Documentation — Spybara

Files

guides
- agents
  - guardrails-approvals.md
- ip-allowlist.md
- safety-checks
  - cybersecurity.md
- your-data.md
models
- all.md
models.md

guides/agents/guardrails-approvals.md +25 −0

Details

221 221

222If you need checks around every custom tool call in a manager-style workflow, don't rely only on agent-level input or output guardrails. Put validation next to the tool that creates the side effect.222If you need checks around every custom tool call in a manager-style workflow, don't rely only on agent-level input or output guardrails. Put validation next to the tool that creates the side effect.

223 223

224## Review cybersecurity actions before execution

225

226For authorized cybersecurity workflows, evaluate each sensitive tool call

227before it executes. Use tool guardrails and approval interruptions to enforce

228the written engagement scope at the boundary where side effects occur:

229

2301. Check the proposed target, action, tool arguments, calling identity, and

231 engagement window against the approved scope.

2322. Give a separate policy component or reviewer the exact proposed action and

233 only the context needed to evaluate it.

2343. Deny out-of-scope hosts, credential theft, persistence, data exfiltration,

235 destructive changes, production access, and attempts to bypass policy.

2364. Pause ambiguous or high-risk actions for explicit human approval before the

237 tool runs.

2385. Enforce independent filesystem, network, identity, and project boundaries,

239 record decisions and execution outcomes, and fail closed if review times out

240 or becomes unavailable.

241

242Responses API and Agents SDK applications don't automatically inherit

243[Codex Auto-review](https://developers.openai.com/codex/sandboxing/auto-review). Add review and enforcement

244to your own harness. The

245[open-source Codex reviewer policy](https://github.com/openai/codex/blob/main/codex-rs/core/src/guardian/policy.md)

246illustrates one approach; [Cyber Safety](https://developers.openai.com/codex/cyber-safety) explains approved

247model access and safe engagement setup.

248

224## Streaming and delayed review use the same state model249## Streaming and delayed review use the same state model

225 250

226Streaming doesn't create a separate approval system. If a streamed run pauses, wait for it to settle, inspect `interruptions`, resolve the approvals, and resume from the same `state`. If the review happens later, store the serialized state and continue the same run when the decision arrives.251Streaming doesn't create a separate approval system. If a streamed run pauses, wait for it to settle, inspect `interruptions`, resolve the approvals, and resume from the same `state`. If the review happens later, store the serialized state and continue the same run when the decision arrives.

guides/ip-allowlist.md +58 −0 created

Details

1# IP allowlist

3> For the complete documentation index, see [llms.txt](/llms.txt). Markdown versions of documentation pages are available by appending `.md` to the page URL.

5An IP allowlist lets you restrict OpenAI API requests to IP addresses or CIDR ranges that you trust. When you enable an allowlist, OpenAI rejects requests from other IP addresses even if they include a valid API key.

7Use an IP allowlist as another layer of protection for production workloads with fixed or well-defined network egress. It applies only to API requests; it does not restrict access to [platform.openai.com](https://platform.openai.com) or user sign-in.

9IP allowlisting controls requests that your applications send to OpenAI. If

10 you need to allow requests that OpenAI products send to services you control,

11 use the published [IP egress ranges](https://developers.openai.com/api/docs/guides/ip-addresses) instead.

13## Before you enable an allowlist

15Identify the public egress IP address or range for every workload that calls the API. Check the address after any network address translation (NAT), VPN, firewall, or proxy, because the API evaluates the source IP that reaches OpenAI.

17An allowlist can contain up to 50 individual IP addresses or CIDR ranges. The organization owner role includes the `Read` and `Write` permissions needed to manage IP allowlist settings. For more information about permissions, see [Manage permissions in the OpenAI platform](https://developers.openai.com/api/docs/guides/rbac).

19Start with one non-critical project before applying an allowlist to your entire organization. Keep a tested request path from an allowed IP available while you test the configuration.

21Project-level allowlists take precedence over organization-level allowlists. The entries do not combine: a project with its own active allowlist uses that allowlist, while a project without one uses the organization-level allowlist.

