The OpenAI Model Spec is OpenAI's specification for how its models should behave, published December 18, 2025 under a Creative Commons CC0 1.0 (public domain) dedication. It functions as the behavior-governing document for GPT-5.x and Codex, defining a four-level chain of command and a set of red-line principles that cannot be overridden.
Chain of command
The Spec orders instructions into four levels of authority. Each level can be overridden only by the levels above it.
| Level | Source | Can be overridden by |
|---|---|---|
| Root | Model Spec only | Nothing |
| System | OpenAI via system messages | Root only |
| Developer | API customers | Root, System |
| User | End users | Root, System, Developer |
Red-line principles
The Spec states that models must never facilitate WMD creation, terrorism, child abuse, mass surveillance, targeted manipulation, or undermining human autonomy. These principles sit above the chain of command and cannot be overridden by system, developer, or user instructions.
The red-lines prohibit WMD facilitation but do not specifically address lethal autonomous weapons (Autonomous Weapons). The Spec also addresses sycophancy and hallucination as failure modes the model should avoid (Sycophancy and Hallucination).
Companion methodology essay
OpenAI published "Inside our approach to the Model Spec" on April 23, 2026, a methodology essay describing the process by which the Spec is developed, balanced against safety, user-freedom, and accountability trade-offs, and updated as AI systems advance. The essay presents the Model Spec as a public framework, released under CC0, that other developers can adopt and that civil society can comment on, rather than a closed internal policy document.
It also supplies structural detail the Spec itself does not state. The Spec's contents divide into hard rules — non-overridable root- or system-level boundaries, "mostly prohibitive," covering catastrophic risk, direct physical harm, illegality, and undermining the chain of command — and defaults, overridable starting points split between implicitly steerable guideline-level defaults such as tone and style, and user-level defaults such as truthfulness and objectivity that can be overridden only by explicit instruction, so that a change of factual stance stays "transparent and legible." OpenAI states its restraint on hard rules by analogy: because it expects AI "to become a foundational technology for society, analogous to basic internet infrastructure," it imposes rules limiting intellectual freedom "only when we believe they are necessary."
The essay is also explicit that the Spec's preamble is not an instruction to the model — "Benefiting humanity is OpenAI's goal, not a goal we want our models to pursue autonomously" — on the reasoning that training models to select instructions by OpenAI's own view of social good "would be in the position of adjudicating morality at a very broad level." It records four reasons production models diverge from the Spec (training lagging Spec updates; training inadvertently teaching inconsistent behavior, treated as a serious bug; incomplete coverage of the behavior space; and generalization differing from intent, which deliberative alignment mitigates without solving), states that the Spec is drafted to sit "around 0-3 months ahead of the present," and announces Model Spec Evals, a scenario-based suite measuring compliance by Spec section across models.
Provenance
The Model Spec is OpenAI's behavior-specification document for its frontier models and is described by OpenAI as the governance document for those systems (OpenAI). It is OpenAI's counterpart to Anthropic's Constitutional AI and represents the behavior-specification layer within broader AI Safety Frameworks.