{"id":"405ff946-c504-4b92-9f4f-7e925db996bf","entityType":"agent","slug":"clawhub-runapi-ai-runapi-gpt-image-2","name":"gpt-image-2","canonicalUrl":"https://www.xpersona.co/agent/clawhub-runapi-ai-runapi-gpt-image-2","canonicalPath":"/agent/clawhub-runapi-ai-runapi-gpt-image-2","generatedAt":"2026-10-11T17:41:50.482Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-11T15:43:46.837Z","emptyReason":null},"description":"Generate and edit images with GPT Image 2 through RunAPI. Use when the user asks an agent to create, edit, or transform images with GPT Image 2. Default to the RunAPI CLI for one-off generation; use SDKs only when the user is integrating RunAPI into an app or backend. Skill: gpt-image-2 Owner: runapi-ai Summary: Generate and edit images with GPT Image 2 through RunAPI. Use when the user asks an agent to create, edit, or transform images with GPT Image 2. Default to the RunAPI CLI for one-off generation; use SDKs only when the user is integrating RunAPI into an app or backend. Tags: latest:0.2.9 Version history: v0.2.9 | 2026-08-12T06:07:52.665Z | user Changed - Generate the gpt-im","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 1K downloads reported by the source. Last updated 10/11/2026.","installCommand":"clawhub skill install s1771k6pjxksnjws51x2htfjvd876syh:runapi-gpt-image-2","sourceUrl":"https://clawhub.ai/runapi-ai/runapi-gpt-image-2","homepage":"https://clawhub.ai/runapi-ai/skills/runapi-gpt-image-2","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/runapi-ai/runapi-gpt-image-2","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/runapi-ai/skills/runapi-gpt-image-2","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":60,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Generate and edit images with GPT Image 2 through RunAPI. Use when the user asks an agent to create, edit, or transform images with GPT Image 2. Default to the "},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-11T15:43:46.837Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T15:43:46.837Z","emptyReason":null},"stars":null,"forks":null,"downloads":1036,"packageName":null,"latestVersion":"0.2.9","tractionLabel":"1K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T15:43:46.823Z","emptyReason":null},"lastUpdatedAt":"2026-10-11T15:43:46.837Z","lastCrawledAt":"2026-10-11T15:43:46.823Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-12T15:43:46.823Z","lastVerifiedAt":null,"highlights":[{"version":"0.2.9","createdAt":"2026-08-12T06:07:52.665Z","changelog":"## Changed - Generate the gpt-image-2 skill from the shared RunAPI recipe with contract-discovered request rules and task behavior, direct local media inputs, complete result verification, and bounded recovery.","fileCount":3,"zipByteSize":4638},{"version":"0.2.8","createdAt":"2026-08-10T14:04:02.999Z","changelog":"## Changed - Complete marketplace distribution for the RunAPI GPT Image 2 skill.","fileCount":3,"zipByteSize":3094},{"version":"0.2.4","createdAt":"2026-05-22T09:14:41.421Z","changelog":"Agent-facing CLI-first redesign","fileCount":3,"zipByteSize":2578},{"version":"0.2.3","createdAt":"2026-05-22T07:06:47.219Z","changelog":"Publish RunAPI skill README install prompt updates.","fileCount":2,"zipByteSize":1133}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s1771k6pjxksnjws51x2htfjvd876syh:runapi-gpt-image-2","setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-runapi-ai-runapi-gpt-image-2/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-runapi-ai-runapi-gpt-image-2/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-runapi-ai-runapi-gpt-image-2/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-runapi-ai-runapi-gpt-image-2/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-runapi-ai-runapi-gpt-image-2/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-runapi-ai-runapi-gpt-image-2/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-11T17:41:50.481Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-runapi-ai-runapi-gpt-image-2/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-runapi-ai-runapi-gpt-image-2/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-runapi-ai-runapi-gpt-image-2/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-runapi-ai-runapi-gpt-image-2/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"high","updatedAt":"2026-10-11T15:43:46.837Z","emptyReason":null},"readme":"Skill: gpt-image-2\n\nOwner: runapi-ai\n\nSummary: Generate and edit images with GPT Image 2 through RunAPI. Use when the user asks an agent to create, edit, or transform images with GPT Image 2. Default to the RunAPI CLI for one-off generation; use SDKs only when the user is integrating RunAPI into an app or backend.