DeepSeek V4 Flash 0423 is the named Flash edition retained for text-based coding, reasoning and agent assignments. Its producer-family reference is DeepSeek-V4-Flash, the smaller mixture-of-experts model in the V4 series. It receives written instructions and context and produces text, which can contain an explanation, code or a proposed tool operation. The 0423 designation remains separate from the moving Latest card and other named Flash editions.
The published V4 Flash family table lists 284 billion total parameters, 13 billion active parameters and a one-million-token context. Its attention combines Compressed Sparse Attention and Heavily Compressed Attention to handle longer source sequences efficiently. Manifold-constrained hyper-connections support propagation across layers, and the producer describes a two-stage post-training process that develops domain-specific experts before consolidating their skills. These family characteristics support written tasks that bring substantial source context together with a focused question.
The V4 family’s instruction profile has Non-think, Think High and Think Max modes. Non-think is intended for direct routine responses, High for logical analysis and planning and Max for extended reasoning effort. The mode affects how reasoning is prepared and separated from the final answer. DeepSeek recommends at least 384K context for local Think Max use and temperature 1.0 with top-p 1.0 in its local reference. Those are producer configuration recommendations, distinct from a universal maximum-output ceiling or a control that every application exposes.
For a software task, provide the relevant source text, observed behaviour and the desired result. An illustrative instruction is: “Implement the described change, preserve the public function names and explain the conditions that the solution handles.” For analysis, label the documents and define the comparison criteria. A large context is useful only if the question and the required final artifact remain clear, so identify the sections that matter instead of relying on the model to infer the purpose of a long collection.
The producer supplies a dedicated V4 message encoding and output format for conversations, reasoning and tool use. Its release does not provide a Jinja-format chat template. A correctly represented conversation preserves the distinction between the user’s task, the model’s proposal and the returned tool result. A chosen function is executed by the surrounding application, which then supplies the observation used for the next reasoning step.
Prepare a multi-step task with a final artifact and a completion rule: a specific change, a source-backed comparison or a defined set of extracted fields. State the allowed actions and keep important names, assumptions and conditions in the text. Ask the final answer to identify what follows from the supplied material and where information is still missing. For a long document or repository excerpt, retain source labels so the result can cite the relevant passage or fragment.
Use the 0423 named edition for text-based coding, reasoning and agent tasks; choose the separate Vision Exp edition for image-aware work. A result can be reused as text, code or an analytical record once compared with the supplied requirements and source evidence; generated proposals remain distinct from actions or validation outcomes that an application has actually performed.
", "aboutText": "DeepSeek V4 Flash 0423 is the named Flash edition retained for text-based coding, reasoning and agent assignments. Its producer-family reference is DeepSeek-V4-Flash, the smaller mixture-of-experts model in the V4 series. It receives written instructions and context and produces text, which can contain an explanation, code or a proposed tool operation. The 0423 designation remains separate from the moving Latest card and other named Flash editions.\n\nThe published V4 Flash family table lists 284 billion total parameters, 13 billion active parameters and a one-million-token context. Its attention combines Compressed Sparse Attention and Heavily Compressed Attention to handle longer source sequences efficiently. Manifold-constrained hyper-connections support propagation across layers, and the producer describes a two-stage post-training process that develops domain-specific experts before consolidating their skills. These family characteristics support written tasks that bring substantial source context together with a focused question.\n\nThe V4 family’s instruction profile has Non-think, Think High and Think Max modes. Non-think is intended for direct routine responses, High for logical analysis and planning and Max for extended reasoning effort. The mode affects how reasoning is prepared and separated from the final answer. DeepSeek recommends at least 384K context for local Think Max use and temperature 1.0 with top-p 1.0 in its local reference. Those are producer configuration recommendations, distinct from a universal maximum-output ceiling or a control that every application exposes.\n\nFor a software task, provide the relevant source text, observed behaviour and the desired result. An illustrative instruction is: “Implement the described change, preserve the public function names and explain the conditions that the solution handles.” For analysis, label the documents and define the comparison criteria. A large context is useful only if the question and the required final artifact remain clear, so identify the sections that matter instead of relying on the model to infer the purpose of a long collection.