Source: https://ailoot.ai/models/en/openai-gpt-5-image-mini/ Canonical: https://ailoot.ai/models/en/openai-gpt-5-image-mini/ Language: en # OpenAI: GPT-5 Image Mini [Markdown](https://ailoot.ai/models/en/openai-gpt-5-image-mini/index.md) · [JSON](https://ailoot.ai/models/en/openai-gpt-5-image-mini/facts.json) ## [OpenAI: GPT-5 Image Mini](https://ailoot.ai/models/en/openai-gpt-5-image-mini/) GPT-5 Image Mini combines OpenAI’s GPT-5 Mini language capabilities with GPT Image 1 Mini for visual generation and reference-led edits. It accepts text, images and documents and returns text and images, supporting workflows that need both a written response and a visual asset. - [**Ailoot Ultra · OpenAI Chat** `POST /v1/chat/completions` `openai/gpt-5-image-mini`](https://ailoot.ai/models/en/openai-gpt-5-image-mini/#method-0) - [**Ailoot Ultra · Images** `POST /v1/images/generations` `openai/gpt-5-image-mini`](https://ailoot.ai/models/en/openai-gpt-5-image-mini/#method-1) - [**Ailoot Ultra · Anthropic Messages** `POST /v1/messages` `openai/gpt-5-image-mini`](https://ailoot.ai/models/en/openai-gpt-5-image-mini/#method-2) About the model This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below. GPT-5 Image Mini is a combined language-and-image profile built around OpenAI’s GPT-5 Mini and GPT Image 1 Mini. Its language component interprets a written task and source material, while its image component creates or revises visual content. The published profile emphasizes instruction following, text rendering and detailed image editing. It is useful for a focused visual brief that also needs textual interpretation, explanation or supporting copy. #### Bring the written task and visual result together Prepare a brief with the intended asset, subject, composition and required text. Describe how the image will be used, such as a product concept, an illustration accompanying a short explanation or a visual draft for a page. Ask for the written and visual deliverables explicitly so an explanation of the concept is easy to distinguish from the image itself. For example, supply a description of a reusable water bottle and request a simple product-scene concept with a short caption. Specify the visible bottle shape, background, light direction and the exact words that belong in the visual. Keep facts used in the caption separate from decorative details in the scene. Review the returned image and written text against those two parts of the brief. The documented combined profile accepts text, images and files such as PDFs. A document can provide requirements or facts to interpret before creating the visual. An image can supply appearance, layout or an editing source. State each source’s role rather than assume that every attachment should affect every part of the result. Keep source names and ordering clear when several inputs are supplied. #### Generate and revise with references For a new image, specify what should be visible and how the parts relate to one another. For a reference-led edit, identify the change and the details to preserve. A product scene can request a new setting while retaining the item’s recognizable form and visible label. A diagram can ask for a corrected relationship while naming the text and elements that should stay. The profile’s own published card permits up to sixteen reference images for editing. Choose references that contribute to the task and explain their purpose: the product, character, background or visual treatment. Several references can contain conflicting lighting or composition, so name the intended result clearly. Inspect subject details, lettering and the boundaries of a requested change in the actual returned image. Text rendering is a documented capability, but a visual draft still needs a word-by-word check. Provide exact wording, punctuation and placement, then compare important labels and numbers with the brief at the intended viewing size. For a repeated series, retain the references and visual requirements with each result and compare the completed images together. #### Working context and controls The combined profile publishes a 400,000-token context window and up to 128,000 completion tokens. These are working-context and completion allowances, separate from an image’s pixel dimensions or the number of returned image artifacts. Organize long source material around the required interpretation and leave room for the response. A compact brief with relevant references is more useful than unrelated documents whose role has not been explained. Its published text-output contract supports JSON-schema structured results. Define the fields and types when a written result needs to be consumed by an application, and validate the values against the supplied evidence. The combined profile does not expose application function calling. Its use of a language component with image generation is a named profile capability; it does