DeepSeek R1 is DeepSeek’s original reasoning-focused model for mathematical, coding and logical tasks. It builds on DeepSeek V3 Base and uses a training pipeline with cold-start examples, supervised refinement and reinforcement learning. The input is text and the result is a textual solution or answer. It remains distinct from R1 Zero, the later R1-0528 edition and the separately distilled models.
The producer distinguishes R1 from R1 Zero’s pure reinforcement-learning approach. Cold-start material gives R1 a more readable starting pattern before reasoning-oriented reinforcement learning. Subsequent rejection sampling and supervised training add reasoning and general-purpose data, followed by another reinforcement-learning stage. The card describes two supervised and two reinforcement-learning stages, intended to improve reasoning patterns and alignment with the requested response.
Its published architecture has 671 billion total parameters with 37 billion active per token and a 128K context. That window contains the source, prompt and generated reasoning or answer together; it is not a separate guarantee of 128K output. A long mathematical condition, code fragment or set of requirements should still be organised so the model can identify the actual problem and the form of the result you need.
DeepSeek recommends temperature between 0.5 and 0.7, with 0.6 recommended, to reduce repetition or incoherent output. It advises putting instructions in the user prompt rather than adding a system prompt. Its research report also recommends a direct zero-shot statement of the problem and output format, because few-shot prompting can reduce performance in this original profile. These are the producer’s usage recommendations rather than defaults assumed for every application.
For mathematics, provide the complete condition, variable definitions and domain restrictions. The producer recommends asking for a step-by-step solution with the final result in a \\boxed{} expression. An illustrative brief can request the final formula, the assumptions under which it holds and a substitution check. For code, include the behaviour to implement, constraints and representative input, then ask for the proposed algorithm and the code artifact separately from its explanation.
The model’s reasoning format separates a thinking phase from the final answer. DeepSeek notes that some queries can produce an empty thinking block and recommends a reasoning-start prefix in its reference workflow when deeper reasoning is intended. Preserve the distinction between that producer format and the final answer you want the user to read. The requested deliverable can be a concise conclusion or code even when the model’s intermediate process is longer.
The original research identifies concrete limitations. R1 is optimised for Chinese and English, and other-language queries can lead to unwanted language mixing. It is sensitive to prompting, and its complex multi-turn, role-playing, JSON and function-call behaviour is less developed than its mathematical and coding-reasoning focus. The JSON and tool support documented for R1-0528 is a later edition change, not the original R1 contract. State the output language and format explicitly and keep the problem statement direct.
For a practical technical task, define what constitutes a correct result: a formula with assumptions, an algorithm meeting the stated complexity, or a reasoned comparison against supplied criteria. Ask the final answer to identify missing information rather than invent it. For source-dependent work, provide the authoritative passages as text. Review the proposed code or conclusion against the original conditions; the useful artifact is the final solution and its supporting explanation, distinct from an action or validation the surrounding application has actually performed.
", "aboutText": "DeepSeek R1 is DeepSeek’s original reasoning-focused model for mathematical, coding and logical tasks. It builds on DeepSeek V3 Base and uses a training pipeline with cold-start examples, supervised refinement and reinforcement learning. The input is text and the result is a textual solution or answer. It remains distinct from R1 Zero, the later R1-0528 edition and the separately distilled models.\n\nThe producer distinguishes R1 from R1 Zero’s pure reinforcement-learning approach. Cold-start material gives R1 a more readable starting pattern before reasoning-oriented reinforcement learning. Subsequent rejection sampling and supervised training add reasoning and general-purpose data, followed by another reinforcement-learning stage. The card describes two supervised and two reinforcement-learning stages, intended to improve reasoning patterns and alignment with the requested response.\n\nIts published architecture has 671 billion total parameters with 37 billion active per token and a 128K context. That window contains the source, prompt and generated reasoning or answer together; it is not a separate guarantee of 128K output. A long mathematical condition, code fragment or set of requirements should still be organised so the model can identify the actual problem and the form of the result you need.\n\nDeepSeek recommends temperature between 0.5 and 0.7, with 0.6 recommended, to reduce repetition or incoherent output. It advises putting instructions in the user prompt rather than adding a system prompt. Its research report also recommends a direct zero-shot statement of the problem and output format, because few-shot prompting can reduce performance in this original profile. These are the producer’s usage recommendations rather than defaults assumed for every application.\n\nFor mathematics, provide the complete condition, variable definitions and domain restrictions. The producer recommends asking for a step-by-step solution with the final result in a \\boxed{} expression. An illustrative brief can request the final formula, the assumptions under which it holds and a substitution check. For code, include the behaviour to implement, constraints and representative input, then ask for the proposed algorithm and the code artifact separately from its explanation.