\n\nThe producer supplies a dedicated V4 message encoding and output format for conversations, reasoning and tool use. Its release does not provide a Jinja-format chat template. A correctly represented conversation preserves the distinction between the user’s task, the model’s proposal and the returned tool result. A chosen function is executed by the surrounding application, which then supplies the observation used for the next reasoning step.\n\nPrepare a multi-step task with a final artifact and a completion rule: a specific change, a source-backed comparison or a defined set of extracted fields. State the allowed actions and keep important names, assumptions and conditions in the text. Ask the final answer to identify what follows from the supplied material and where information is still missing. For a long document or repository excerpt, retain source labels so the result can cite the relevant passage or fragment.\n\nUse the 0423 named edition for text-based coding, reasoning and agent tasks; choose the separate Vision Exp edition for image-aware work. A result can be reused as text, code or an analytical record once compared with the supplied requirements and source evidence; generated proposals remain distinct from actions or validation outcomes that an application has actually performed.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Fix pagination at an exact boundary\n\nA Python pager uses pages = total // size + 1. For total=20 and size=10 it reports three pages, but the product requires two; for total=0 it requires zero. Replace only the calculation, assuming total >= 0 and size > 0. Include assertions for totals 0, 1, 20 and 21.A replacement calculation, a brief rationale and four assertions.Both an exact multiple and zero must avoid the extra page.deepseek/deepseek-v4-flashDeepSeek V4 Flash 0423 is a named V4 Flash edition for text, coding and reasoning work. Its producer family uses compressed attention and three reasoning-effort modes for long-context and agent tasks, while the 0423 identity remains separate from Latest.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
DeepSeek V4 Flash 0423 is the named Flash edition retained for text-based coding, reasoning and agent assignments. Its producer-family reference is DeepSeek-V4-Flash, the smaller mixture-of-experts model in the V4 series. It receives written instructions and context and produces text, which can contain an explanation, code or a proposed tool operation. The 0423 designation remains separate from the moving Latest card and other named Flash editions.
The published V4 Flash family table lists 284 billion total parameters, 13 billion active parameters and a one-million-token context. Its attention combines Compressed Sparse Attention and Heavily Compressed Attention to handle longer source sequences efficiently. Manifold-constrained hyper-connections support propagation across layers, and the producer describes a two-stage post-training process that develops domain-specific experts before consolidating their skills. These family characteristics support written tasks that bring substantial source context together with a focused question.
The V4 family’s instruction profile has Non-think, Think High and Think Max modes. Non-think is intended for direct routine responses, High for logical analysis and planning and Max for extended reasoning effort. The mode affects how reasoning is prepared and separated from the final answer. DeepSeek recommends at least 384K context for local Think Max use and temperature 1.0 with top-p 1.0 in its local reference. Those are producer configuration recommendations, distinct from a universal maximum-output ceiling or a control that every application exposes.
For a software task, provide the relevant source text, observed behaviour and the desired result. An illustrative instruction is: “Implement the described change, preserve the public function names and explain the conditions that the solution handles.” For analysis, label the documents and define the comparison criteria. A large context is useful only if the question and the required final artifact remain clear, so identify the sections that matter instead of relying on the model to infer the purpose of a long collection.
The producer supplies a dedicated V4 message encoding and output format for conversations, reasoning and tool use. Its release does not provide a Jinja-format chat template. A correctly represented conversation preserves the distinction between the user’s task, the model’s proposal and the returned tool result. A chosen function is executed by the surrounding application, which then supplies the observation used for the next reasoning step.
Prepare a multi-step task with a final artifact and a completion rule: a specific change, a source-backed comparison or a defined set of extracted fields. State the allowed actions and keep important names, assumptions and conditions in the text. Ask the final answer to identify what follows from the supplied material and where information is still missing. For a long document or repository excerpt, retain source labels so the result can cite the relevant passage or fragment.
