Model Metadata
- name
- GPT-6 Cyber
- description
- Cybersecurity model for finding and validating exploitable vulnerabilities in authorized security research
- family
- gpt
- open weights
- No
- release date
- 2026-11-05
- modalities
- input: text, image/jpeg, image/png, image/gif, image/webp; output: text
- capabilities
- tools: supported: Yes; reasoning: supported: Yes; temperature: No; top_p: No; top_k: No
- limit
- context: 1,050,000; input: 922,000; output: 128,000
Provider Variants 1
OpenAI gpt-6-cyber
Context 1,050,000 · Output 128,000
- name
- GPT-6 Cyber
- description
- Cybersecurity model for finding and validating exploitable vulnerabilities in authorized security research
- family
- gpt
- open weights
- No
- release date
- 2026-11-05
- modalities
- input: text, image/jpeg, image/png, image/gif, image/webp; output: text
- capabilities
- tools: supported: Yes; reasoning: supported: Yes; effort: low, medium, high, xhigh, max; cache: implicit: ttl: 30m, 12h; min_tokens: 1,024; explicit: ttl: 30m, 12h; max_breakpoints: 4; min_tokens: 1,024; structured_output: Yes; temperature: No; top_p: No; top_k: No; system_updates: Yes; effort_updates: No; store: Yes; prompt_cache_key: Yes
- limit
- context: 1,050,000; input: 922,000; output: 128,000
- id
- gpt-6-cyber
- canonical id
- openai/gpt-6-cyber
- type
- chat
- last updated
- 2026-11-05
- api
- responses: base_url: https://api.openai.com/v1; sdk: aisdk: @ai-sdk/openai; opencodeai: @opencode/ai/providers/openai/responses; capabilities: tools: strict: Yes; choice: auto, none, required, tool; search: Yes; freeform: text, lark, regex; updates: add, remove, replace
- recommended api
- responses