GPT-5 Image is a combined profile that brings OpenAI’s GPT-5 language model together with GPT Image 1. The language component interprets requirements and source material; the image component creates the visual result. Its published description emphasizes reasoning, instruction following, text rendering and detailed image editing. The profile suits tasks where a visual asset and its written interpretation need to follow the same brief.
Give the model the purpose of the image, the intended audience and the content that must appear. Separate facts that need to be represented accurately from choices of composition or visual treatment. A diagram brief can identify the entities and relationships, then specify the labels, arrangement and style. A poster brief can define the event information, hierarchy and scene, with the exact words that belong in the visual.
For example, prepare a poster concept for a community science event. Supply the event facts, ask for a short explanation of the layout and request an image that uses a clear title with supporting visual elements. Specify which words should appear in the image and which belong only in the accompanying description. Review the written explanation and generated poster together, so a sensible layout plan is checked against the actual visible result.
Text, images and files such as PDFs are documented inputs to the combined profile. A document can supply the requirements for a visual or the information that needs summarizing. Reference images can establish a subject, product, location or layout. Name each source and explain its role before describing the target, especially when a reference contains content that should be preserved and content that should change.
For a revision, identify the source image and describe the requested change precisely. A product-scene edit might change the setting while retaining the item’s form and visible labeling. A visual explanation might replace one element while keeping the surrounding relationships. State the preservation requirements in the brief and inspect the actual image for the details that matter.
The exact combined profile’s card permits up to sixteen reference images for editing. Keep references relevant to the task and explain which features each contributes. When several images show different lighting, viewpoints or treatments, identify the intended composition instead of asking every source to dominate the result. Retain the sources with the completed image so a later correction can refer to the same material.
The published profile includes text rendering among its capabilities. Give exact wording, punctuation and placement for important text, and specify its relation to objects or other labels. Check every required word and number in the returned image at its intended display size. For a diagram, also check that lines, positions and groupings express the relationship described by the written source.
The combined profile publishes a 400,000-token context window and up to 128,000 completion tokens. These allowances describe the input and generated completion, not a particular pixel size or image count. Use the context for relevant requirements, references and conversation state, and leave room for the requested output. Label long source material so the model can connect each instruction to the right passage.
Its documented text-output contract supports structured results through a JSON schema. A written response can define the fields needed to describe a concept, summarize a requirement or identify a requested change. Validate those fields and their values against the source before an application consumes them. The combined profile does not expose application function calling, even though its named language-and-image arrangement carries out visual generation internally.
The chat request schema can select text and image output modalities. State the actual written and visual deliverables in the brief, then inspect the completed response for both. Image configuration is specific to the exact model and interface. Keep the accepted settings with the request, and use only controls documented for that combined profile; a direct image-component interface can have a different arrangement of fields and capabilities.
The image component named for this profile is GPT Image 1. Its direct image-generation profile handles image-focused workloads, while GPT-5 Image joins that capability with GPT-5 language processing. GPT-5 Image Mini is a separate combination of GPT-5 Mini and GPT Image 1 Mini. Keep the selected profile’s identity with the source material and output settings rather than treating similarly named combinations as the same model.
For a conversation that includes several revisions, carry forward the relevant written requirements and source references. State the specific correction in the newest brief, such as moving a label, changing an object or simplifying the composition. Avoid an undirected request to make everything better when the useful change is already visible in the returned asset.
Retain the written response and every actual image artifact supplied by the completion. Save the images in their reported format, together with the prompt, source references and chosen settings. Inspect the image itself for composition, subject details and text; compare accompanying prose with the evidence it describes. A useful finished result joins the written requirements with a visual that can be opened, reviewed and placed in the intended document, page or creative workflow.
