Introduction: a smaller R1-derived reasoning model
DeepSeek-R1-Distill-Qwen-7B transfers reasoning examples from DeepSeek-R1 into a dense model based on Qwen2.5-Math-7B. It accepts text and generates text, including worked solutions, programming explanations and answers to logical problems. This exact 7B distillation is a separate checkpoint from full DeepSeek-R1, from the original Qwen2.5-Math-7B, and from larger distilled editions. Its name records both the reasoning-data producer and the underlying model family.
What distillation contributes
DeepSeek’s R1 research distinguishes the training of the large reasoning teacher from the fine-tuning of its smaller students. The teacher’s pipeline uses reinforcement learning and supervised stages; the released distilled models are fine-tuned with samples produced by R1. The maker describes 800,000 curated examples for these releases. Do not assume that the 7B student itself has the full model’s mixture-of-experts architecture or underwent every teacher-training stage. Distillation gives this model a learned style of reasoning; it does not make its conclusions equivalent to those of the teacher.
The exact model and its configuration
The official model table identifies Qwen2.5-Math-7B as this edition’s base. DeepSeek changes configuration and tokenizer settings, so the exact released checkpoint and chat template matter. Its published configuration uses a Qwen2 causal-language-model architecture with 28 layers and bfloat16 weights. It sets maximum positions to 131,072. That configuration value is not a separate validation of long-document accuracy: the shared R1 card’s 128K context table describes the full R1 models, while its distilled-model table identifies ancestry without publishing a per-student validated context table.
Use it for a task with a checkable outcome. For mathematics, supply the complete statement, definitions and units. For code, include the relevant function, input, observed result and desired behavior. For a logic question, list the facts and distinguish a required conclusion from an assumption. Request a final result that can be independently checked, such as a boxed value, a concise proof outline or an explained patch. These examples apply the maker’s documented reasoning scope; they are not claims that the model runs code or verifies proofs automatically.
How to prepare the prompt
DeepSeek recommends placing all instructions in the user prompt and avoiding a system prompt for this R1 release. For a mathematical problem, ask for step-by-step reasoning and a clearly delimited final answer. Include any output structure in the same prompt: for example, a short conclusion followed by assumptions and supporting calculations. An application should use the student’s own tokenizer and formatting rather than substitute the base Qwen template without checking the maker’s changes.
The maker notes that some queries can produce an empty thinking block and bypass the intended reasoning pattern. Its recommended remedy is to make generation begin with the opening thinking marker and a newline in a compatible workflow. This is a documented generation-format recommendation, not a promise that every application exposes such a control. Keep the final answer distinct from the longer reasoning text when presenting a result.
Generation settings and available space
DeepSeek recommends a temperature between 0.5 and 0.7, with 0.6 as the preferred starting point, to reduce repeated or incoherent output. Its evaluation setup uses a 32,768-token generation allowance and top_p 0.95. Those evaluation choices are not a universal hard maximum. Reasoning, source text and the final response all need space in the configured context, so a request containing a long proof or code listing should still leave room for completion.
Limitations that affect model choice
A small distilled model remains a distinct reasoning trade-off. The maker’s release materials do not establish image, audio or video input for this checkpoint, nor a dedicated tool-calling protocol. Tool execution or access to current data would need a separately configured application workflow. The release also does not inherit later DeepSeek-R1-0528 prompt-policy changes simply through the R1 name. Verify numerical answers, inspect proposed code changes and check whether the final conclusion follows from the supplied facts; a long reasoning transcript alone is not proof of correctness.