not make every feature of a standalone GPT-5 Mini interface part of this workflow. Image settings should come from the exact profile and interface being used. Keep the selected configuration with the prompt when comparing revisions. The direct GPT Image 1 Mini component and a combined chat profile have different request arrangements, so component-specific size, masking or output controls need an explicit mapping before they are treated as settings of this combined profile. #### Keep the text and image artifacts The documented chat request schema can select text and image as output modalities. Process the returned text and every actual image artifact that accompanies the completion. Save the images in the format identified by the result and retain the written response with the prompt, source references and settings. A completion containing explanatory text alone is different from a completed visual deliverable, so check what the result actually contains before using it in a layout. GPT-5 Image Mini is distinct from the full GPT-5 Image profile, which combines GPT-5 with GPT Image 1. Use the Mini profile for bounded language-and-visual tasks whose brief and review criteria are clear. Check composition, object identity, image text and supporting prose, then request the specific correction required. Keep the successful elements and the relevant references in the next brief so a revision has a concrete target. Practical task ### Create a labelled refill-bottle scene Technical example in English ``` Create a labelled refill-bottle scene Create a product-scene image of a plain cylindrical blue reusable water bottle with a silver screw cap, standing upright on pale stone. Soft daylight enters from the left. Place the exact word REFILL clearly on the bottle, with no other text, logos, accessories or unsupported product claims. Keep the full bottle visible. ``` #### Expected result ``` One image artifact showing the full specified bottle, left-side daylight and the exact single-word label. ``` #### Check the result ``` Inspect the actual image for bottle shape, cap, complete framing and letter-by-letter spelling of REFILL. ``` **Ailoot Ultra · OpenAI Chat** `POST /v1/chat/completions` `openai/gpt-5-image-mini` [`openai/gpt-5-image-mini`](https://ailoot.ai/models/en/#m=openai%2Fgpt-5-image-mini&route=Ultra&caller=openai%2Fgpt-5-image-mini&fmt=chat) OpenAI /`openai/gpt-5-image-mini` ### Overview GPT-5 Image Mini combines OpenAI’s GPT-5 Mini language capabilities with GPT Image 1 Mini for visual generation and reference-led edits. It accepts text, images and documents and returns text and images, supporting workflows that need both a written response and a visual asset. Accepted inputs Text Results Text ### Available in Ailoot · inputs & methods **Ailoot Ultra · OpenAI Chat** `POST /v1/chat/completions` Input types `text` Output types `text` Output format json or SSE | Field | Type | Requirement | Values & limits | Default | | --- | --- | --- | --- | --- | | Field`model` | Type`string` | RequirementRequired | Values & limits openai/gpt-5-image-mini | Default— | | Field`messages` | Type`message[]` | RequirementRequired | Values & limits Minimum items: 1 | Default— | | Field`messages[].role` | Type`string` | 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— | | Field`messages[].content` | Type`string\|content_part[]\|null` | RequirementOptional | Values & limits | Default— | | Field`messages[].tool_calls` | Type`tool_call[]` | RequirementOptional | Values & limits | Default— | | Field`messages[].tool_call_id` | Type`string` | RequirementOptional | Values & limits Applies when: role=tool; use actual returned ID | Default— | | Field`messages[].name` | Type`string` | RequirementOptional | Values & limits | Default— | | Field`messages[].reasoning_content` | Type`string` | RequirementOptional | Values & limits Applies when: Round-trip actual returned reasoning where this model uses it | Default— | | Field`messages[].reasoning_details` | Type`object\|array` | RequirementOptional | Values & limits Model-specific | Default— | | Field`max_tokens` | Type`integer` | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— | | Field`max_completion_tokens` | Type`integer` | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— | | Field`stream` | Type`boolean` | RequirementOptional | Values & limits | Defaultfalse | | Field`stream_options.include_usage` | Type`boolean` | RequirementOptional | Values & limits Model-specific | Default— | | Field`temperature` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— | | Field`top_p` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— | | Field`stop` | Type`string\|string[]` | RequirementOptional | Values & limits Model-specific | Default— | | Field`tools` | Type`function_tool[]` | RequirementOptional | Values & limits Model-specific | Default— | | Field`tools[].type` | Type`string` | RequirementOptional | Values & limits