", "aboutText": "GPT-5 Image is a combined profile that brings OpenAI’s GPT-5 language model together with GPT Image 1. The language component interprets requirements and source material; the image component creates the visual result. Its published description emphasizes reasoning, instruction following, text rendering and detailed image editing. The profile suits tasks where a visual asset and its written interpretation need to follow the same brief.\n\n### Interpret the brief and create the asset\n\nGive the model the purpose of the image, the intended audience and the content that must appear. Separate facts that need to be represented accurately from choices of composition or visual treatment. A diagram brief can identify the entities and relationships, then specify the labels, arrangement and style. A poster brief can define the event information, hierarchy and scene, with the exact words that belong in the visual.\n\nFor example, prepare a poster concept for a community science event. Supply the event facts, ask for a short explanation of the layout and request an image that uses a clear title with supporting visual elements. Specify which words should appear in the image and which belong only in the accompanying description. Review the written explanation and generated poster together, so a sensible layout plan is checked against the actual visible result.\n\nText, images and files such as PDFs are documented inputs to the combined profile. A document can supply the requirements for a visual or the information that needs summarizing. Reference images can establish a subject, product, location or layout. Name each source and explain its role before describing the target, especially when a reference contains content that should be preserved and content that should change.\n\n### Reference-led edits and text rendering\n\nFor a revision, identify the source image and describe the requested change precisely. A product-scene edit might change the setting while retaining the item’s form and visible labeling. A visual explanation might replace one element while keeping the surrounding relationships. State the preservation requirements in the brief and inspect the actual image for the details that matter.\n\nThe exact combined profile’s card permits up to sixteen reference images for editing. Keep references relevant to the task and explain which features each contributes. When several images show different lighting, viewpoints or treatments, identify the intended composition instead of asking every source to dominate the result. Retain the sources with the completed image so a later correction can refer to the same material.\n\nThe published profile includes text rendering among its capabilities. Give exact wording, punctuation and placement for important text, and specify its relation to objects or other labels. Check every required word and number in the returned image at its intended display size. For a diagram, also check that lines, positions and groupings express the relationship described by the written source.\n\n### Context and response shape\n\nThe combined profile publishes a 400,000-token context window and up to 128,000 completion tokens. These allowances describe the input and generated completion, not a particular pixel size or image count. Use the context for relevant requirements, references and conversation state, and leave room for the requested output. Label long source material so the model can connect each instruction to the right passage.\n\nIts documented text-output contract supports structured results through a JSON schema. A written response can define the fields needed to describe a concept, summarize a requirement or identify a requested change. Validate those fields and their values against the source before an application consumes them. The combined profile does not expose application function calling, even though its named language-and-image arrangement carries out visual generation internally.\n\nThe chat request schema can select text and image output modalities. State the actual written and visual deliverables in the brief, then inspect the completed response for both. Image configuration is specific to the exact model and interface. Keep the accepted settings with the request, and use only controls documented for that combined profile; a direct image-component interface can have a different arrangement of fields and capabilities.\n\n### Use the named composition deliberately\n\nThe image component named for this profile is GPT Image 1. Its direct image-generation profile handles image-focused workloads, while GPT-5 Image joins that capability with GPT-5 language processing. GPT-5 Image Mini is a separate combination of GPT-5 Mini and GPT Image 1 Mini. Keep the selected profile’s identity with the source material and output settings rather than treating similarly named combinations as the same model.\n\nFor a conversation that includes several revisions, carry forward the relevant written requirements and source references. State the specific correction in the newest brief, such as moving a label, changing an object or simplifying the composition. Avoid an undirected request to make everything better when the useful change is already visible in the returned asset.\n\n### Keep and review the completed result\n\nRetain the written response and every actual image artifact supplied by the completion. Save the images in their reported format, together with the prompt, source references and chosen settings. Inspect the image itself for composition, subject details and text; compare accompanying prose with the evidence it describes. A useful finished result joins the written requirements with a visual that can be opened, reviewed and placed in the intended document, page or creative workflow.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Simplify a community-event poster\n\nEdit the supplied community science poster. Preserve the exact event title, date, venue and central telescope illustration. Remove the small decorative stars around the footer, increase the empty space around the title and keep the original portrait layout and two-color palette. Add no new event facts or text. Return the revised poster image.A revised poster image retaining all event wording and the telescope while simplifying the requested areas.Check every event word and number against the source and confirm that only the named decorative elements were removed.openai/gpt-5-imageGPT-5 Image combines OpenAI’s GPT-5 language and reasoning capabilities with GPT Image 1 for image generation and reference-led editing. It accepts text, images and documents and returns text and images, connecting a written brief with a visual result.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
GPT-5 Image is a combined profile that brings OpenAI’s GPT-5 language model together with GPT Image 1. The language component interprets requirements and source material; the image component creates the visual result. Its published description emphasizes reasoning, instruction following, text rendering and detailed image editing. The profile suits tasks where a visual asset and its written interpretation need to follow the same brief.
Give the model the purpose of the image, the intended audience and the content that must appear. Separate facts that need to be represented accurately from choices of composition or visual treatment. A diagram brief can identify the entities and relationships, then specify the labels, arrangement and style. A poster brief can define the event information, hierarchy and scene, with the exact words that belong in the visual.