\n\nTags: latest:0.2.9\n\nVersion history:\n\nv0.2.9 | 2026-08-12T06:07:52.665Z | user\n\n## Changed\n- Generate the gpt-image-2 skill from the shared RunAPI recipe with contract-discovered request rules and task behavior, direct local media inputs, complete result verification, and bounded recovery.\n\nv0.2.8 | 2026-08-10T14:04:02.999Z | user\n\n## Changed\n- Complete marketplace distribution for the RunAPI GPT Image 2 skill.\n\nv0.2.4 | 2026-05-22T09:14:41.421Z | user\n\nAgent-facing CLI-first redesign\n\nv0.2.3 | 2026-05-22T07:06:47.219Z | user\n\nPublish RunAPI skill README install prompt updates.\n\nArchive index:\n\nArchive v0.2.9: 3 files, 4638 bytes\n\nFiles: skill-card.md (2729b), SKILL.md (6914b), _meta.json (137b)\n\nFile v0.2.9:SKILL.md\n\n---\nname: gpt-image-2\ndescription: \"Generate and edit images with GPT Image 2 through RunAPI. Use when the user asks an agent to create, edit, or transform images with GPT Image 2. Default to the RunAPI CLI for one-off generation; use SDKs only when the user is integrating RunAPI into an app or backend.\"\ndocumentation: https://runapi.ai/models/gpt-image-2.md\nprovider_page: https://runapi.ai/providers/openai.md\ncatalog: https://runapi.ai/models.md\nmetadata:\n openclaw:\n homepage: https://runapi.ai/models/gpt-image-2\n requires:\n bins:\n - runapi\n install:\n - kind: brew\n formula: runapi-ai/tap/runapi\n bins:\n - runapi\n envVars:\n - name: RUNAPI_API_KEY\n required: false\n description: Optional RunAPI API key; agents should prefer environment auth or saved CLI config. Browser login is interactive fallback only.\n---\n\n# GPT Image 2 on RunAPI\n\n## Choose route\n\n- For a one-off artifact or result, use the registered `gpt-image-2` service in the `runapi` CLI. If the installed command catalog does not list it, stop and report the missing service instead of inventing a command.\n- For an app, backend, worker, library, webhook pipeline, or production codebase, go directly to **Integrate with SDK**. Never shell out to the CLI as the production runtime.\n\n## Discover contract\n\nAuthenticate, then inspect the installed command catalog and the selected operation's current contract:\n\n```shell\nrunapi auth status > auth.json\njq -e '.authenticated == true' auth.json\nrunapi gpt-image-2 --help\nrunapi gpt-image-2 --help\ncurl --fail --location https://runapi.ai/docs/api/gpt-image-2/.md --output contract.md\n```\n\nIf authentication is false, stop before submitting. Ask the user to provide a valid `RUNAPI_API_KEY`, or import a user-provided key from stdin with `runapi auth import-token --token -`; use interactive browser login only when the user explicitly requests it. Choose `` only from service help. Treat command help as authoritative for the installed operation, model, and top-level field roster. Treat its API Reference as authoritative for the complete request schema, nested fields, conditional rules, task behavior, and response variants. If the two surfaces disagree, stop and report the contract mismatch instead of guessing.\n\n## Build request\n\nCreate `request.json` as valid JSON using only fields accepted by the discovered operation contract. For the chosen model and values, evaluate every applicable conditional rule as a set: satisfy every required field, omit every forbidden field, and stop on unresolved contradictions.\n\nTraverse nested objects and arrays before execution. Close every relationship stated by the discovered contract, including uniqueness constraints and cross-references between nested values.\n\nFor a discovered local media input, including file-typed fields and top-level media URL fields, put an agent-readable local file path directly in `request.json`. The CLI consumes file fields as declared and uploads local paths in top-level media URL fields. Use `runapi files create` only when the user needs a reusable URL, provides Base64, or the discovered contract explicitly requires a separate upload.\n\nValidate the file before sending it:\n\n```shell\njq empty request.json\n```\n\n## Execute\n\nSubmit exactly once and persist the task response before waiting:\n\n```shell\nrunapi gpt-image-2 --async --input-file request.json > task.json\ntask_id=\"$(jq -er '.id' task.json)\"\n```\n\nFor a one-off result, immediately wait for that same task and save the complete JSON response. This blocking wait is the default:\n\n```shell\nrunapi wait \"$task_id\" --service gpt-image-2 --action > result.json\n```\n\nOnly when the user explicitly asks for background execution, polling, or webhook integration may you stop after validating `task.json`. Report the task id and do not claim that the deliverable is complete.\n\n## Verify\n\nA success status is not the deliverable. Read and validate the complete response according to the discovered result contract. Preserve the complete non-media result in the exact requested format, including JSON, text, SRT, or VTT.