function Model-specific | Default— | | Field`tools[].function.name` | Type`string` | RequirementRequired | Values & limits Applies when: function tool supplied | Default— | | Field`tools[].function.description` | Type`string` | RequirementOptional | Values & limits | Default— | | Field`tools[].function.parameters` | Type`JSON_schema` | RequirementOptional | Values & limits | Default— | | Field`tool_choice` | Type`string\|object` | RequirementOptional | Values & limits Model-specific | Default— | | Field`parallel_tool_calls` | Type`boolean` | RequirementOptional | Values & limits Model-specific | Default— | | Field`response_format` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— | | Field`reasoning_effort` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— | | Field`reasoning` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— | | Field`service_tier` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— | | Field`instructions` | Type`string` | RequirementOptional | Values & limits Compatibility field | Default— | | Field`functions` | Type`function[]` | RequirementOptional | Values & limits Model-specific | Default— | | Field`function_call` | Type`string\|object` | RequirementOptional | Values & limits Model-specific | Default— | | Field`prompt_cache_options` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— | | Field`modalities` | Type`string[]` | RequirementOptional | Values & limits text | Default— | | Field`provider` | Type`object` | RequirementOptional | Values & limits Conditions: provider.options is rejected on this Ultra text route | Default— | | Field`cache_control.ttl` | Type`string` | RequirementOptional | Values & limits Conditions: 1h is rejected in actual prompt-cache locations | Default— | Input material combinations **Text** · UTF8 text `messages[].content` Method parameters and lifecycle | Parameter | Contract | | --- | --- | | Parameter`content_type` | Contractapplication/json | | Parameter`required` | Contractmodel, messages | | Parameter`material_types` | Contracttext | | Parameter`messages` | Contractmessage array with role/content shape | | Parameter`file_material` | Contractactual UTF-8 document inserted as literal text; no file ID inferred | | Parameter`optional_controls` | Contractstream, temperature, top\_p, stop, max\_tokens, max\_completion\_tokens, reasoning, response\_format, tools, tool\_choice | | Parameter`control_scope` | Contractmodel-specific; user function tools differ from hosted tools | | Parameter`output_modalities` | Contracttext | | Parameter`hosted_operations` | Contractfalse | | Parameter`multimodal_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. ### Pricing Tariff references do not add request options. Supported parameters are listed for the selected method. Fast mode Standard rate When fast mode is selected Flex mode Standard rate When flex mode is selected Maximum reasoning effort Standard rate When maximum reasoning effort uses the default adjustment #### Ailoot rates #### Prices by configuration 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 **$0.005** / 1K tokens Output · Output tokens **$0.004** / 1K tokens Input · Cache read **$0.0005** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens Output · Image output tokens **$0.016** / 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 **$0.005** / 1K tokens Output · Output tokens **$0.004** / 1K tokens Input · Cache read **$0.0005** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens | #### Reference tariff details Model-level reference schedules do not change method selection, quotes or charges. Active charges use the selected Ailoot method rates. OpenAI: GPT-5 Image Mini #### Prices by configuration | Configuration | Billing conditions | Charge | | --- | --- | --- | | ConfigurationOpenAI: GPT-5 Image Mini · Default configuration | Billing conditionsDefault configuration | Charge Input · Input tokens **$0.005** / 1K tokens Output · Output tokens **$0.004** / 1K tokens Output · Output image **$0.016** / 1K tokens Output · Web search **$0.02** per search Input · Cache read **$0.0005** / 1K tokens | Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. [How reservation and settlement work →](https://ailoot.ai/docs/en/billing/reserve/) ### Example requests #### Ailoot Ultra · OpenAI Chat curlPython SDKPython stream ```bash set -eu : "${AILOOT_API_KEY:?Set your Ailoot API key}" python3 - <<'PY_REQUEST' import json,os from pathlib import Path p=json.loads('{"model": "openai/gpt-5-image-mini", "messages": [{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}]}') Path("request.json").write_text(json.dumps(p,ensure_ascii=False)) PY_REQUEST curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \ -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \ --data-binary @request.json -D response-headers.txt -o result.json python3 - <<'PY_RESULT' import json from pathlib import Path r=json.loads(Path("result.json").read_text()) for x in r.get("choices",[]): if x.get("message",{}).get("content"): print(x["message"]["content"]) PY_RESULT ``` ```python from openai import OpenAI import os if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request") client=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0) result=client.chat.completions.create(model='openai/gpt-5-image-mini',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) import base64, json from pathlib import Path def save_result(data, stem="result"): # Keep every field, including usage, IDs, reasoning and tool requests. Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8") print(json.dumps(data, ensure_ascii=False, indent=2)) def save_blob(encoded, suffix, label): raw = base64.b64decode(encoded, altchars=b"-_", validate=True) 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 file = Path(stem + "-" + label + "." + ext) file.write_bytes(raw) print("Saved", file) for index, block in enumerate(data.get("content") or []): print("Content", index, json.dumps(block, ensure_ascii=False)) for choice in data.get("choices") or []: print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False)) for index, item in enumerate(data.get("output") or []): print("Output", index, json.dumps(item, ensure_ascii=False)) if item.get("type") == "image_generation_call" and item.get("result"): save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index)) for ci, candidate in enumerate(data.get("candidates") or []): for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []): print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False)) blob = part.get("inlineData") or part.get("inline_data") if blob and blob.get("data"): mime = blob.get("mimeType") or blob.get("mime_type") suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin") save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi)) save_result(result.to_dict(mode="json")) ``` ```python from openai import OpenAI import os from pathlib import Path if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request") client=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0) import base64, json from pathlib import Path def save_result(data, stem="result"): # Keep every field, including usage, IDs, reasoning and tool requests. Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8") print(json.dumps(data, ensure_ascii=False, indent=2)) def save_blob(encoded, suffix, label): raw = base64.b64decode(encoded, altchars=b"-_", validate=True) 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 file = Path(stem + "-" + label + "." + ext) file.write_bytes(raw) print("Saved", file) for index, block in enumerate(data.get("content") or []): print("Content", index, json.dumps(block, ensure_ascii=False)) for choice in data.get("choices") or []: print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False)) for index, item in enumerate(data.get("output") or []): print("Output", index, json.dumps(item, ensure_ascii=False)) if item.get("type") == "image_generation_call" and item.get("result"): save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index)) for ci, candidate in enumerate(data.get("candidates") or []): for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []): print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False)) blob = part.get("inlineData") or part.get("inline_data") if blob and blob.get("data"): mime = blob.get("mimeType") or blob.get("mime_type") suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin") save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi)) with client.chat.completions.stream(model='openai/gpt-5-image-mini',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream: with Path("stream-events.jsonl").open("w",encoding="utf-8") as log: for event in stream: payload=event.to_dict(mode="json") log.write(json.dumps(payload,ensure_ascii=False)+"\n"); log.flush() print(json.dumps(payload,ensure_ascii=False)) final=stream.get_final_completion() save_result(final.to_dict(mode="json"),"stream-result") ``` ### Receive and save results #### Ailoot Ultra · OpenAI Chat json or SSE ##### Keep all completed results 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. ##### If the original response needs checking Keep request/response IDs and headers. No generic text job retrieval URL is supplied. Response fields | Field | Type | | --- | --- | | Field`choices[].index` | Typeinteger | | Field`choices[].message.content` | Typestring\|null | | Field`choices[].message.tool_calls` | Typetool\_call\[\] | | Field`choices[].message.reasoning_content` | Typestring | | Field`choices[].message.reasoning_details` | Typeobject\|array | | Field`choices[].finish_reason` | Typestring\|null | | Field`usage` | Typeobject | Errors and next steps | 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. | ### Aliases #### Model aliases **Ailoot Ultra** [`openai/gpt-5-image-mini`](https://ailoot.ai/models/en/#m=openai%2Fgpt-5-image-mini&route=Ultra&caller=openai%2Fgpt-5-image-mini&fmt=chat) #### Method