For example, prepare a poster concept for a community science event. Supply the event facts, ask for a short explanation of the layout and request an image that uses a clear title with supporting visual elements. Specify which words should appear in the image and which belong only in the accompanying description. Review the written explanation and generated poster together, so a sensible layout plan is checked against the actual visible result.
Text, images and files such as PDFs are documented inputs to the combined profile. A document can supply the requirements for a visual or the information that needs summarizing. Reference images can establish a subject, product, location or layout. Name each source and explain its role before describing the target, especially when a reference contains content that should be preserved and content that should change.
For a revision, identify the source image and describe the requested change precisely. A product-scene edit might change the setting while retaining the item’s form and visible labeling. A visual explanation might replace one element while keeping the surrounding relationships. State the preservation requirements in the brief and inspect the actual image for the details that matter.
The exact combined profile’s card permits up to sixteen reference images for editing. Keep references relevant to the task and explain which features each contributes. When several images show different lighting, viewpoints or treatments, identify the intended composition instead of asking every source to dominate the result. Retain the sources with the completed image so a later correction can refer to the same material.
The published profile includes text rendering among its capabilities. Give exact wording, punctuation and placement for important text, and specify its relation to objects or other labels. Check every required word and number in the returned image at its intended display size. For a diagram, also check that lines, positions and groupings express the relationship described by the written source.
The combined profile publishes a 400,000-token context window and up to 128,000 completion tokens. These allowances describe the input and generated completion, not a particular pixel size or image count. Use the context for relevant requirements, references and conversation state, and leave room for the requested output. Label long source material so the model can connect each instruction to the right passage.
Its documented text-output contract supports structured results through a JSON schema. A written response can define the fields needed to describe a concept, summarize a requirement or identify a requested change. Validate those fields and their values against the source before an application consumes them. The combined profile does not expose application function calling, even though its named language-and-image arrangement carries out visual generation internally.
The chat request schema can select text and image output modalities. State the actual written and visual deliverables in the brief, then inspect the completed response for both. Image configuration is specific to the exact model and interface. Keep the accepted settings with the request, and use only controls documented for that combined profile; a direct image-component interface can have a different arrangement of fields and capabilities.
The image component named for this profile is GPT Image 1. Its direct image-generation profile handles image-focused workloads, while GPT-5 Image joins that capability with GPT-5 language processing. GPT-5 Image Mini is a separate combination of GPT-5 Mini and GPT Image 1 Mini. Keep the selected profile’s identity with the source material and output settings rather than treating similarly named combinations as the same model.
For a conversation that includes several revisions, carry forward the relevant written requirements and source references. State the specific correction in the newest brief, such as moving a label, changing an object or simplifying the composition. Avoid an undirected request to make everything better when the useful change is already visible in the returned asset.
Retain the written response and every actual image artifact supplied by the completion. Save the images in their reported format, together with the prompt, source references and chosen settings. Inspect the image itself for composition, subject details and text; compare accompanying prose with the evidence it describes. A useful finished result joins the written requirements with a visual that can be opened, reviewed and placed in the intended document, page or creative workflow.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits openai/gpt-5-image | Default— |
Fieldmessages | Typemessage[] | RequirementRequired | Values & limits Minimum items: 1 | Default— |
Fieldmessages[].role | Typestring | RequirementRequired | Values & limits Examples: system, user, assistant, tool, function Conditions: These roles are explicitly represented by Source compatibility types; the exact model role set remains model-specific. Model-specific | Default— |
Fieldmessages[].content | Typestring|content_part[]|null | RequirementOptional | Values & limits | Default— |
Fieldmessages[].tool_calls | Typetool_call[] | RequirementOptional | Values & limits | Default— |
Fieldmessages[].tool_call_id | Typestring | RequirementOptional | Values & limits Applies when: role=tool; use actual returned ID | Default— |
Fieldmessages[].name | Typestring | RequirementOptional | Values & limits | Default— |
Fieldmessages[].reasoning_content | Typestring | RequirementOptional | Values & limits Applies when: Round-trip actual returned reasoning where this model uses it | Default— |