\n\nFor every requested media deliverable listed anywhere in the response, download all of them rather than returning only the first URL. Before downloading, derive its expected MIME type or family from response metadata when present, then the selected output format, then an unambiguous result field such as `videos`, `images`, or `audios` in the API Reference. The Catalog-declared fallback families for this skill are `image/*`. Stop only when no single expected type or family can be established from those sources.\n\nFor every downloaded file, require both a non-empty file and the expected MIME type or family:\n\n```shell\ncurl --fail --location --output \nfor file in ; do\n expected_mime=\n test -s \"$file\"\n [[ \"$(file --brief --mime-type \"$file\")\" == $expected_mime ]]\ndone\n```\n\nDo not report completion when any requested deliverable is missing, empty, or has an unexpected MIME type. Record `Skill Conformance` separately from `Task Outcome` so a service failure does not hide whether this recipe was followed.\n\n## Recover or stop\n\n- Correct a request shape at most once, and only when the discovered contract or returned validation error identifies the correction.\n- Retry a transient transport failure at most once, and only when evidence confirms that no task was created, no billing occurred, and retrying is safe.\n- If waiting times out or loses transport after `task.json` exists, preserve the error and rerun `runapi wait` for that same task at most once. Never submit a replacement task.\n- On a terminal RunAPI or service failure, preserve the task/error evidence and stop. Keep the selected model and capability, and do not submit another paid request without user authorization.\n- If the contract is missing a fact required to build or verify the request, stop and report the contract gap. Do not turn a product defect into a permanent skill workaround.\n\n## Integrate with SDK\n\nUse this route only for application or production-code integration. Open the current RunAPI SDK reference below, select the package for the target language and `GPT Image 2`, and confirm its install command, client methods, request types, response types, and error classes before coding. Build the request from the same discovered product contract and apply the same deliverable verification and stop rules. Do not invoke `runapi` as a subprocess from production code.\n\n## References\n\n- Model overview, pricing, and rate limits: https://runapi.ai/models/gpt-image-2.md\n- Provider overview: https://runapi.ai/providers/openai.md\n- Full model catalog: https://runapi.ai/models.md\n- SDK integration: https://github.com/runapi-ai/gpt-image-2-sdk\n\nFile v0.2.9:_meta.json\n\n{\n \"ownerId\": \"kn70me4rk7jqjt92evshjeb5z18768g7\",\n \"slug\": \"runapi-gpt-image-2\",\n \"version\": \"0.2.9\",\n \"publishedAt\": 1786514872665\n}\n\nFile v0.2.9:skill-card.md\n\n## Description:\n\nGenerate and edit images with GPT Image 2 through RunAPI. Use when the user asks an agent to create, edit, or transform images with GPT Image 2. Default to the RunAPI CLI for one-off generation; use SDKs only when the user is integrating RunAPI into an app or backend.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[runapi-ai](https://clawhub.ai/user/runapi-ai)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and agents use this skill to generate, edit, or transform images with GPT Image 2 through RunAPI. The skill supports one-off CLI generation and SDK-oriented integration for applications, backends, workers, and pipelines.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: RunAPI credentials may be exposed in shared workspaces.\n\nMitigation: Prefer environment authentication or saved CLI configuration, keep API keys out of shared files, and import user-provided tokens through stdin when needed.\n\nRisk: The workflow can create paid API tasks.\n\nMitigation: Authenticate first, validate the request contract before submission, submit once, and retry only when evidence confirms that no task was created and no billing occurred.\n\nRisk: Intermediate JSON files and generated images may contain sensitive task or output data.\n\nMitigation: Store results in an appropriate workspace, review outputs before sharing, and verify downloaded files are non-empty images with the expected MIME type.\n\n## Reference(s):\n\n- [ClawHub skill release](https://clawhub.ai/runapi-ai/skills/runapi-gpt-image-2)\n- [RunAPI GPT Image 2 homepage](https://runapi.ai/models/gpt-image-2)\n- [Model overview, pricing, and rate limits](https://runapi.ai/models/gpt-image-2.md)\n- [Provider overview](https://runapi.ai/providers/openai.md)\n- [Full model catalog](https://runapi.ai/models.md)\n- [SDK integration](https://github.com/runapi-ai/gpt-image-2-sdk)\n\n## Skill Output:\n\n**Output Type(s):** [Guidance, Shell commands, Configuration, Code, Files]\n\n**Output Format:** [Markdown guidance with shell commands, JSON request and response files, and generated image files when tasks complete]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Requires the RunAPI CLI and optional RUNAPI_API_KEY; generated media should be downloaded, checked for non-empty content, and verified against the expected image MIME type.]