23## Configure an IP allowlist

251. Open [Settings > Security > IP allowlist](https://platform.openai.com/settings/organization/security/ip-allowlist).

262. Add the individual IP addresses or CIDR ranges that you want to allow. For example, use `203.0.113.10` for one address or `203.0.113.0/24` for a range.

273. Optionally, use the **Check** tool to confirm that the allowlist includes a specific IP address.

284. Enable the allowlist for a specific project or for your entire organization.

295. Wait up to 15 minutes for the change to take effect.

306. Send API requests from each expected environment to verify access.

32Enabling an organization-level allowlist affects API requests for projects

33 that do not have their own active allowlist. Confirm every production,

34 staging, CI, and disaster-recovery egress path in each affected scope before

35 you enable it.

37## Verify enforcement

39From an allowed network path, send a representative API request. For example:

41```bash

42curl https://api.openai.com/v1/models \

43 -H "Authorization: Bearer $OPENAI_API_KEY"

44```

46The request should complete according to the API key's normal authentication and authorization. From an IP address that is not included in the active allowlist, the request fails with HTTP `401` and the `ip_not_authorized` error code.

48## Troubleshoot blocked requests

50If an expected request fails with `ip_not_authorized`:

52- Confirm the workload's public egress IP from the same network path that sends the API request. A local development machine can have a different public IP than a deployed service.

53- Check whether a NAT gateway, VPN, firewall, proxy, or cloud provider changed the egress address.

54- Use the **Check** tool in [IP allowlist settings](https://platform.openai.com/settings/organization/security/ip-allowlist) to check the address against the configured entries.

55- Confirm that the active allowlist applies to the organization or project associated with the API key.

56- Wait up to 15 minutes after a configuration change, then test again.

58An IP allowlist does not replace secure API key storage, key rotation, or account security. If a request must originate from a private Azure network instead of a public IP, consider [Private Link](https://developers.openai.com/api/docs/guides/private-link); Private Link is not compatible with IP allowlist controls.

guides/safety-checks/cybersecurity.md +32 −0

Details

6 6

7These safeguards monitor for signals of potentially suspicious cybersecurity activity. If certain thresholds are met, access to the model may be temporarily limited while activity is reviewed. Because these systems are still being calibrated, legitimate security research or defensive work may occasionally be flagged. We expect only a small portion of traffic to be impacted, and we’re continuing to refine the overall API experience.7These safeguards monitor for signals of potentially suspicious cybersecurity activity. If certain thresholds are met, access to the model may be temporarily limited while activity is reviewed. Because these systems are still being calibrated, legitimate security research or defensive work may occasionally be flagged. We expect only a small portion of traffic to be impacted, and we’re continuing to refine the overall API experience.

8 8

9## Authorized access and agentic workflows

11[Trusted Access for Cyber](https://developers.openai.com/codex/cyber-safety#trusted-access-for-cyber) is a

12reviewed access program, not the name of a model. Approval for Daybreak Blue

13applies only to the authorized person or service, workspace or API organization

14and project, model, and product surface. Daybreak Red requires separate

15approval and provisioning; applying, verifying an identity, or receiving

16Daybreak Blue access doesn't grant specialist-model access.

18For approved API projects, `gpt-daybreak-blue-latest` resolves to `gpt-5.6-sol`,

19and `gpt-daybreak-red-latest` resolves to `gpt-5.6-cyber`. Use the Daybreak

20alias or, if your project has the required approval, the corresponding

21underlying model ID. Access and model behavior depend on the approved

22organization and project; the model ID alone doesn't grant access.

24Trusted Access doesn't automatically grant Zero Data Retention. Confirm any

25separately approved retention controls for the exact API organization and

26applicable endpoint.

28Trusted Access governs approved model access; it doesn't configure your tools,

29environment, or engagement scope.

31If a Responses API or Agents SDK workflow can take sensitive cybersecurity

32actions, review each proposed tool call against the approved scope before

33execution. Deny unauthorized actions, pause ambiguous or high-risk changes for

34human approval, enforce independent filesystem and network boundaries, keep

35audit logs, and fail closed when review is unavailable. See

36[Guardrails and human review](https://developers.openai.com/api/docs/guides/agents/guardrails-approvals#review-cybersecurity-actions-before-execution).

