find what others miss: unknown flaws like RCE, sandbox escapes, auth bypasses, privilege escalation and attack chains; Go beyond detection: reason through attack paths, challenge its own hypotheses and rank flaws by demonstrable exploitability; Built for autonomous agents: 1M-token context, native tool calling and extended reasoning for large codebases

How does OrcaCyber Zero 1.5 perform on benchmarks?

The model page lists 4 vendor-reported results, last evaluated October 10, 2026:

Cybench: 100% (39/39, unrestricted agent execution); CVE-Bench: 95.8% (23/24 evaluable tasks); HumanEval+: 93.9%; SWE-bench Pro V2: 76.5%

Cybench contains 40 professional CTF tasks, so the 100% covers 39 of them. CVE-Bench is built on 40 critical-severity web CVEs. Orca’s 95.8% covers a 24-task evaluable subset. The SWE-bench Pro V2 score is not directly comparable with standard SWE-bench Pro results.

How does it compare with other cyber models?

All competitor figures come from each vendor’s own announcement. None are independent replications.

How do developers access OrcaCyber Zero 1.5?

The model uses an OpenAI-compatible API. Developers set base_url to https://api.orcarouter.ai/v1 and call orca/orcacyber-zero-1.5.

Access is gated to the Security Research tier. Orca lists an engagement, a passkey and accepted terms as requirements. The tier targets trusted security researchers, red teams and authorized testing.

Pricing is $3.00 per 1M input tokens and $7.50 per 1M output tokens. Cache reads cost $0.75 per 1M tokens. Over the past 7 days, p50 time-to-first-token was 500 ms and p95 was 2.36 s. That sample is small, at 1.3K tokens of traffic.

Zero 1.0 recorded a 3.43 s p50 over a much larger traffic window. The 2 latency figures are not a clean comparison.

Key Takeaways

OrcaCyber Zero 1.5 is a gated, 1M-context cybersecurity model on OrcaRouter; It reports 100% on Cybench and 95.8% on a 24-task CVE-Bench subset; Pricing is $3.00 / $7.50 per 1M tokens, far below Mythos Preview’s $25 / $125; The 98% CyberGym claim belongs to Zero 1.0 inside Orca’s harness; All results are vendor-reported, with no technical report yet

Asif Razzaq

Asif RazzaqSakana AI’s LLM Peer Review System Catches 73% of Core-Claim Errors; Asif RazzaqMicrosoft AI Releases Microsoft-Decision-1: A Qwen3.5-9B Decision-Scoring Model; Asif RazzaqNace AI Open-Sources Drex 1.5: A 9B Decision Model That Scores Options, Not Text; Asif RazzaqAlibaba Qwen Releases Qwen-Image-2.1-Turbo, an 8-Step 7B Image Model