\n\n## Skill Version(s):\n\n0.2.9 (source: server release evidence)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nArchive v0.2.8: 3 files, 3094 bytes\n\nFiles: skill-card.md (2405b), SKILL.md (3637b), _meta.json (137b)\n\nFile v0.2.8:SKILL.md\n\n---\nname: gpt-image-2\ndescription: Generate and edit images with GPT Image 2 through RunAPI. Use when the user asks an agent to create, edit, or transform images with GPT Image 2. Default to the RunAPI CLI for one-off generation; use SDKs only when the user is integrating RunAPI into an app or backend.\ndocumentation: https://runapi.ai/models/gpt-image-2.md\nprovider_page: https://runapi.ai/providers/openai.md\ncatalog: https://runapi.ai/models.md\nmetadata:\n openclaw:\n homepage: https://runapi.ai/models/gpt-image-2\n requires:\n bins:\n - runapi\n install:\n - kind: brew\n formula: runapi-ai/tap/runapi\n bins:\n - runapi\n envVars:\n - name: RUNAPI_API_KEY\n required: false\n description: Optional RunAPI API key; agents should prefer environment auth or saved CLI config. Browser login is interactive fallback only.\n---\n\n# GPT Image 2 on RunAPI\n\nGenerate and edit images with GPT Image 2 through RunAPI. The default path for one-off agent tasks is the `runapi` CLI; SDKs are for application integration.\n\n## Critical: Integration Runtime\n\n- Integration work (app, backend, worker, library, Rails service, Node service, Go service, webhook pipeline, or production codebase) uses the **SDK integration path** for the target language.\n- One-off generation, editing, transformation, manual smoke tests, debugging, or user-requested CLI runs use the **CLI path** with the `runapi` binary. For full CLI-specific agent guidance, see https://github.com/runapi-ai/cli-skill.\n- Never shell out to the `runapi` CLI as the production runtime integration layer.\n\n## SDK integration path\n\nWhen integrating GPT Image 2 into an app, backend, worker, library, Rails service, Node service, Go service, webhook pipeline, or production workflow, start by checking the current SDK package and official usage. Confirm install commands, client methods (`create`, `get`, `run`), request fields, response shape, and error classes before using CLI help or raw HTTP examples. Use a RunAPI SDK package:\n\n- JavaScript / TypeScript: `@runapi.ai/gpt-image-2`\n- Ruby: `runapi-gpt-image-2`\n- Go: `github.com/runapi-ai/gpt-image-2-sdk/go`\n\n## CLI path\n\nThe `runapi` binary is the one-off and manual testing runtime dependency. For full CLI-specific agent guidance, see https://github.com/runapi-ai/cli-skill. Run `runapi auth status` first. For agents and headless runs, prefer `RUNAPI_API_KEY` or import it into saved config with `printf '%s' \"$RUNAPI_API_KEY\" | runapi auth import-token --token -`. Use `runapi login` only when the user explicitly wants interactive browser auth.\n\nInspect the available commands and request fields with CLI help:\n\n```shell\nrunapi gpt-image-2 --help\nrunapi gpt-image-2 text-to-image --help\n```\n\nRun a one-off task (synchronous — polls until the task completes):\n\n```shell\nrunapi gpt-image-2 text-to-image --input-file request.json\n```\n\nSubmit asynchronously and poll separately:\n\n```shell\nrunapi gpt-image-2 text-to-image --async --input-file request.json\nrunapi wait --service gpt-image-2 --action text-to-image\n```\n\nAvailable commands: `text-to-image`, `edit-image`.\n\n## Generated file storage\n\nRunAPI-generated file URLs are temporary. Download and store generated images, videos, audio, or other files in your own durable storage within 7 days; do not treat returned URLs as long-term assets.\n\n## References\n\n- Model overview, pricing, and rate limits: https://runapi.ai/models/gpt-image-2.md\n- Provider comparison: https://runapi.ai/providers/openai.md\n- Full model catalog: https://runapi.ai/models.md\n\n## Model\n\n- [GPT Image 2](https://runapi.ai/models/gpt-image-2.md)\n\nFile v0.2.8:_meta.json\n\n{\n \"ownerId\": \"kn70me4rk7jqjt92evshjeb5z18768g7\",\n \"slug\": \"runapi-gpt-image-2\",\n \"version\": \"0.2.8\",\n \"publishedAt\": 1786370642999\n}\n\nFile v0.2.8:skill-card.md\n\n## Description:\n\nGenerate and edit images with GPT Image 2 through RunAPI.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[runapi-ai](https://clawhub.ai/user/runapi-ai)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and agents use this skill to generate, edit, or transform images with GPT Image 2 through RunAPI, using the CLI for one-off tasks and SDKs for application integration.