", "aboutText": "Introduction: a smaller R1-derived reasoning model\n\nDeepSeek-R1-Distill-Qwen-7B transfers reasoning examples from DeepSeek-R1 into a dense model based on Qwen2.5-Math-7B. It accepts text and generates text, including worked solutions, programming explanations and answers to logical problems. This exact 7B distillation is a separate checkpoint from full DeepSeek-R1, from the original Qwen2.5-Math-7B, and from larger distilled editions. Its name records both the reasoning-data producer and the underlying model family.\n\nWhat distillation contributes\n\nDeepSeek’s R1 research distinguishes the training of the large reasoning teacher from the fine-tuning of its smaller students. The teacher’s pipeline uses reinforcement learning and supervised stages; the released distilled models are fine-tuned with samples produced by R1. The maker describes 800,000 curated examples for these releases. Do not assume that the 7B student itself has the full model’s mixture-of-experts architecture or underwent every teacher-training stage. Distillation gives this model a learned style of reasoning; it does not make its conclusions equivalent to those of the teacher.\n\nThe exact model and its configuration\n\nThe official model table identifies Qwen2.5-Math-7B as this edition’s base. DeepSeek changes configuration and tokenizer settings, so the exact released checkpoint and chat template matter. Its published configuration uses a Qwen2 causal-language-model architecture with 28 layers and bfloat16 weights. It sets maximum positions to 131,072. That configuration value is not a separate validation of long-document accuracy: the shared R1 card’s 128K context table describes the full R1 models, while its distilled-model table identifies ancestry without publishing a per-student validated context table.\n\nUse it for a task with a checkable outcome. For mathematics, supply the complete statement, definitions and units. For code, include the relevant function, input, observed result and desired behavior. For a logic question, list the facts and distinguish a required conclusion from an assumption. Request a final result that can be independently checked, such as a boxed value, a concise proof outline or an explained patch. These examples apply the maker’s documented reasoning scope; they are not claims that the model runs code or verifies proofs automatically.\n\nHow to prepare the prompt\n\nDeepSeek recommends placing all instructions in the user prompt and avoiding a system prompt for this R1 release. For a mathematical problem, ask for step-by-step reasoning and a clearly delimited final answer. Include any output structure in the same prompt: for example, a short conclusion followed by assumptions and supporting calculations. An application should use the student’s own tokenizer and formatting rather than substitute the base Qwen template without checking the maker’s changes.\n\nThe maker notes that some queries can produce an empty thinking block and bypass the intended reasoning pattern. Its recommended remedy is to make generation begin with the opening thinking marker and a newline in a compatible workflow. This is a documented generation-format recommendation, not a promise that every application exposes such a control. Keep the final answer distinct from the longer reasoning text when presenting a result.\n\nGeneration settings and available space\n\nDeepSeek recommends a temperature between 0.5 and 0.7, with 0.6 as the preferred starting point, to reduce repeated or incoherent output. Its evaluation setup uses a 32,768-token generation allowance and top_p 0.95. Those evaluation choices are not a universal hard maximum. Reasoning, source text and the final response all need space in the configured context, so a request containing a long proof or code listing should still leave room for completion.\n\nLimitations that affect model choice\n\nA small distilled model remains a distinct reasoning trade-off. The maker’s release materials do not establish image, audio or video input for this checkpoint, nor a dedicated tool-calling protocol. Tool execution or access to current data would need a separately configured application workflow. The release also does not inherit later DeepSeek-R1-0528 prompt-policy changes simply through the R1 name. Verify numerical answers, inspect proposed code changes and check whether the final conclusion follows from the supplied facts; a long reasoning transcript alone is not proof of correctness.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "a436cadf67fcdf67446346fc5e20acfb862a0eea2499481400809e10a9383b1c", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "en", "methods": [ { "html": "Pro/deepseek-ai/DeepSeek-R1-Distill-Qwen-7BDeepSeek-R1-Distill-Qwen-7B is DeepSeek’s compact dense reasoning model, fine-tuned from Qwen2.5-Math-7B using R1-generated examples. It takes text and produces text for mathematical, coding and logical tasks, with checkpoint-specific prompting guidance.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Introduction: a smaller R1-derived reasoning model
DeepSeek-R1-Distill-Qwen-7B transfers reasoning examples from DeepSeek-R1 into a dense model based on Qwen2.5-Math-7B. It accepts text and generates text, including worked solutions, programming explanations and answers to logical problems. This exact 7B distillation is a separate checkpoint from full DeepSeek-R1, from the original Qwen2.5-Math-7B, and from larger distilled editions. Its name records both the reasoning-data producer and the underlying model family.
