DeepSeek OCR 2 converts a document image and a text instruction into a textual result. Its main published prompts cover free OCR and converting a document to Markdown with grounding information. The second edition introduces DeepEncoder V2 and visual causal flow: the encoder learns a reading order shaped by the content of the image before the language decoder interprets it. This is especially relevant to pages with columns, tables, formulas and non-linear layouts.
Architecture and reading order. The model retains an encoder-and-decoder structure. DeepEncoder V2 replaces the earlier encoder’s CLIP component with a compact language-model-style encoder. Visual tokens can attend across the image, while learned causal queries progressively organise that information into a sequence for the decoder. The design addresses the difference between a page’s two-dimensional layout and the one-dimensional order required for generating its text.
Image preparation and resolution. The manufacturer’s default dynamic-resolution mode uses one 1024 × 1024 global view and zero to six 768 × 768 local views. The global view produces 256 visual tokens and each local view adds 144, giving 256–1,120 tokens per image in the described setup. These are published model-processing settings rather than a request to manually cut every page into that number of pieces. Supply a readable image that preserves the page boundaries and the relationships between headings, columns and tables.
The encoder includes a visual tokenizer based on SAM with convolutional compression and a compact encoder initialised from Qwen2 0.5B. The decoder remains the first OCR edition’s 3B mixture-of-experts model, with roughly 500 million active parameters. Training proceeds through encoder preparation, query enhancement and decoder specialisation; the final stage fixes the encoder and updates the decoder. The emphasis of this revision is better visual reading logic while retaining compressed image representations.
Choose the output task. Free OCR concentrates on the recognised text without layout. The Markdown prompt requests document conversion with layout information, making the result easier to use in a text-processing pipeline. For a report or paper, the resulting artifact can retain readable sections that you subsequently search, summarise or use as reference material. For a table, inspect whether row and column relationships survived conversion before extracting numerical fields from it.
For a collection of pages, prepare page images in their original order and retain a page identifier alongside each output. The official project describes both image OCR and PDF-processing workflows, including result saving and accelerated inference. Page rendering, iteration and assembly are responsibilities of the surrounding process. Keep the recognised output separate from any later summary so an extraction error can be traced back to its source page.
Document review. The research examines text, formulas, tables and reading order, and discusses particularly dense newspaper pages as an area that remains difficult. Preserve the clearest source image and check small text, table headings, subscripts and decisive values against the original. If a passage is unreadable, obtain a better scan or a focused view that retains enough surrounding layout to establish its role. Also inspect the output for repetition or omitted sections before treating it as a complete record.
OCR 2 supplies the recognised material for the next task. A downstream request can then extract fields, build a searchable note or answer a question from the converted text. The producer describes optical document reading as the present focus; broader visual reasoning and additional modalities are research directions. Keep the expected artifact specific to recognition and document conversion when selecting this edition.
", "aboutText": "DeepSeek OCR 2 converts a document image and a text instruction into a textual result. Its main published prompts cover free OCR and converting a document to Markdown with grounding information. The second edition introduces DeepEncoder V2 and visual causal flow: the encoder learns a reading order shaped by the content of the image before the language decoder interprets it. This is especially relevant to pages with columns, tables, formulas and non-linear layouts.\n\nArchitecture and reading order. The model retains an encoder-and-decoder structure. DeepEncoder V2 replaces the earlier encoder’s CLIP component with a compact language-model-style encoder. Visual tokens can attend across the image, while learned causal queries progressively organise that information into a sequence for the decoder. The design addresses the difference between a page’s two-dimensional layout and the one-dimensional order required for generating its text.\n\nImage preparation and resolution. The manufacturer’s default dynamic-resolution mode uses one 1024 × 1024 global view and zero to six 768 × 768 local views. The global view produces 256 visual tokens and each local view adds 144, giving 256–1,120 tokens per image in the described setup. These are published model-processing settings rather than a request to manually cut every page into that number of pieces. Supply a readable image that preserves the page boundaries and the relationships between headings, columns and tables.\n\nThe encoder includes a visual tokenizer based on SAM with convolutional compression and a compact encoder initialised from Qwen2 0.5B. The decoder remains the first OCR edition’s 3B mixture-of-experts model, with roughly 500 million active parameters. Training proceeds through encoder preparation, query enhancement and decoder specialisation; the final stage fixes the encoder and updates the decoder. The emphasis of this revision is better visual reading logic while retaining compressed image representations.\n\nChoose the output task. Free OCR concentrates on the recognised text without layout. The Markdown prompt requests document conversion with layout information, making the result easier to use in a text-processing pipeline. For a report or paper, the resulting artifact can retain readable sections that you subsequently search, summarise or use as reference material. For a table, inspect whether row and column relationships survived conversion before extracting numerical fields from it.