path aliases `/v1/images` #### Related caller IDs [`openai/gpt-5-image-mini`](https://ailoot.ai/models/en/#m=openai%2Fgpt-5-image-mini&route=Ultra&caller=openai%2Fgpt-5-image-mini&fmt=chat) **Ailoot Ultra · Images** `POST /v1/images/generations` `openai/gpt-5-image-mini` [`openai/gpt-5-image-mini`](https://ailoot.ai/models/en/#m=openai%2Fgpt-5-image-mini&route=Ultra&caller=openai%2Fgpt-5-image-mini&fmt=images) OpenAI /`openai/gpt-5-image-mini` ### Overview GPT-5 Image Mini combines OpenAI’s GPT-5 Mini language capabilities with GPT Image 1 Mini for visual generation and reference-led edits. It accepts text, images and documents and returns text and images, supporting workflows that need both a written response and a visual asset. Accepted inputs Text · Images Results Images ### Available in Ailoot · inputs & methods **Ailoot Ultra · Images** `POST /v1/images/generations` Input types `text`, `image` Output types `image` | Field | Type | Requirement | Values & limits | Default | | --- | --- | --- | --- | --- | | Field`model` | Type`string` | RequirementRequired | Values & limits openai/gpt-5-image-mini | Default— | | Field`prompt` | Type`string` | RequirementRequired | Values & limits Minimum length: 1 | Default— | | Field`aspect_ratio` | Type`string` | RequirementOptional | Values & limits 1:1, 3:2, 2:3, auto | Default— | | Field`quality` | Type`string` | RequirementOptional | Values & limits auto, low, medium, high | Default— | | Field`background` | Type`string` | RequirementOptional | Values & limits auto, transparent, opaque | Default— | | Field`n` | Type`integer` | RequirementOptional | Values & limits Minimum: 1 Maximum: 10 | Default— | | Field`input_references` | Type`array` | RequirementOptional | Values & limits Minimum items: 0 Maximum items: 16 | Default— | | Field`output_compression` | Type`integer` | RequirementOptional | Values & limits Minimum: 0 Maximum: 100 | Default— | | Field`provider` | Type`object` | RequirementOptional | Values & limits | Default— | Method parameters and lifecycle | Parameter | Contract | | --- | --- | | Parameter`content_type` | Contractapplication/json | | Parameter`required` | Contractmodel, prompt | | Parameter`material_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}` ### Pricing ##### How the final charge is calculated 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. Fast mode Not specified When fast mode is selected Flex mode Not specified When flex mode is selected Maximum reasoning effort Not specified When maximum reasoning effort uses the default adjustment #### Estimated rates for comparison #### Prices by configuration 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 **$0.065536** estimate before generation This estimate is not an additional charge or a fixed rate for the completed generation. | Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. [How reservation and settlement work →](https://ailoot.ai/docs/en/billing/reserve/) ### Example requests #### Ailoot Ultra · Images curl ```bash set -eu : "${AILOOT_API_KEY:?Set your Ailoot API key}" export AILOOT_API_KEY python3 - <<'PY_REQUEST' import json,os from pathlib import Path p={'model': 'openai/gpt-5-image-mini', 'prompt': 'a red panda astronaut floating in space, studio lighting'} Path("request.json").write_text(json.dumps(p,ensure_ascii=False)) PY_REQUEST curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/images/generations \ -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \ --data-binary @request.json -D response-headers.txt -o result.json python3 - <<'PY_RESULT' import base64, json, os, subprocess from pathlib import Path from urllib.parse import urlsplit, urljoin def save_images(items): if not items: raise SystemExit("No completed images; retain the full response") for index, item in enumerate(items): encoded=item.get("b64_json") uri=item.get("url", "") if not encoded and uri.startswith("data:image/"): header, separator, encoded=uri.partition(",") if not separator or ";base64" not in header: raise SystemExit("Unsupported image data URI") if encoded: raw=base64.b64decode(encoded,validate=True) elif uri: uri=urljoin("https://api.ailoot.ai",uri) parsed=urlsplit(uri) if parsed.scheme!="https" or not parsed.netloc or parsed.username or parsed.password: raise SystemExit("Invalid returned image URL") owned=parsed.netloc=="api.ailoot.ai" and parsed.path.startswith("/v1/media/assets/") and parsed.path.endswith("/content") args=["curl","--fail-with-body","--silent","--show-error",uri] if owned: args += ["-H","Authorization: Bearer "+os.environ["AILOOT_API_KEY"]] temporary=Path(f"image-{index}.bin") subprocess.run(args+["-o",str(temporary)],check=True) raw=temporary.read_bytes() temporary.unlink() else: raise SystemExit("Image has neither bytes nor URL") if not raw: raise SystemExit("Empty image result") 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"