Fieldmessages[].reasoning_details | Typeobject|array | RequirementOptional | Values & limits Model-specific | Default— |
Fieldmax_tokens | Typeinteger | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
Fieldmax_completion_tokens | Typeinteger | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
Fieldstream_options.include_usage | Typeboolean | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtemperature | Typenumber | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtop_p | Typenumber | RequirementOptional | Values & limits Model-specific | Default— |
Fieldstop | Typestring|string[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtools | Typefunction_tool[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtools[].type | Typestring | RequirementOptional | Values & limits function Model-specific | Default— |
Fieldtools[].function.name | Typestring | RequirementRequired | Values & limits Applies when: function tool supplied | Default— |
Fieldtools[].function.description | Typestring | RequirementOptional | Values & limits | Default— |
Fieldtools[].function.parameters | TypeJSON_schema | RequirementOptional | Values & limits | Default— |
Fieldtool_choice | Typestring|object | RequirementOptional | Values & limits Model-specific | Default— |
Fieldparallel_tool_calls | Typeboolean | RequirementOptional | Values & limits Model-specific | Default— |
Fieldresponse_format | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldreasoning_effort | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
Fieldreasoning | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldservice_tier | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
Fieldinstructions | Typestring | RequirementOptional | Values & limits Compatibility field | Default— |
Fieldfunctions | Typefunction[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldfunction_call | Typestring|object | RequirementOptional | Values & limits Model-specific | Default— |
Fieldprompt_cache_options | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldmodalities | Typestring[] | RequirementOptional | Values & limits text | Default— |
Fieldprovider | Typeobject | RequirementOptional | Values & limits Conditions: provider.options is rejected on this Ultra text route | Default— |
Fieldcache_control.ttl | Typestring | RequirementOptional | Values & limits Conditions: 1h is rejected in actual prompt-cache locations | Default— |
Text · UTF8 text
messages[].content
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, messages |
Parametermaterial_types | Contracttext |
Parametermessages | Contractmessage array with role/content shape |
Parameterfile_material | Contractactual UTF-8 document inserted as literal text; no file ID inferred |
Parameteroptional_controls | Contractstream, temperature, top_p, stop, max_tokens, max_completion_tokens, reasoning, response_format, tools, tool_choice |
Parametercontrol_scope | Contractmodel-specific; user function tools differ from hosted tools |
Parameteroutput_modalities | Contracttext |
Parameterhosted_operations | Contractfalse |
Parametermultimodal_input_binding | Contractnull |
Lifecycle: synchronous_or_streamed
Send exact model ID with messages.
Context length is not an output cap.
A text file may supply literal text; image/audio/file-object inputs need exact binding.
Tariff references do not add request options. Supported parameters are listed for the selected method.
Match each charge to the conditions shown. Use one rate for each set of alternative configurations.
| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
|---|---|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.02 / 1K tokens Output · Output tokens $0.02 / 1K tokens Input · Cache read $0.0025 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens Output · Image output tokens $0.08 / 1K image tokens |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.02 / 1K tokens Output · Output tokens $0.02 / 1K tokens Input · Cache read $0.0025 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Model-level reference schedules do not change method selection, quotes or charges. Active charges use the selected Ailoot method rates.
| Configuration | Billing conditions | Charge |
|---|---|---|
| ConfigurationOpenAI: GPT-5 Image · Default configuration | Billing conditionsDefault configuration | Charge Input · Input tokens $0.02 / 1K tokens Output · Output tokens $0.02 / 1K tokens Output · Output image $0.08 / 1K tokens Output · Web search $0.02 per search Input · Cache read $0.0025 / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "openai/gpt-5-image", "messages": [{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}]}')\n\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path("result.json").read_text())\nfor x in r.get("choices",[]):\n if x.get("message",{}).get("content"): print(x["message"]["content"])\nPY_RESULT\nfrom openai import OpenAI\nimport os\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nresult=client.chat.completions.create(model='openai/gpt-5-image',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}])\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(result.to_dict(mode="json"))\nfrom openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nwith client.chat.completions.stream(model='openai/gpt-5-image',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:\n with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:\n for event in stream:\n payload=event.to_dict(mode="json")\n log.write(json.dumps(payload,ensure_ascii=False)+"\\n"); log.flush()\n print(json.dumps(payload,ensure_ascii=False))\n final=stream.get_final_completion()\n save_result(final.to_dict(mode="json"),"stream-result")\njson or SSE
Keep every complete returned response, file and content part.
Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.