38Application-level tool review and Codex product-side sandboxing are separate

39from the API cybersecurity safeguards described on this page.

9## Safeguard actions for non-ZDR Organizations41## Safeguard actions for non-ZDR Organizations

10 42

11If our systems detect potentially suspicious cybersecurity activity within your traffic that exceeds defined thresholds, access to these models may be temporarily revoked. In this case, API requests will return an error with the error code `cyber_policy`.43If our systems detect potentially suspicious cybersecurity activity within your traffic that exceeds defined thresholds, access to these models may be temporarily revoked. In this case, API requests will return an error with the error code `cyber_policy`.

guides/your-data.md +4 −4

Details

183| Singapore\* | `sg.api.openai.com` | Yes | No | Yes | Text, Audio, Voice, Image | `/v1/audio/transcriptions, /v1/audio/translations, /v1/audio/speech` `/v1/batches` `/v1/chat/completions` `/v1/embeddings` `/v1/files` `/v1/fine_tuning/jobs` `/v1/images/edits` `/v1/images/generations` `/v1/moderations` `/v1/responses` `/v1/responses File Search` `/v1/responses Web Search` `/v1/vector_stores` `Code Interpreter tool` `File Search` `File Uploads` `Remote MCP server tool` `Scale Tier` `Structured Outputs (excluding schema)` `Supported input modalities` | None |183| Singapore\* | `sg.api.openai.com` | Yes | No | Yes | Text, Audio, Voice, Image | `/v1/audio/transcriptions, /v1/audio/translations, /v1/audio/speech` `/v1/batches` `/v1/chat/completions` `/v1/embeddings` `/v1/files` `/v1/fine_tuning/jobs` `/v1/images/edits` `/v1/images/generations` `/v1/moderations` `/v1/responses` `/v1/responses File Search` `/v1/responses Web Search` `/v1/vector_stores` `Code Interpreter tool` `File Search` `File Uploads` `Remote MCP server tool` `Scale Tier` `Structured Outputs (excluding schema)` `Supported input modalities` | None |

184| South Korea\* | `kr.api.openai.com` | Yes | No | Yes | Text, Audio, Voice, Image | `/v1/audio/transcriptions, /v1/audio/translations, /v1/audio/speech` `/v1/batches` `/v1/chat/completions` `/v1/embeddings` `/v1/files` `/v1/fine_tuning/jobs` `/v1/images/edits` `/v1/images/generations` `/v1/moderations` `/v1/responses` `/v1/responses File Search` `/v1/responses Web Search` `/v1/vector_stores` `Code Interpreter tool` `File Search` `File Uploads` `Remote MCP server tool` `Scale Tier` `Structured Outputs (excluding schema)` `Supported input modalities` | None |184| South Korea\* | `kr.api.openai.com` | Yes | No | Yes | Text, Audio, Voice, Image | `/v1/audio/transcriptions, /v1/audio/translations, /v1/audio/speech` `/v1/batches` `/v1/chat/completions` `/v1/embeddings` `/v1/files` `/v1/fine_tuning/jobs` `/v1/images/edits` `/v1/images/generations` `/v1/moderations` `/v1/responses` `/v1/responses File Search` `/v1/responses Web Search` `/v1/vector_stores` `Code Interpreter tool` `File Search` `File Uploads` `Remote MCP server tool` `Scale Tier` `Structured Outputs (excluding schema)` `Supported input modalities` | None |