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Prompts and image inputs may be submitted to RunAPI/OpenAI-backed services.\n\nMitigation: Review provider terms and avoid sending sensitive prompts or images unless the deployment requirements allow it.\n\nRisk: The skill may use a RunAPI API key or saved CLI login.\n\nMitigation: Prefer environment-based or saved CLI authentication, keep credentials out of prompts and files, and rotate credentials if exposed.\n\nRisk: Generated file URLs are temporary and may not serve as durable storage.\n\nMitigation: Download generated outputs and store them in approved durable storage within the retention window.\n\nRisk: Image generation and editing can incur provider costs.\n\nMitigation: Review pricing, rate limits, and usage controls before running high-volume tasks.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/runapi-ai/skills/runapi-gpt-image-2)\n- [RunAPI GPT Image 2 model overview](https://runapi.ai/models/gpt-image-2.md)\n- [RunAPI GPT Image 2 homepage](https://runapi.ai/models/gpt-image-2)\n- [RunAPI OpenAI provider comparison](https://runapi.ai/providers/openai.md)\n- [RunAPI model catalog](https://runapi.ai/models.md)\n- [RunAPI CLI skill](https://github.com/runapi-ai/cli-skill)\n\n## Skill Output:\n\n**Output Type(s):** [guidance, shell commands, code, configuration]\n\n**Output Format:** [Markdown with inline shell commands and SDK package guidance]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [May guide agents to generate or edit image files through RunAPI and to download temporary generated file URLs into durable storage.]\n\n## Skill Version(s):\n\n0.2.8 (source: server release evidence)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nArchive v0.2.4: 3 files, 2578 bytes\n\nFiles: skill-card.md (2290b), SKILL.md (2673b), _meta.json (137b)\n\nFile v0.2.4:SKILL.md\n\n---\nname: gpt-image-2\ndescription: Generate and edit images with GPT Image 2 through RunAPI. Use when the user asks an agent to create, edit, or transform images with GPT Image 2. Default to the RunAPI CLI for one-off generation; use SDKs only when the user is integrating RunAPI into an app or backend.\ndocumentation: https://runapi.ai/models/gpt-image-2.md\nprovider_page: https://runapi.ai/providers/openai.md\ncatalog: https://runapi.ai/models.md\nmetadata:\n openclaw:\n homepage: https://runapi.ai/models/gpt-image-2\n requires:\n bins:\n - runapi\n install:\n - kind: brew\n formula: runapi-ai/tap/runapi\n bins:\n - runapi\n envVars:\n - name: RUNAPI_API_KEY\n required: false\n description: Optional RunAPI API key; runapi login or saved CLI config can also authenticate the runapi binary.\n---\n\n# GPT Image 2 on RunAPI\n\nGenerate and edit images with GPT Image 2 through RunAPI. The default path for one-off agent tasks is the `runapi` CLI; SDKs are for application integration.\n\n## Routing decision\n\n- One-off generation, editing, or transformation for the user → use the **CLI path** with the `runapi` binary.\n- Building an app, backend, worker, library, or production codebase → use the **SDK integration path**.\n\n## CLI path\n\nThe `runapi` binary is the runtime dependency. Authenticate with `runapi login` (browser) or set `RUNAPI_API_KEY`; a saved CLI config also works — no required environment variable.\n\nInspect the available actions and request fields with CLI help:\n\n```shell\nrunapi gpt-image-2 --help\nrunapi gpt-image-2 text-to-image --help\n```\n\nRun a one-off task (synchronous — polls until the task completes):\n\n```shell\nrunapi gpt-image-2 text-to-image --input-file request.json\n```\n\nSubmit asynchronously and poll separately:\n\n```shell\nrunapi gpt-image-2 text-to-image --async --input-file request.json\nrunapi wait --service gpt-image-2 --action text-to-image\n```\n\nAvailable actions: `text-to-image`, `edit-image`.\n\n## SDK integration path\n\nWhen integrating GPT Image 2 into an app, backend, worker, or library — not for one-off tasks — use a RunAPI SDK package:\n\n- JavaScript / TypeScript: `@runapi.ai/gpt-image-2`\n- Ruby: `runapi-gpt_image_2`\n- Go: `github.com/runapi-ai/gpt-image-2-sdk/go`\n\n## References\n\n- Model overview, pricing, and rate limits: https://runapi.ai/models/gpt-image-2.md\n- Provider comparison: https://runapi.ai/providers/openai.md\n- Full model catalog: https://runapi.ai/models.md\n\n## Variants\n\n- [GPT Image 2 text to image](https://runapi.ai/models/gpt-image-2/text-to-image.md)\n- [GPT Image 2 image to image](https://runapi.ai/models/gpt-image-2/image-to-image.md)\n\nFile v0.2.4:_meta.json\n\n{\n \"ownerId\": \"kn70me4rk7jqjt92evshjeb5z18768g7\",\n \"slug\": \"runapi-gpt-image-2\",\n \"version\": \"0.2.4\",\n \"publishedAt\": 1779441281421\n}\n\nFile v0.2.4:skill-card.md\n\n## Description:
\nGenerate and edit images with GPT Image 2 through RunAPI.