Keep request/response IDs and headers. No generic text job retrieval URL is supplied.
| Field | Type |
|---|---|
Fieldchoices[].index | Typeinteger |
Fieldchoices[].message.content | Typestring|null |
Fieldchoices[].message.tool_calls | Typetool_call[] |
Fieldchoices[].message.reasoning_content | Typestring |
Fieldchoices[].message.reasoning_details | Typeobject|array |
Fieldchoices[].finish_reason | Typestring|null |
Fieldusage | Typeobject |
| Response | Condition | Next step |
|---|---|---|
Response400 · invalid_request_error | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |
Ailoot Ultra openai/gpt-5-image
/v1/images
openai/gpt-5-imageGPT-5 Image combines OpenAI’s GPT-5 language and reasoning capabilities with GPT Image 1 for image generation and reference-led editing. It accepts text, images and documents and returns text and images, connecting a written brief with a visual result.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
GPT-5 Image is a combined profile that brings OpenAI’s GPT-5 language model together with GPT Image 1. The language component interprets requirements and source material; the image component creates the visual result. Its published description emphasizes reasoning, instruction following, text rendering and detailed image editing. The profile suits tasks where a visual asset and its written interpretation need to follow the same brief.
Give the model the purpose of the image, the intended audience and the content that must appear. Separate facts that need to be represented accurately from choices of composition or visual treatment. A diagram brief can identify the entities and relationships, then specify the labels, arrangement and style. A poster brief can define the event information, hierarchy and scene, with the exact words that belong in the visual.
For example, prepare a poster concept for a community science event. Supply the event facts, ask for a short explanation of the layout and request an image that uses a clear title with supporting visual elements. Specify which words should appear in the image and which belong only in the accompanying description. Review the written explanation and generated poster together, so a sensible layout plan is checked against the actual visible result.
Text, images and files such as PDFs are documented inputs to the combined profile. A document can supply the requirements for a visual or the information that needs summarizing. Reference images can establish a subject, product, location or layout. Name each source and explain its role before describing the target, especially when a reference contains content that should be preserved and content that should change.
For a revision, identify the source image and describe the requested change precisely. A product-scene edit might change the setting while retaining the item’s form and visible labeling. A visual explanation might replace one element while keeping the surrounding relationships. State the preservation requirements in the brief and inspect the actual image for the details that matter.
The exact combined profile’s card permits up to sixteen reference images for editing. Keep references relevant to the task and explain which features each contributes. When several images show different lighting, viewpoints or treatments, identify the intended composition instead of asking every source to dominate the result. Retain the sources with the completed image so a later correction can refer to the same material.
The published profile includes text rendering among its capabilities. Give exact wording, punctuation and placement for important text, and specify its relation to objects or other labels. Check every required word and number in the returned image at its intended display size. For a diagram, also check that lines, positions and groupings express the relationship described by the written source.
The combined profile publishes a 400,000-token context window and up to 128,000 completion tokens. These allowances describe the input and generated completion, not a particular pixel size or image count. Use the context for relevant requirements, references and conversation state, and leave room for the requested output. Label long source material so the model can connect each instruction to the right passage.
Its documented text-output contract supports structured results through a JSON schema. A written response can define the fields needed to describe a concept, summarize a requirement or identify a requested change. Validate those fields and their values against the source before an application consumes them. The combined profile does not expose application function calling, even though its named language-and-image arrangement carries out visual generation internally.
The chat request schema can select text and image output modalities. State the actual written and visual deliverables in the brief, then inspect the completed response for both. Image configuration is specific to the exact model and interface. Keep the accepted settings with the request, and use only controls documented for that combined profile; a direct image-component interface can have a different arrangement of fields and capabilities.
The image component named for this profile is GPT Image 1. Its direct image-generation profile handles image-focused workloads, while GPT-5 Image joins that capability with GPT-5 language processing. GPT-5 Image Mini is a separate combination of GPT-5 Mini and GPT Image 1 Mini. Keep the selected profile’s identity with the source material and output settings rather than treating similarly named combinations as the same model.
For a conversation that includes several revisions, carry forward the relevant written requirements and source references. State the specific correction in the newest brief, such as moving a label, changing an object or simplifying the composition. Avoid an undirected request to make everything better when the useful change is already visible in the returned asset.
Retain the written response and every actual image artifact supplied by the completion. Save the images in their reported format, together with the prompt, source references and chosen settings. Inspect the image itself for composition, subject details and text; compare accompanying prose with the evidence it describes. A useful finished result joins the written requirements with a visual that can be opened, reviewed and placed in the intended document, page or creative workflow.