185| United Kingdom\* | `gb.api.openai.com` | Yes | No | Yes | Text, Audio, Voice, Image | `/v1/audio/transcriptions, /v1/audio/translations, /v1/audio/speech` `/v1/batches` `/v1/chat/completions` `/v1/embeddings` `/v1/files` `/v1/fine_tuning/jobs` `/v1/images/edits` `/v1/images/generations` `/v1/moderations` `/v1/responses` `/v1/responses File Search` `/v1/responses Web Search` `/v1/vector_stores` `Code Interpreter tool` `File Search` `File Uploads` `Remote MCP server tool` `Scale Tier` `Structured Outputs (excluding schema)` `Supported input modalities` | None |185| United Kingdom\* | `gb.api.openai.com` | Yes | No | Yes | Text, Audio, Voice, Image | `/v1/audio/transcriptions, /v1/audio/translations, /v1/audio/speech` `/v1/batches` `/v1/chat/completions` `/v1/embeddings` `/v1/files` `/v1/fine_tuning/jobs` `/v1/images/edits` `/v1/images/generations` `/v1/moderations` `/v1/responses` `/v1/responses File Search` `/v1/responses Web Search` `/v1/vector_stores` `Code Interpreter tool` `File Search` `File Uploads` `Remote MCP server tool` `Scale Tier` `Structured Outputs (excluding schema)` `Supported input modalities` | None |

186| United Arab Emirates\* | `ae.api.openai.com` | Yes | Yes | Yes | Text, Audio, Voice, Image | `/v1/audio/transcriptions, /v1/audio/translations, /v1/audio/speech` `/v1/batches` `/v1/chat/completions` `/v1/embeddings` `/v1/files` `/v1/fine_tuning/jobs` `/v1/images/edits` `/v1/images/generations` `/v1/moderations` `/v1/responses` `/v1/responses File Search` `/v1/responses Web Search` `/v1/vector_stores` `Code Interpreter tool` `File Search` `File Uploads` `Remote MCP server tool` `Scale Tier` `Structured Outputs (excluding schema)` `Supported input modalities` | `/v1/chat/completions` (`gpt-5.2-2025-12-11`) `/v1/embeddings` (`text-embedding-3-large`) `/v1/responses` (`gpt-5.2-2025-12-11`) |186| United Arab Emirates\* | `ae.api.openai.com` | Yes | Yes | Yes | Text, Audio, Voice, Image | `/v1/audio/transcriptions, /v1/audio/translations, /v1/audio/speech` `/v1/batches` `/v1/chat/completions` `/v1/embeddings` `/v1/files` `/v1/fine_tuning/jobs` `/v1/images/edits` `/v1/images/generations` `/v1/moderations` `/v1/responses` `/v1/responses File Search` `/v1/responses Web Search` `/v1/vector_stores` `Code Interpreter tool` `File Search` `File Uploads` `Remote MCP server tool` `Scale Tier` `Structured Outputs (excluding schema)` `Supported input modalities` | `/v1/chat/completions` (`gpt-5.6-luna`, `gpt-5.5-2026-04-23`, `gpt-5.2-2025-12-11`) `/v1/embeddings` (`text-embedding-3-large`) `/v1/responses` (`gpt-5.5-pro-2026-04-23`, `gpt-5.6-luna`, `gpt-5.5-2026-04-23`, `gpt-5.2-2025-12-11`) |

187 187

188\* Image support in these regions requires approval for enhanced Zero Data Retention or enhanced Modified Abuse Monitoring.188\* Image support in these regions requires approval for enhanced Zero Data Retention or enhanced Modified Abuse Monitoring.

189 189

192#### API Endpoint, tool and model support192#### API Endpoint, tool and model support

193 193

195| -------------------------------------------------------------------- | ---------------- | ----------------------------------------- | --------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------- | ----------------------------------------------------------------------------------------------------------- |195| -------------------------------------------------------------------- | ---------------- | ----------------------------------------- | --------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------- |