What distillation contributes
DeepSeek’s R1 research distinguishes the training of the large reasoning teacher from the fine-tuning of its smaller students. The teacher’s pipeline uses reinforcement learning and supervised stages; the released distilled models are fine-tuned with samples produced by R1. The maker describes 800,000 curated examples for these releases. Do not assume that the 7B student itself has the full model’s mixture-of-experts architecture or underwent every teacher-training stage. Distillation gives this model a learned style of reasoning; it does not make its conclusions equivalent to those of the teacher.
The exact model and its configuration
The official model table identifies Qwen2.5-Math-7B as this edition’s base. DeepSeek changes configuration and tokenizer settings, so the exact released checkpoint and chat template matter. Its published configuration uses a Qwen2 causal-language-model architecture with 28 layers and bfloat16 weights. It sets maximum positions to 131,072. That configuration value is not a separate validation of long-document accuracy: the shared R1 card’s 128K context table describes the full R1 models, while its distilled-model table identifies ancestry without publishing a per-student validated context table.
Use it for a task with a checkable outcome. For mathematics, supply the complete statement, definitions and units. For code, include the relevant function, input, observed result and desired behavior. For a logic question, list the facts and distinguish a required conclusion from an assumption. Request a final result that can be independently checked, such as a boxed value, a concise proof outline or an explained patch. These examples apply the maker’s documented reasoning scope; they are not claims that the model runs code or verifies proofs automatically.
How to prepare the prompt
DeepSeek recommends placing all instructions in the user prompt and avoiding a system prompt for this R1 release. For a mathematical problem, ask for step-by-step reasoning and a clearly delimited final answer. Include any output structure in the same prompt: for example, a short conclusion followed by assumptions and supporting calculations. An application should use the student’s own tokenizer and formatting rather than substitute the base Qwen template without checking the maker’s changes.
The maker notes that some queries can produce an empty thinking block and bypass the intended reasoning pattern. Its recommended remedy is to make generation begin with the opening thinking marker and a newline in a compatible workflow. This is a documented generation-format recommendation, not a promise that every application exposes such a control. Keep the final answer distinct from the longer reasoning text when presenting a result.
Generation settings and available space
DeepSeek recommends a temperature between 0.5 and 0.7, with 0.6 as the preferred starting point, to reduce repeated or incoherent output. Its evaluation setup uses a 32,768-token generation allowance and top_p 0.95. Those evaluation choices are not a universal hard maximum. Reasoning, source text and the final response all need space in the configured context, so a request containing a long proof or code listing should still leave room for completion.
Limitations that affect model choice
A small distilled model remains a distinct reasoning trade-off. The maker’s release materials do not establish image, audio or video input for this checkpoint, nor a dedicated tool-calling protocol. Tool execution or access to current data would need a separately configured application workflow. The release also does not inherit later DeepSeek-R1-0528 prompt-policy changes simply through the R1 name. Verify numerical answers, inspect proposed code changes and check whether the final conclusion follows from the supplied facts; a long reasoning transcript alone is not proof of correctness.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits Pro/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B | Default— |
Fieldmessages | Typemessage[] | RequirementRequired | Values & limits Minimum items: 1 | Default— |
Fieldmessages[].role | Typestring | RequirementRequired | Values & limits Model-specific | Default— |
Fieldmessages[].content | Typestring | RequirementOptional | Values & limits Applies when: Text conversation | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
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 |
Parametercontrol_scope | ContractText conversation; stream is a boolean and defaults to false. |
Parameteroutput_modalities | Contracttext |
Parameterhosted_operations | Contractfalse |
Parametermultimodal_input_binding | Contractnull |
Method aliases: /chat/completions
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.