POST /v1/images/generationstext, imageimage| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits openai/gpt-5-image | Default— |
Fieldprompt | Typestring | RequirementRequired | Values & limits Minimum length: 1 | Default— |
Fieldaspect_ratio | Typestring | RequirementOptional | Values & limits 1:1, 3:2, 2:3, auto | Default— |
Fieldquality | Typestring | RequirementOptional | Values & limits auto, low, medium, high | Default— |
Fieldbackground | Typestring | RequirementOptional | Values & limits auto, transparent, opaque | Default— |
Fieldn | Typeinteger | RequirementOptional | Values & limits Minimum: 1 Maximum: 10 | Default— |
Fieldinput_references | Typearray | RequirementOptional | Values & limits Minimum items: 0 Maximum items: 16 | Default— |
Fieldoutput_compression | Typeinteger | RequirementOptional | Values & limits Minimum: 0 Maximum: 100 | Default— |
Fieldprovider | Typeobject | RequirementOptional | Values & limits | Default— |
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, prompt |
Parametermaterial_types | Contracttext, image |
Lifecycle: synchronous_result_then_owned_library
GET /v1/media/tasks/{task_id} · actual returned task_id or media library record
GET /v1/media/assets/{asset_id}/content
GET /v1/media/assets
GET /v1/media/assets/{asset_id}
The displayed rates estimate the cost before generation. The final charge is calculated from the cost recorded for the original generation. Measured output duration and forecast quantities are not the final billable quantity.
Tariff references do not add request options. Supported parameters are listed for the selected method.
Match each charge to the conditions shown. Use one rate for each set of alternative configurations.
| Configuration | Rate schedule | Forecast quantity | Charge |
|---|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Forecast quantity— | Charge Input · Input tokens · Estimate for comparison only — / 1K tokens Output · Output tokens · Estimate for comparison only — / 1K tokens Input · Cache read · Estimate for comparison only — / 1K tokens Input · Cache write · Estimate for comparison only — / 1K tokens Input · Cache write, 1 hour · Estimate for comparison only — / 1K tokens |
| ConfigurationEstimated generation cost | Rate schedule— | Forecast quantityone generation estimate | Charge Output · Estimated generation cost · Estimate for comparison only $0.32768 estimate before generation This estimate is not an additional charge or a fixed rate for the completed generation. |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\nexport AILOOT_API_KEY\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np={'model': 'openai/gpt-5-image', 'prompt': 'a red panda astronaut floating in space, studio lighting'}\n\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/images/generations \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json, os, subprocess\nfrom pathlib import Path\nfrom urllib.parse import urlsplit, urljoin\n\ndef save_images(items):\n if not items: raise SystemExit("No completed images; retain the full response")\n for index, item in enumerate(items):\n encoded=item.get("b64_json")\n uri=item.get("url", "")\n if not encoded and uri.startswith("data:image/"):\n header, separator, encoded=uri.partition(",")\n if not separator or ";base64" not in header: raise SystemExit("Unsupported image data URI")\n if encoded:\n raw=base64.b64decode(encoded,validate=True)\n elif uri:\n uri=urljoin("https://api.ailoot.ai",uri)\n parsed=urlsplit(uri)\n if parsed.scheme!="https" or not parsed.netloc or parsed.username or parsed.password:\n raise SystemExit("Invalid returned image URL")\n owned=parsed.netloc=="api.ailoot.ai" and parsed.path.startswith("/v1/media/assets/") and parsed.path.endswith("/content")\n args=["curl","--fail-with-body","--silent","--show-error",uri]\n if owned: args += ["-H","Authorization: Bearer "+os.environ["AILOOT_API_KEY"]]\n temporary=Path(f"image-{index}.bin")\n subprocess.run(args+["-o",str(temporary)],check=True)\n raw=temporary.read_bytes()\n temporary.unlink()\n else: raise SystemExit("Image has neither bytes nor URL")\n if not raw: raise SystemExit("Empty image result")\n ext="png" if raw.startswith(b"\\x89PNG") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else "svg" if raw.lstrip().startswith((b"<svg",b"<?xml")) else "bin"\n Path(f"image-{index}.{ext}").write_bytes(raw)\n print("Every returned image saved; complete response metadata retained")\nsave_images(json.loads(Path("result.json").read_text())["data"])\nPY_RESULT\nDownload each returned image or save its Base64 contents
GET /v1/media/tasks/{task_id}GET /v1/media/assets/{asset_id}/contentGET /v1/media/assetsGET /v1/media/assets/{asset_id}set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/media/assets \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -o owned-assets.json\n# Preserve every returned asset and follow its exact signed content URL. Do not construct a signed token.\nSave every completed image; retrieve each returned URL or decode its Base64 contents.