197| `/v1/batches` | Batches | All listed regions | United States, Europe (EEA + Switzerland) | `gpt-5.5-pro-2026-04-23`, `gpt-5.4-pro-2026-03-05`, `gpt-5.2-pro-2025-12-11`, `gpt-5-pro-2025-10-06`, `gpt-5.6-sol`, `gpt-5.6-terra`, `gpt-5.6-luna`, `gpt-5.5-2026-04-23`, `gpt-5.4-2026-03-05`, `gpt-5-2025-08-07`, `gpt-5.4-mini-2026-03-17`, `gpt-5.4-nano-2026-03-17`, `gpt-5.2-2025-12-11`, `gpt-5.1-2025-11-13`, `gpt-5-mini-2025-08-07`, `gpt-5-nano-2025-08-07`, `gpt-4.1-2025-04-14`, `gpt-4.1-mini-2025-04-14`, `gpt-4.1-nano-2025-04-14`, `o3-2025-04-16`, `o4-mini-2025-04-16`, `o1-pro`, `o1-pro-2025-03-19`, `o3-mini-2025-01-31`, `o1-2024-12-17`, `gpt-4o-2024-11-20`, `gpt-4o-2024-08-06`, `gpt-4o-mini-2024-07-18`, `gpt-4-turbo-2024-04-09`, `gpt-4-0613`, `gpt-3.5-turbo-0125` | None | — |197| `/v1/batches` | Batches | All listed regions | United States, Europe (EEA + Switzerland) | `gpt-5.5-pro-2026-04-23`, `gpt-5.4-pro-2026-03-05`, `gpt-5.2-pro-2025-12-11`, `gpt-5-pro-2025-10-06`, `gpt-5.6-sol`, `gpt-5.6-terra`, `gpt-5.6-luna`, `gpt-5.5-2026-04-23`, `gpt-5.4-2026-03-05`, `gpt-5-2025-08-07`, `gpt-5.4-mini-2026-03-17`, `gpt-5.4-nano-2026-03-17`, `gpt-5.2-2025-12-11`, `gpt-5.1-2025-11-13`, `gpt-5-mini-2025-08-07`, `gpt-5-nano-2025-08-07`, `gpt-4.1-2025-04-14`, `gpt-4.1-mini-2025-04-14`, `gpt-4.1-nano-2025-04-14`, `o3-2025-04-16`, `o4-mini-2025-04-16`, `o1-pro`, `o1-pro-2025-03-19`, `o3-mini-2025-01-31`, `o1-2024-12-17`, `gpt-4o-2024-11-20`, `gpt-4o-2024-08-06`, `gpt-4o-mini-2024-07-18`, `gpt-4-turbo-2024-04-09`, `gpt-4-0613`, `gpt-3.5-turbo-0125` | None | — |

198| `/v1/chat/completions` | Chat Completions | All listed regions | United States, Europe (EEA + Switzerland), United Arab Emirates | `gpt-5.6-sol`, `gpt-5.6-terra`, `gpt-5.6-luna`, `gpt-5.5-2026-04-23`, `gpt-5.4-2026-03-05`, `gpt-5.4-mini-2026-03-17`, `gpt-5.4-nano-2026-03-17`, `gpt-5.2-2025-12-11`, `gpt-5.1-2025-11-13`, `gpt-5-2025-08-07`, `gpt-5-mini-2025-08-07`, `gpt-5-nano-2025-08-07`, `gpt-4.1-2025-04-14`, `gpt-4.1-mini-2025-04-14`, `gpt-4.1-nano-2025-04-14`, `o3-mini-2025-01-31`, `o3-2025-04-16`, `o4-mini-2025-04-16`, `o1-2024-12-17`, `gpt-4o-2024-11-20`, `gpt-4o-2024-08-06`, `gpt-4o-mini-2024-07-18`, `gpt-4-turbo-2024-04-09`, `gpt-4-0613`, `gpt-3.5-turbo-0125` | United Arab Emirates: `gpt-5.2-2025-12-11` | — |198| `/v1/chat/completions` | Chat Completions | All listed regions | United States, Europe (EEA + Switzerland), United Arab Emirates | `gpt-5.6-sol`, `gpt-5.6-terra`, `gpt-5.6-luna`, `gpt-5.5-2026-04-23`, `gpt-5.4-2026-03-05`, `gpt-5.4-mini-2026-03-17`, `gpt-5.4-nano-2026-03-17`, `gpt-5.2-2025-12-11`, `gpt-5.1-2025-11-13`, `gpt-5-2025-08-07`, `gpt-5-mini-2025-08-07`, `gpt-5-nano-2025-08-07`, `gpt-4.1-2025-04-14`, `gpt-4.1-mini-2025-04-14`, `gpt-4.1-nano-2025-04-14`, `o3-mini-2025-01-31`, `o3-2025-04-16`, `o4-mini-2025-04-16`, `o1-2024-12-17`, `gpt-4o-2024-11-20`, `gpt-4o-2024-08-06`, `gpt-4o-mini-2024-07-18`, `gpt-4-turbo-2024-04-09`, `gpt-4-0613`, `gpt-3.5-turbo-0125` | United Arab Emirates: `gpt-5.6-luna`, `gpt-5.5-2026-04-23`, `gpt-5.2-2025-12-11` | — |