| Configuration | Rate schedule | Charge |
|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Charge Input · Input tokens $0.0001 / 1K tokens Output · Output tokens $0.0001 / 1K tokens Input · Cache read $0 / 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":"Pro/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B","messages":[{"role":"user","content":"hello"}],"stream":false}')\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="Pro/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B", messages=[{"role":"user","content":"hello"}], stream=False)\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"))\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 Pro/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
/chat/completions
Pro/deepseek-ai/DeepSeek-R1-Distill-Qwen-7BDeepSeek-R1-Distill-Qwen-7B is DeepSeek’s compact dense reasoning model, fine-tuned from Qwen2.5-Math-7B using R1-generated examples. It takes text and produces text for mathematical, coding and logical tasks, with checkpoint-specific prompting guidance.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Introduction: a smaller R1-derived reasoning model
DeepSeek-R1-Distill-Qwen-7B transfers reasoning examples from DeepSeek-R1 into a dense model based on Qwen2.5-Math-7B. It accepts text and generates text, including worked solutions, programming explanations and answers to logical problems. This exact 7B distillation is a separate checkpoint from full DeepSeek-R1, from the original Qwen2.5-Math-7B, and from larger distilled editions. Its name records both the reasoning-data producer and the underlying model family.
What distillation contributes
DeepSeek’s R1 research distinguishes the training of the large reasoning teacher from the fine-tuning of its smaller students. The teacher’s pipeline uses reinforcement learning and supervised stages; the released distilled models are fine-tuned with samples produced by R1. The maker describes 800,000 curated examples for these releases. Do not assume that the 7B student itself has the full model’s mixture-of-experts architecture or underwent every teacher-training stage. Distillation gives this model a learned style of reasoning; it does not make its conclusions equivalent to those of the teacher.
The exact model and its configuration
The official model table identifies Qwen2.5-Math-7B as this edition’s base. DeepSeek changes configuration and tokenizer settings, so the exact released checkpoint and chat template matter. Its published configuration uses a Qwen2 causal-language-model architecture with 28 layers and bfloat16 weights. It sets maximum positions to 131,072. That configuration value is not a separate validation of long-document accuracy: the shared R1 card’s 128K context table describes the full R1 models, while its distilled-model table identifies ancestry without publishing a per-student validated context table.
Use it for a task with a checkable outcome. For mathematics, supply the complete statement, definitions and units. For code, include the relevant function, input, observed result and desired behavior. For a logic question, list the facts and distinguish a required conclusion from an assumption. Request a final result that can be independently checked, such as a boxed value, a concise proof outline or an explained patch. These examples apply the maker’s documented reasoning scope; they are not claims that the model runs code or verifies proofs automatically.
How to prepare the prompt
DeepSeek recommends placing all instructions in the user prompt and avoiding a system prompt for this R1 release. For a mathematical problem, ask for step-by-step reasoning and a clearly delimited final answer. Include any output structure in the same prompt: for example, a short conclusion followed by assumptions and supporting calculations. An application should use the student’s own tokenizer and formatting rather than substitute the base Qwen template without checking the maker’s changes.
The maker notes that some queries can produce an empty thinking block and bypass the intended reasoning pattern. Its recommended remedy is to make generation begin with the opening thinking marker and a newline in a compatible workflow. This is a documented generation-format recommendation, not a promise that every application exposes such a control. Keep the final answer distinct from the longer reasoning text when presenting a result.
Generation settings and available space
DeepSeek recommends a temperature between 0.5 and 0.7, with 0.6 as the preferred starting point, to reduce repeated or incoherent output. Its evaluation setup uses a 32,768-token generation allowance and top_p 0.95. Those evaluation choices are not a universal hard maximum. Reasoning, source text and the final response all need space in the configured context, so a request containing a long proof or code listing should still leave room for completion.
Limitations that affect model choice
A small distilled model remains a distinct reasoning trade-off. The maker’s release materials do not establish image, audio or video input for this checkpoint, nor a dedicated tool-calling protocol. Tool execution or access to current data would need a separately configured application workflow. The release also does not inherit later DeepSeek-R1-0528 prompt-policy changes simply through the R1 name. Verify numerical answers, inspect proposed code changes and check whether the final conclusion follows from the supplied facts; a long reasoning transcript alone is not proof of correctness.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits Pro/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B | 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.
| Configuration | Rate schedule | Charge |
|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Charge Input · Input tokens $0.0001 / 1K tokens Output · Output tokens $0.0001 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "Pro/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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': 'Pro/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B', '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': 'Pro/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B', '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 Pro/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
/chat/completions