Retain the complete response and headers, every actual output, original returned identifiers and all usage fields. Recover the original operation without submitting creation again.
Keep the returned X-Client-Request-ID for reconciliation. Read only actual returned task_id/asset_id values or the owned media library; never build a task URL from the operation ID and never resubmit creation.
| Field | Type |
|---|---|
Fieldcreated | Type |
Fielddata[].url | Type |
Fielddata[].b64_json | Type |
Fieldusage | Type |
Ailoot Ultra openai/gpt-5-image
/v1/images
openai/gpt-5-imageGPT-5 Image combines OpenAI’s GPT-5 language and reasoning capabilities with GPT Image 1 for image generation and reference-led editing. It accepts text, images and documents and returns text and images, connecting a written brief with a visual result.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
GPT-5 Image is a combined profile that brings OpenAI’s GPT-5 language model together with GPT Image 1. The language component interprets requirements and source material; the image component creates the visual result. Its published description emphasizes reasoning, instruction following, text rendering and detailed image editing. The profile suits tasks where a visual asset and its written interpretation need to follow the same brief.
Give the model the purpose of the image, the intended audience and the content that must appear. Separate facts that need to be represented accurately from choices of composition or visual treatment. A diagram brief can identify the entities and relationships, then specify the labels, arrangement and style. A poster brief can define the event information, hierarchy and scene, with the exact words that belong in the visual.
For example, prepare a poster concept for a community science event. Supply the event facts, ask for a short explanation of the layout and request an image that uses a clear title with supporting visual elements. Specify which words should appear in the image and which belong only in the accompanying description. Review the written explanation and generated poster together, so a sensible layout plan is checked against the actual visible result.
Text, images and files such as PDFs are documented inputs to the combined profile. A document can supply the requirements for a visual or the information that needs summarizing. Reference images can establish a subject, product, location or layout. Name each source and explain its role before describing the target, especially when a reference contains content that should be preserved and content that should change.
For a revision, identify the source image and describe the requested change precisely. A product-scene edit might change the setting while retaining the item’s form and visible labeling. A visual explanation might replace one element while keeping the surrounding relationships. State the preservation requirements in the brief and inspect the actual image for the details that matter.
The exact combined profile’s card permits up to sixteen reference images for editing. Keep references relevant to the task and explain which features each contributes. When several images show different lighting, viewpoints or treatments, identify the intended composition instead of asking every source to dominate the result. Retain the sources with the completed image so a later correction can refer to the same material.
The published profile includes text rendering among its capabilities. Give exact wording, punctuation and placement for important text, and specify its relation to objects or other labels. Check every required word and number in the returned image at its intended display size. For a diagram, also check that lines, positions and groupings express the relationship described by the written source.
The combined profile publishes a 400,000-token context window and up to 128,000 completion tokens. These allowances describe the input and generated completion, not a particular pixel size or image count. Use the context for relevant requirements, references and conversation state, and leave room for the requested output. Label long source material so the model can connect each instruction to the right passage.
Its documented text-output contract supports structured results through a JSON schema. A written response can define the fields needed to describe a concept, summarize a requirement or identify a requested change. Validate those fields and their values against the source before an application consumes them. The combined profile does not expose application function calling, even though its named language-and-image arrangement carries out visual generation internally.
The chat request schema can select text and image output modalities. State the actual written and visual deliverables in the brief, then inspect the completed response for both. Image configuration is specific to the exact model and interface. Keep the accepted settings with the request, and use only controls documented for that combined profile; a direct image-component interface can have a different arrangement of fields and capabilities.
The image component named for this profile is GPT Image 1. Its direct image-generation profile handles image-focused workloads, while GPT-5 Image joins that capability with GPT-5 language processing. GPT-5 Image Mini is a separate combination of GPT-5 Mini and GPT Image 1 Mini. Keep the selected profile’s identity with the source material and output settings rather than treating similarly named combinations as the same model.
For a conversation that includes several revisions, carry forward the relevant written requirements and source references. State the specific correction in the newest brief, such as moving a label, changing an object or simplifying the composition. Avoid an undirected request to make everything better when the useful change is already visible in the returned asset.