209| `/v1/responses` | Responses | All listed regions | United States, Europe (EEA + Switzerland), United Arab Emirates | `gpt-5.5-pro-2026-04-23`, `gpt-5.4-pro-2026-03-05`, `gpt-5.2-pro-2025-12-11`, `gpt-5-pro-2025-10-06`, `gpt-5.6-sol`, `gpt-5.6-terra`, `gpt-5.6-luna`, `gpt-5.5-2026-04-23`, `gpt-5.4-2026-03-05`, `gpt-5-2025-08-07`, `gpt-5.4-mini-2026-03-17`, `gpt-5.4-nano-2026-03-17`, `gpt-5.2-2025-12-11`, `gpt-5.1-2025-11-13`, `gpt-5-mini-2025-08-07`, `gpt-5-nano-2025-08-07`, `gpt-4.1-2025-04-14`, `gpt-4.1-mini-2025-04-14`, `gpt-4.1-nano-2025-04-14`, `o3-2025-04-16`, `o4-mini-2025-04-16`, `o1-pro`, `o1-pro-2025-03-19`, `o3-mini-2025-01-31`, `o1-2024-12-17`, `gpt-4o-2024-11-20`, `gpt-4o-2024-08-06`, `gpt-4o-mini-2024-07-18`, `gpt-4-turbo-2024-04-09`, `gpt-4-0613`, `gpt-3.5-turbo-0125` | United Arab Emirates: `gpt-5.2-2025-12-11` | — |209| `/v1/responses` | Responses | All listed regions | United States, Europe (EEA + Switzerland), United Arab Emirates | `gpt-5.5-pro-2026-04-23`, `gpt-5.4-pro-2026-03-05`, `gpt-5.2-pro-2025-12-11`, `gpt-5-pro-2025-10-06`, `gpt-5.6-sol`, `gpt-5.6-terra`, `gpt-5.6-luna`, `gpt-5.5-2026-04-23`, `gpt-5.4-2026-03-05`, `gpt-5-2025-08-07`, `gpt-5.4-mini-2026-03-17`, `gpt-5.4-nano-2026-03-17`, `gpt-5.2-2025-12-11`, `gpt-5.1-2025-11-13`, `gpt-5-mini-2025-08-07`, `gpt-5-nano-2025-08-07`, `gpt-4.1-2025-04-14`, `gpt-4.1-mini-2025-04-14`, `gpt-4.1-nano-2025-04-14`, `o3-2025-04-16`, `o4-mini-2025-04-16`, `o1-pro`, `o1-pro-2025-03-19`, `o3-mini-2025-01-31`, `o1-2024-12-17`, `gpt-4o-2024-11-20`, `gpt-4o-2024-08-06`, `gpt-4o-mini-2024-07-18`, `gpt-4-turbo-2024-04-09`, `gpt-4-0613`, `gpt-3.5-turbo-0125` | United Arab Emirates: `gpt-5.5-pro-2026-04-23`, `gpt-5.6-luna`, `gpt-5.5-2026-04-23`, `gpt-5.2-2025-12-11` | — |

models.md +3 −0

Details

27- [codex-mini-latest](/api/docs/models/codex-mini-latest.md): Fast reasoning model optimized for the Codex CLI27- [codex-mini-latest](/api/docs/models/codex-mini-latest.md): Fast reasoning model optimized for the Codex CLI

28- [computer-use-preview](/api/docs/models/computer-use-preview.md): Specialized model for computer use tool28- [computer-use-preview](/api/docs/models/computer-use-preview.md): Specialized model for computer use tool

29- [davinci-002](/api/docs/models/davinci-002.md): Replacement for the GPT-3 curie and davinci base models29- [davinci-002](/api/docs/models/davinci-002.md): Replacement for the GPT-3 curie and davinci base models

30- [Daybreak Blue](/api/docs/models/daybreak-blue-latest.md): An alias for frontier general-purpose models with safeguards for defensive cybersecurity work.