\n\nThe model’s reasoning format separates a thinking phase from the final answer. DeepSeek notes that some queries can produce an empty thinking block and recommends a reasoning-start prefix in its reference workflow when deeper reasoning is intended. Preserve the distinction between that producer format and the final answer you want the user to read. The requested deliverable can be a concise conclusion or code even when the model’s intermediate process is longer.\n\nThe original research identifies concrete limitations. R1 is optimised for Chinese and English, and other-language queries can lead to unwanted language mixing. It is sensitive to prompting, and its complex multi-turn, role-playing, JSON and function-call behaviour is less developed than its mathematical and coding-reasoning focus. The JSON and tool support documented for R1-0528 is a later edition change, not the original R1 contract. State the output language and format explicitly and keep the problem statement direct.\n\nFor a practical technical task, define what constitutes a correct result: a formula with assumptions, an algorithm meeting the stated complexity, or a reasoned comparison against supplied criteria. Ask the final answer to identify missing information rather than invent it. For source-dependent work, provide the authoritative passages as text. Review the proposed code or conclusion against the original conditions; the useful artifact is the final solution and its supporting explanation, distinct from an action or validation the surrounding application has actually performed.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Optimize a rectangular enclosure\n\nA rectangular enclosure has 60 metres of fencing, used on all four sides. Its width and length are positive real numbers. Derive the largest possible area, justify why the optimum is global and check the dimensions against the fencing constraint. Give the final result in a boxed mathematical expression.A derivation, optimal dimensions, a perimeter check and a boxed maximum area.Check that the solution respects positivity and uses 2(length + width) = 60 rather than a three-sided constraint.deepseek/deepseek-r1DeepSeek R1 is DeepSeek’s original reasoning-focused text model for mathematics, code and logic. It combines cold-start instruction examples with reinforcement learning and a 128K context, with producer guidance for direct prompts and explicit final-answer formatting.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
DeepSeek R1 is DeepSeek’s original reasoning-focused model for mathematical, coding and logical tasks. It builds on DeepSeek V3 Base and uses a training pipeline with cold-start examples, supervised refinement and reinforcement learning. The input is text and the result is a textual solution or answer. It remains distinct from R1 Zero, the later R1-0528 edition and the separately distilled models.
The producer distinguishes R1 from R1 Zero’s pure reinforcement-learning approach. Cold-start material gives R1 a more readable starting pattern before reasoning-oriented reinforcement learning. Subsequent rejection sampling and supervised training add reasoning and general-purpose data, followed by another reinforcement-learning stage. The card describes two supervised and two reinforcement-learning stages, intended to improve reasoning patterns and alignment with the requested response.
Its published architecture has 671 billion total parameters with 37 billion active per token and a 128K context. That window contains the source, prompt and generated reasoning or answer together; it is not a separate guarantee of 128K output. A long mathematical condition, code fragment or set of requirements should still be organised so the model can identify the actual problem and the form of the result you need.
DeepSeek recommends temperature between 0.5 and 0.7, with 0.6 recommended, to reduce repetition or incoherent output. It advises putting instructions in the user prompt rather than adding a system prompt. Its research report also recommends a direct zero-shot statement of the problem and output format, because few-shot prompting can reduce performance in this original profile. These are the producer’s usage recommendations rather than defaults assumed for every application.
For mathematics, provide the complete condition, variable definitions and domain restrictions. The producer recommends asking for a step-by-step solution with the final result in a \\boxed{} expression. An illustrative brief can request the final formula, the assumptions under which it holds and a substitution check. For code, include the behaviour to implement, constraints and representative input, then ask for the proposed algorithm and the code artifact separately from its explanation.
The model’s reasoning format separates a thinking phase from the final answer. DeepSeek notes that some queries can produce an empty thinking block and recommends a reasoning-start prefix in its reference workflow when deeper reasoning is intended. Preserve the distinction between that producer format and the final answer you want the user to read. The requested deliverable can be a concise conclusion or code even when the model’s intermediate process is longer.
The original research identifies concrete limitations. R1 is optimised for Chinese and English, and other-language queries can lead to unwanted language mixing. It is sensitive to prompting, and its complex multi-turn, role-playing, JSON and function-call behaviour is less developed than its mathematical and coding-reasoning focus. The JSON and tool support documented for R1-0528 is a later edition change, not the original R1 contract. State the output language and format explicitly and keep the problem statement direct.