\n\nThis skill is ready for commercial/non-commercial use.
\n\n## Publisher:
\n[runapi-ai](https://clawhub.ai/user/runapi-ai)
\n\n### License/Terms of Use:
\nMIT-0
\n\n\n## Use Case:
\nAgents use this skill to route image generation, editing, and transformation requests to GPT Image 2 through RunAPI. It guides one-off CLI use and points developers to SDK packages when integrating the model into an app or backend.
\n\n### Deployment Geography for Use:
\nGlobal
\n\n## Known Risks and Mitigations:
\nRisk: The RunAPI CLI may use a saved account session or API key.
\nMitigation: Review which account or RUNAPI_API_KEY the CLI will use before running image generation or editing commands.
\nRisk: Prompts and source images may contain confidential or sensitive content.
\nMitigation: Submit confidential prompts or private images only when RunAPI's data handling is acceptable for the use case.
\n\n\n## Reference(s):
\n- [RunAPI GPT Image 2 model overview](https://runapi.ai/models/gpt-image-2.md)
\n- [RunAPI GPT Image 2 homepage](https://runapi.ai/models/gpt-image-2)
\n- [RunAPI OpenAI provider comparison](https://runapi.ai/providers/openai.md)
\n- [RunAPI model catalog](https://runapi.ai/models.md)
\n- [GPT Image 2 text-to-image variant](https://runapi.ai/models/gpt-image-2/text-to-image.md)
\n- [GPT Image 2 image-to-image variant](https://runapi.ai/models/gpt-image-2/image-to-image.md)
\n\n\n## Skill Output:
\n**Output Type(s):** [Markdown, Shell commands, Configuration, Guidance]
\n**Output Format:** [Markdown with shell command examples and SDK package names]
\n**Output Parameters:** [1D]
\n**Other Properties Related to Output:** [Requires the runapi CLI for the CLI path; RUNAPI_API_KEY is optional because login or saved CLI configuration can authenticate the binary.]
\n\n## Skill Version(s):
\n0.2.4 (source: server release evidence)
\n\n## Ethical Considerations:
\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.