31- [Daybreak Red](/api/docs/models/daybreak-red-latest.md): An alias for advanced cybersecurity models for authorized vulnerability research and security testing.

30- [GPT Image 1](/api/docs/models/gpt-image-1.md): Our previous image generation model32- [GPT Image 1](/api/docs/models/gpt-image-1.md): Our previous image generation model

31- [GPT Image 1.5](/api/docs/models/gpt-image-1.5.md): Our previous image generation model33- [GPT Image 1.5](/api/docs/models/gpt-image-1.5.md): Our previous image generation model

32- [GPT Image 2](/api/docs/models/gpt-image-2.md): State-of-the-art image generation model34- [GPT Image 2](/api/docs/models/gpt-image-2.md): State-of-the-art image generation model

75- [GPT-5.4 Pro](/api/docs/models/gpt-5.4-pro.md): Version of GPT-5.4 that produces smarter and more precise responses.77- [GPT-5.4 Pro](/api/docs/models/gpt-5.4-pro.md): Version of GPT-5.4 that produces smarter and more precise responses.

76- [GPT-5.5](/api/docs/models/gpt-5.5.md): A new class of intelligence for coding and professional work.78- [GPT-5.5](/api/docs/models/gpt-5.5.md): A new class of intelligence for coding and professional work.

77- [GPT-5.5 Pro](/api/docs/models/gpt-5.5-pro.md): Version of GPT-5.5 that produces smarter and more precise responses.79- [GPT-5.5 Pro](/api/docs/models/gpt-5.5-pro.md): Version of GPT-5.5 that produces smarter and more precise responses.

80- [GPT-5.6 Cyber](/api/docs/models/gpt-5.6-cyber.md): Our most advanced cybersecurity model for authorized vulnerability research and security testing.

78- [GPT-5.6 Luna](/api/docs/models/gpt-5.6-luna.md): GPT-5.6 model optimized for cost-sensitive workloads81- [GPT-5.6 Luna](/api/docs/models/gpt-5.6-luna.md): GPT-5.6 model optimized for cost-sensitive workloads

79- [GPT-5.6 Sol](/api/docs/models/gpt-5.6-sol.md): Frontier model for complex professional work82- [GPT-5.6 Sol](/api/docs/models/gpt-5.6-sol.md): Frontier model for complex professional work

80- [GPT-5.6 Terra](/api/docs/models/gpt-5.6-terra.md): GPT-5.6 model that balances intelligence and cost83- [GPT-5.6 Terra](/api/docs/models/gpt-5.6-terra.md): GPT-5.6 model that balances intelligence and cost

models/all.md +3 −0

Details

30- [Daybreak Blue](/api/docs/models/daybreak-blue-latest.md): An alias for frontier general-purpose models with safeguards for defensive cybersecurity work.

31- [Daybreak Red](/api/docs/models/daybreak-red-latest.md): An alias for advanced cybersecurity models for authorized vulnerability research and security testing.

30- [GPT Image 1](/api/docs/models/gpt-image-1.md): Our previous image generation model32- [GPT Image 1](/api/docs/models/gpt-image-1.md): Our previous image generation model

31- [GPT Image 1.5](/api/docs/models/gpt-image-1.5.md): Our previous image generation model33- [GPT Image 1.5](/api/docs/models/gpt-image-1.5.md): Our previous image generation model

32- [GPT Image 2](/api/docs/models/gpt-image-2.md): State-of-the-art image generation model34- [GPT Image 2](/api/docs/models/gpt-image-2.md): State-of-the-art image generation model

80- [GPT-5.6 Cyber](/api/docs/models/gpt-5.6-cyber.md): Our most advanced cybersecurity model for authorized vulnerability research and security testing.

79- [GPT-5.6 Sol](/api/docs/models/gpt-5.6-sol.md): Frontier model for complex professional work82- [GPT-5.6 Sol](/api/docs/models/gpt-5.6-sol.md): Frontier model for complex professional work

Documentation 2026-08-07 00:58 UTC to 2026-08-10 19:00 UTC