Retain the written response and every actual image artifact supplied by the completion. Save the images in their reported format, together with the prompt, source references and chosen settings. Inspect the image itself for composition, subject details and text; compare accompanying prose with the evidence it describes. A useful finished result joins the written requirements with a visual that can be opened, reviewed and placed in the intended document, page or creative workflow.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits openai/gpt-5-image | Default— |
Fieldmessages | Typemessage[] | RequirementRequired | Values & limits | Default— |
Fieldmessages[].role | Typestring | RequirementRequired | Values & limits user, assistant | Default— |
Fieldmessages[].content | Typestring | RequirementRequired | Values & limits | Default— |
Fieldmax_tokens | Typeinteger | RequirementRequired | Values & limits | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
Text · UTF-8 text
messages[].content string
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, messages, max_tokens |
Parameteroptional_controls | Contractstream |
Parametermaterial_types | Contracttext |
Parametertext_file_material | ContractRead the actual UTF-8 document and put its text in the indicated input or message content string. |
Lifecycle: synchronous_or_streamed
Tariff references do not add request options. Supported parameters are listed for the selected method.
Match each charge to the conditions shown. Use one rate for each set of alternative configurations.
| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
|---|---|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.02 / 1K tokens Output · Output tokens $0.02 / 1K tokens Input · Cache read $0.0025 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens Output · Image output tokens $0.08 / 1K image tokens |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.02 / 1K tokens Output · Output tokens $0.02 / 1K tokens Input · Cache read $0.0025 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "openai/gpt-5-image",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 document}"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ['AILOOT_TEXT_FILE'])\nif not source_file.is_file():\n raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')\ntext = source_file.read_text(encoding='utf-8')\nif not text.strip():\n raise SystemExit('Choose a document containing text')\npayload = {'model': 'openai/gpt-5-image', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}\npayload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\\n\\n' + text\nPath('request.json').write_text(json.dumps(payload, ensure_ascii=False), encoding='utf-8')\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path('result.json').read_text(encoding='utf-8'))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\nPY_RESULT\nimport json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ['AILOOT_TEXT_FILE'])\nif not source_file.is_file():\n raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')\ntext = source_file.read_text(encoding='utf-8')\nif not text.strip():\n raise SystemExit('Choose a document containing text')\npayload = {'model': 'openai/gpt-5-image', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}\npayload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\\n\\n' + text\nfrom urllib.request import Request, urlopen\nfrom urllib.error import HTTPError\n\napi_key = os.environ['AILOOT_API_KEY']\nif not api_key.strip():\n raise SystemExit('Set AILOOT_API_KEY before making a request')\nheaders = {'x-api-key': 'PLACEHOLDER_KEY', 'anthropic-version': '2023-06-01', 'Content-Type': 'application/json'}\nheaders['x-api-key'] = api_key\nrequest = Request('https://api.ailoot.ai/v1/messages', data=json.dumps(payload, ensure_ascii=False).encode('utf-8'), headers=headers, method='POST')\ntry:\n with urlopen(request, timeout=120) as response:\n raw = response.read()\n Path('response-headers.txt').write_text(str(response.headers), encoding='utf-8')\nexcept HTTPError as error:\n Path('result.json').write_bytes(error.read())\n Path('response-headers.txt').write_text(str(error.headers), encoding='utf-8')\n raise\nPath('result.json').write_bytes(raw)\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path('result.json').read_text(encoding='utf-8'))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\nJSON or SSE
Keep every complete returned response, file and content part.
Keep all content blocks, thinking signatures and actual tool-use IDs. Assemble all SSE block deltas; a first text block is not the complete output.
Keep request/response IDs and headers. No generic text job retrieval URL is supplied.
| Field | Type |
|---|---|
Fieldid | Typestring |
Fieldmodel | Typestring |
Fieldcontent[] | Typetext|thinking|tool_use|other content block |
Fieldstop_reason | Typestring|null |
Fieldusage | Typeobject |
| Response | Condition | Next step |
|---|---|---|
Response400 · invalid_request_error | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |
Ailoot Ultra openai/gpt-5-image
/v1/images
Technical example in English
Simplify a community-event poster\n\nEdit the supplied community science poster. Preserve the exact event title, date, venue and central telescope illustration. Remove the small decorative stars around the footer, increase the empty space around the title and keep the original portrait layout and two-color palette. Add no new event facts or text. Return the revised poster image.A revised poster image retaining all event wording and the telescope while simplifying the requested areas.Check every event word and number against the source and confirm that only the named decorative elements were removed.