\n\nArchive v0.2.3: 2 files, 1133 bytes\n\nFiles: SKILL.md (1993b), _meta.json (137b)\n\nFile v0.2.3:SKILL.md\n\n---\nname: gpt-image-2\ndescription: GPT Image 2 API skill for RunAPI. Use when the user asks for gpt image 2 api SDK setup, CLI usage, pricing, model docs, or agent integration. Learn more at https://runapi.ai/models/gpt-image-2.\ndocumentation: https://runapi.ai/models/gpt-image-2\nprovider_page: https://runapi.ai/providers/openai\ncatalog: https://runapi.ai/models\nmetadata:\n openclaw:\n homepage: https://runapi.ai/models/gpt-image-2\n primaryEnv: RUNAPI_API_KEY\n requires:\n env:\n - RUNAPI_API_KEY\n envVars:\n - name: RUNAPI_API_KEY\n required: true\n description: RunAPI API key from https://runapi.ai/api_keys.\n---\n\n# GPT Image 2 API Skill for RunAPI\n\nUse this skill for gpt image 2 api work through RunAPI. Learn more at https://runapi.ai/models/gpt-image-2.\n\n## When to use\n\n- The user asks for gpt image 2 api integration, examples, SDK installation, CLI calls, or agent workflow setup.\n- The user needs RunAPI SDK or CLI guidance for GPT Image 2.\n- The user asks about GPT Image 2 pricing, rate limits, commercial usage, or variant choice.\n\n## Workflow\n\n- Prefer the SDK repository at https://github.com/runapi-ai/gpt-image-2-sdk for application code.\n- Use https://runapi.ai/docs#sdk-gpt-image-2 for SDK docs and https://runapi.ai/docs#gpt-image-2 for model endpoint details.\n- For CLI flows, pass JSON request bodies through `--input` or `--input-file`; do not invent hand-written flags for every model parameter.\n- Keep API keys in `RUNAPI_API_KEY` or the RunAPI CLI config; never commit secrets.\n\n## Routing\n\n- Main gpt image 2 api page: https://runapi.ai/models/gpt-image-2\n- Default pricing/rate-limit/commercial page: https://runapi.ai/models/gpt-image-2/text-to-image\n- Provider comparison: https://runapi.ai/providers/openai\n- Full catalog: https://runapi.ai/models\n\n## Variants\n\n- [GPT Image 2 text to image](https://runapi.ai/models/gpt-image-2/text-to-image)\n- [GPT Image 2 image to image](https://runapi.ai/models/gpt-image-2/image-to-image)\n\nFile v0.2.3:_meta.json\n\n{\n \"ownerId\": \"kn70me4rk7jqjt92evshjeb5z18768g7\",\n \"slug\": \"runapi-gpt-image-2\",\n \"version\": \"0.2.3\",\n \"publishedAt\": 1779433607219\n}","readmeExcerpt":"Skill: gpt-image-2 Owner: runapi-ai Summary: Generate and edit images with GPT Image 2 through RunAPI. Use when the user asks an agent to create, edit, or transform images with GPT Image 2. Default to the RunAPI CLI for one-off generation; use SDKs only when the user is integrating RunAPI into an app or backend. Tags: latest:0.2.9 Version history: v0.2.9 | 2026-08-12T06:07:52.665Z | user Changed - Generate the gpt-im","codeSnippets":[],"executableExamples":[{"language":"shell","snippet":"curl --fail --location https://runapi.ai/docs/api/gpt-image-2/.md --output contract.md"},{"language":"shell","snippet":"runapi auth status > auth.json\njq -e '.authenticated == true' auth.json\nrunapi gpt-image-2 --help\nrunapi gpt-image-2 --help\ncurl --fail --location https://runapi.ai/docs/api/gpt-image-2/.md --output contract.md"},{"language":"shell","snippet":"jq empty request.json"},{"language":"shell","snippet":"runapi gpt-image-2 --async --input-file request.json > task.json\ntask_id=\"$(jq -er '.id' task.json)\""},{"language":"shell","snippet":"runapi wait \"$task_id\" --service gpt-image-2 --action > result.json"},{"language":"shell","snippet":"curl --fail --location --output "}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: gpt-image-2\ndescription: \"Generate and edit images with GPT Image 2 through RunAPI. Use when the user asks an agent to create, edit, or transform images with GPT Image 2. Default to the RunAPI CLI for one-off generation; use SDKs only when the user is integrating RunAPI into an app or backend.\"\ndocumentation: https://runapi.ai/models/gpt-image-2.md\nprovider_page: https://runapi.ai/providers/openai.md\ncatalog: https://runapi.ai/models.md\nmetadata:\n openclaw:\n homepage: https://runapi.ai/models/gpt-image-2\n requires:\n bins:\n - runapi\n install:\n - kind: brew\n formula: runapi-ai/tap/runapi\n bins:\n - runapi\n envVars:\n - name: RUNAPI_API_KEY\n required: false\n description: Optional RunAPI API key; agents should prefer environment auth or saved CLI config. Browser login is interactive fallback only.\n---\n\n# GPT Image 2 on RunAPI\n\n## Choose route\n\n- For a one-off artifact or result, use the registered `gpt-image-2` service in the `runapi` CLI. If the installed command catalog does not list it, stop and report the missing service instead of inventing a command.\n- For an app, backend, worker, library, webhook pipeline, or production codebase, go directly to **Integrate with SDK**. Never shell out to the CLI as the production runtime.