For a practical technical task, define what constitutes a correct result: a formula with assumptions, an algorithm meeting the stated complexity, or a reasoned comparison against supplied criteria. Ask the final answer to identify missing information rather than invent it. For source-dependent work, provide the authoritative passages as text. Review the proposed code or conclusion against the original conditions; the useful artifact is the final solution and its supporting explanation, distinct from an action or validation the surrounding application has actually performed.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits deepseek/deepseek-r1 | 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 $0.0014 / 1K tokens Output · Output tokens $0.005 / 1K tokens Input · Cache read $0 / 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 $0.0014 / 1K tokens Output · Output tokens $0.005 / 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": "deepseek/deepseek-r1", "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-r1',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-r1',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-r1
Use the method paths shown above.
deepseek/deepseek-r1DeepSeek R1 is DeepSeek’s original reasoning-focused text model for mathematics, code and logic. It combines cold-start instruction examples with reinforcement learning and a 128K context, with producer guidance for direct prompts and explicit final-answer formatting.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
DeepSeek R1 is DeepSeek’s original reasoning-focused model for mathematical, coding and logical tasks. It builds on DeepSeek V3 Base and uses a training pipeline with cold-start examples, supervised refinement and reinforcement learning. The input is text and the result is a textual solution or answer. It remains distinct from R1 Zero, the later R1-0528 edition and the separately distilled models.
The producer distinguishes R1 from R1 Zero’s pure reinforcement-learning approach. Cold-start material gives R1 a more readable starting pattern before reasoning-oriented reinforcement learning. Subsequent rejection sampling and supervised training add reasoning and general-purpose data, followed by another reinforcement-learning stage. The card describes two supervised and two reinforcement-learning stages, intended to improve reasoning patterns and alignment with the requested response.
Its published architecture has 671 billion total parameters with 37 billion active per token and a 128K context. That window contains the source, prompt and generated reasoning or answer together; it is not a separate guarantee of 128K output. A long mathematical condition, code fragment or set of requirements should still be organised so the model can identify the actual problem and the form of the result you need.
DeepSeek recommends temperature between 0.5 and 0.7, with 0.6 recommended, to reduce repetition or incoherent output. It advises putting instructions in the user prompt rather than adding a system prompt. Its research report also recommends a direct zero-shot statement of the problem and output format, because few-shot prompting can reduce performance in this original profile. These are the producer’s usage recommendations rather than defaults assumed for every application.
For mathematics, provide the complete condition, variable definitions and domain restrictions. The producer recommends asking for a step-by-step solution with the final result in a \\boxed{} expression. An illustrative brief can request the final formula, the assumptions under which it holds and a substitution check. For code, include the behaviour to implement, constraints and representative input, then ask for the proposed algorithm and the code artifact separately from its explanation.
The model’s reasoning format separates a thinking phase from the final answer. DeepSeek notes that some queries can produce an empty thinking block and recommends a reasoning-start prefix in its reference workflow when deeper reasoning is intended. Preserve the distinction between that producer format and the final answer you want the user to read. The requested deliverable can be a concise conclusion or code even when the model’s intermediate process is longer.
The original research identifies concrete limitations. R1 is optimised for Chinese and English, and other-language queries can lead to unwanted language mixing. It is sensitive to prompting, and its complex multi-turn, role-playing, JSON and function-call behaviour is less developed than its mathematical and coding-reasoning focus. The JSON and tool support documented for R1-0528 is a later edition change, not the original R1 contract. State the output language and format explicitly and keep the problem statement direct.
For a practical technical task, define what constitutes a correct result: a formula with assumptions, an algorithm meeting the stated complexity, or a reasoned comparison against supplied criteria. Ask the final answer to identify missing information rather than invent it. For source-dependent work, provide the authoritative passages as text. Review the proposed code or conclusion against the original conditions; the useful artifact is the final solution and its supporting explanation, distinct from an action or validation the surrounding application has actually performed.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits deepseek/deepseek-r1 | 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 $0.0014 / 1K tokens Output · Output tokens $0.005 / 1K tokens Input · Cache read $0 / 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 $0.0014 / 1K tokens Output · Output tokens $0.005 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "deepseek/deepseek-r1",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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-r1', '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-r1', '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-r1
Use the method paths shown above.
Technical example in English
Optimize a rectangular enclosure\n\nA rectangular enclosure has 60 metres of fencing, used on all four sides. Its width and length are positive real numbers. Derive the largest possible area, justify why the optimum is global and check the dimensions against the fencing constraint. Give the final result in a boxed mathematical expression.A derivation, optimal dimensions, a perimeter check and a boxed maximum area.Check that the solution respects positivity and uses 2(length + width) = 60 rather than a three-sided constraint.