Use the 0423 named edition for text-based coding, reasoning and agent tasks; choose the separate Vision Exp edition for image-aware work. A result can be reused as text, code or an analytical record once compared with the supplied requirements and source evidence; generated proposals remain distinct from actions or validation outcomes that an application has actually performed.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits deepseek/deepseek-v4-flash | 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 $0.00044 / 1K tokens Output · Output tokens $0.00132 / 1K tokens Input · Cache read $0.00006 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.00044 / 1K tokens Output · Output tokens $0.00132 / 1K tokens Input · Cache read $0.00006 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "deepseek/deepseek-v4-flash", "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='deepseek/deepseek-v4-flash',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='deepseek/deepseek-v4-flash',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 deepseek/deepseek-v4-flash
Use the method paths shown above.
deepseek/deepseek-v4-flashDeepSeek V4 Flash 0423 is a named V4 Flash edition for text, coding and reasoning work. Its producer family uses compressed attention and three reasoning-effort modes for long-context and agent tasks, while the 0423 identity remains separate from Latest.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
DeepSeek V4 Flash 0423 is the named Flash edition retained for text-based coding, reasoning and agent assignments. Its producer-family reference is DeepSeek-V4-Flash, the smaller mixture-of-experts model in the V4 series. It receives written instructions and context and produces text, which can contain an explanation, code or a proposed tool operation. The 0423 designation remains separate from the moving Latest card and other named Flash editions.
The published V4 Flash family table lists 284 billion total parameters, 13 billion active parameters and a one-million-token context. Its attention combines Compressed Sparse Attention and Heavily Compressed Attention to handle longer source sequences efficiently. Manifold-constrained hyper-connections support propagation across layers, and the producer describes a two-stage post-training process that develops domain-specific experts before consolidating their skills. These family characteristics support written tasks that bring substantial source context together with a focused question.
The V4 family’s instruction profile has Non-think, Think High and Think Max modes. Non-think is intended for direct routine responses, High for logical analysis and planning and Max for extended reasoning effort. The mode affects how reasoning is prepared and separated from the final answer. DeepSeek recommends at least 384K context for local Think Max use and temperature 1.0 with top-p 1.0 in its local reference. Those are producer configuration recommendations, distinct from a universal maximum-output ceiling or a control that every application exposes.
For a software task, provide the relevant source text, observed behaviour and the desired result. An illustrative instruction is: “Implement the described change, preserve the public function names and explain the conditions that the solution handles.” For analysis, label the documents and define the comparison criteria. A large context is useful only if the question and the required final artifact remain clear, so identify the sections that matter instead of relying on the model to infer the purpose of a long collection.
The producer supplies a dedicated V4 message encoding and output format for conversations, reasoning and tool use. Its release does not provide a Jinja-format chat template. A correctly represented conversation preserves the distinction between the user’s task, the model’s proposal and the returned tool result. A chosen function is executed by the surrounding application, which then supplies the observation used for the next reasoning step.
Prepare a multi-step task with a final artifact and a completion rule: a specific change, a source-backed comparison or a defined set of extracted fields. State the allowed actions and keep important names, assumptions and conditions in the text. Ask the final answer to identify what follows from the supplied material and where information is still missing. For a long document or repository excerpt, retain source labels so the result can cite the relevant passage or fragment.
Use the 0423 named edition for text-based coding, reasoning and agent tasks; choose the separate Vision Exp edition for image-aware work. A result can be reused as text, code or an analytical record once compared with the supplied requirements and source evidence; generated proposals remain distinct from actions or validation outcomes that an application has actually performed.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits deepseek/deepseek-v4-flash | 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 $0.00044 / 1K tokens Output · Output tokens $0.00132 / 1K tokens Input · Cache read $0.00006 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.00044 / 1K tokens Output · Output tokens $0.00132 / 1K tokens Input · Cache read $0.00006 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "deepseek/deepseek-v4-flash",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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': 'deepseek/deepseek-v4-flash', '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': 'deepseek/deepseek-v4-flash', '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 deepseek/deepseek-v4-flash
Use the method paths shown above.
Technical example in English
Fix pagination at an exact boundary\n\nA Python pager uses pages = total // size + 1. For total=20 and size=10 it reports three pages, but the product requires two; for total=0 it requires zero. Replace only the calculation, assuming total >= 0 and size > 0. Include assertions for totals 0, 1, 20 and 21.A replacement calculation, a brief rationale and four assertions.Both an exact multiple and zero must avoid the extra page.