\n\n## Discover contract\n\nAuthenticate, then inspect the installed command catalog and the selected operation's current contract:\n\n```shell\nrunapi auth status > auth.json\njq -e '.authenticated == true' auth.json\nrunapi gpt-image-2 --help\nrunapi gpt-image-2 --help\ncurl --fail --location https://runapi.ai/docs/api/gpt-image-2/.md --output contract.md\n```\n\nIf authentication is false, stop before submitting. Ask the user to provide a valid `RUNAPI_API_KEY`, or import a user-provided key from stdin with `runapi auth import-token --token -`; use interactive browser login only when the user explicitly requests it. Choose `` only from service help. Treat command help as authoritative for the installed operation, model, and top-level field roster. Treat its API Reference as authoritative for the complete request schema, nested fields, conditional rules, task behavior, and response variants. If the two surfaces disagree, stop and report the contract mismatch instead of guessing.\n\n## Build request\n\nCreate `request.json` as valid JSON using only fields accepted by the discovered operation contract. For the chosen model and values, evaluate every applicable conditional rule as a set: satisfy every required field, omit every forbidden field, and stop on unresolved contradictions.\n\nTraverse nested objects and arrays before execution. Close every relationship stated by the discovered contract, including uniqueness constraints and cross-references between nested values.\n\nFor a discovered local media input, including file-typed fields and top-level media URL fields, put an agent-readable local file path directly in `request.json`. The CLI consumes file "},{"path":"_meta.json","content":"{\n \"ownerId\": \"kn70me4rk7jqjt92evshjeb5z18768g7\",\n \"slug\": \"runapi-gpt-image-2\",\n \"version\": \"0.2.9\",\n \"publishedAt\": 1786514872665\n}"},{"path":"skill-card.md","content":"## Description:\n\nGenerate and edit images with GPT Image 2 through RunAPI. Use when the user asks an agent to create, edit, or transform images with GPT Image 2. Default to the RunAPI CLI for one-off generation; use SDKs only when the user is integrating RunAPI into an app or backend.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[runapi-ai](https://clawhub.ai/user/runapi-ai)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and agents use this skill to generate, edit, or transform images with GPT Image 2 through RunAPI. The skill supports one-off CLI generation and SDK-oriented integration for applications, backends, workers, and pipelines.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: RunAPI credentials may be exposed in shared workspaces.\n\nMitigation: Prefer environment authentication or saved CLI configuration, keep API keys out of shared files, and import user-provided tokens through stdin when needed.\n\nRisk: The workflow can create paid API tasks.\n\nMitigation: Authenticate first, validate the request contract before submission, submit once, and retry only when evidence confirms that no task was created and no billing occurred.\n\nRisk: Intermediate JSON files and generated images may contain sensitive task or output data.\n\nMitigation: Store results in an appropriate workspace, review outputs before sharing, and verify downloaded files are non-empty images with the expected MIME type.\n\n## Reference(s):\n\n- [ClawHub skill release](https://clawhub.ai/runapi-ai/skills/runapi-gpt-image-2)\n- [RunAPI GPT Image 2 homepage](https://runapi.ai/models/gpt-image-2)\n- [Model overview, pricing, and rate limits](https://runapi.ai/models/gpt-image-2.md)\n- [Provider overview](https://runapi.ai/providers/openai.md)\n- [Full model catalog](https://runapi.ai/models.md)\n- [SDK integration](https://github.com/runapi-ai/gpt-image-2-sdk)\n\n## Skill Output:\n\n**Output Type(s):** [Guidance, Shell commands, Configuration, Code, Files]\n\n**Output Format:** [Markdown guidance with shell commands, JSON request and response files, and generated image files when tasks complete]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Requires the RunAPI CLI and optional RUNAPI_API_KEY; generated media should be downloaded, checked for non-empty content, and verified against the expected image MIME type.]\n\n## Skill Version(s):\n\n0.2.9 (source: server release evidence)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment."}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"Generate and edit images with GPT Image 2 through RunAPI. Use when the user asks an agent to create, edit, or transform images with GPT Image 2. Default to the RunAPI CLI for one-off generation; use SDKs only when the user is integrating RunAPI into an app or backend. Skill: gpt-image-2 Owner: runapi-ai Summary: Generate and edit images with GPT Image 2 through RunAPI. Use when the user asks an agent to create, edit, or transform images with GPT Image 2. Default to the RunAPI CLI for one-off generation; use SDKs only when the user is integrating RunAPI into an app or backend. Tags: latest:0.2.9 Version history: v0.2.9 | 2026-08-12T06:07:52.665Z | user Changed - Generate the gpt-im","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":1223,"uniquenessScore":46,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-11T15:43:46.837Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-10-11T15:43:46.837Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-11T17:41:50.482Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}