\n\nFor a collection of pages, prepare page images in their original order and retain a page identifier alongside each output. The official project describes both image OCR and PDF-processing workflows, including result saving and accelerated inference. Page rendering, iteration and assembly are responsibilities of the surrounding process. Keep the recognised output separate from any later summary so an extraction error can be traced back to its source page.\n\nDocument review. The research examines text, formulas, tables and reading order, and discusses particularly dense newspaper pages as an area that remains difficult. Preserve the clearest source image and check small text, table headings, subscripts and decisive values against the original. If a passage is unreadable, obtain a better scan or a focused view that retains enough surrounding layout to establish its role. Also inspect the output for repetition or omitted sections before treating it as a complete record.\n\nOCR 2 supplies the recognised material for the next task. A downstream request can then extract fields, build a searchable note or answer a question from the converted text. The producer describes optical document reading as the present focus; broader visual reasoning and additional modalities are research directions. Keep the expected artifact specific to recognition and document conversion when selecting this edition.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Structure supplied OCR text\n\nOrganize this already-transcribed page text as Markdown; do not claim to inspect an image. "STOCK COUNT / Item | Count / Washers | 18 / Bolts | 7 / Note: bolt count needs recount." Preserve the heading, table relationships and note. Do not silently correct the uncertain count or turn this into a summary.A Markdown heading, two-column table and separate note preserving the supplied wording and numbers.Verify that the bolt recount note remains attached to the table and both counts are retained.deepseek/deepseek-ocr-2DeepSeek’s second OCR model converts document images into text or layout-aware Markdown. Its DeepEncoder V2 organises visual information by reading logic, supporting pages that combine text, formulas, tables and complex layouts.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
DeepSeek OCR 2 converts a document image and a text instruction into a textual result. Its main published prompts cover free OCR and converting a document to Markdown with grounding information. The second edition introduces DeepEncoder V2 and visual causal flow: the encoder learns a reading order shaped by the content of the image before the language decoder interprets it. This is especially relevant to pages with columns, tables, formulas and non-linear layouts.
Architecture and reading order. The model retains an encoder-and-decoder structure. DeepEncoder V2 replaces the earlier encoder’s CLIP component with a compact language-model-style encoder. Visual tokens can attend across the image, while learned causal queries progressively organise that information into a sequence for the decoder. The design addresses the difference between a page’s two-dimensional layout and the one-dimensional order required for generating its text.
Image preparation and resolution. The manufacturer’s default dynamic-resolution mode uses one 1024 × 1024 global view and zero to six 768 × 768 local views. The global view produces 256 visual tokens and each local view adds 144, giving 256–1,120 tokens per image in the described setup. These are published model-processing settings rather than a request to manually cut every page into that number of pieces. Supply a readable image that preserves the page boundaries and the relationships between headings, columns and tables.
The encoder includes a visual tokenizer based on SAM with convolutional compression and a compact encoder initialised from Qwen2 0.5B. The decoder remains the first OCR edition’s 3B mixture-of-experts model, with roughly 500 million active parameters. Training proceeds through encoder preparation, query enhancement and decoder specialisation; the final stage fixes the encoder and updates the decoder. The emphasis of this revision is better visual reading logic while retaining compressed image representations.
Choose the output task. Free OCR concentrates on the recognised text without layout. The Markdown prompt requests document conversion with layout information, making the result easier to use in a text-processing pipeline. For a report or paper, the resulting artifact can retain readable sections that you subsequently search, summarise or use as reference material. For a table, inspect whether row and column relationships survived conversion before extracting numerical fields from it.
For a collection of pages, prepare page images in their original order and retain a page identifier alongside each output. The official project describes both image OCR and PDF-processing workflows, including result saving and accelerated inference. Page rendering, iteration and assembly are responsibilities of the surrounding process. Keep the recognised output separate from any later summary so an extraction error can be traced back to its source page.
Document review. The research examines text, formulas, tables and reading order, and discusses particularly dense newspaper pages as an area that remains difficult. Preserve the clearest source image and check small text, table headings, subscripts and decisive values against the original. If a passage is unreadable, obtain a better scan or a focused view that retains enough surrounding layout to establish its role. Also inspect the output for repetition or omitted sections before treating it as a complete record.
OCR 2 supplies the recognised material for the next task. A downstream request can then extract fields, build a searchable note or answer a question from the converted text. The producer describes optical document reading as the present focus; broader visual reasoning and additional modalities are research directions. Keep the expected artifact specific to recognition and document conversion when selecting this edition.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits deepseek/deepseek-ocr-2 | 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.
| Configuration | Rate schedule | Charge |
|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Charge Input · Input tokens $0.000062 / 1K tokens Output · Output tokens $0.000062 / 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-ocr-2", "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-ocr-2',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-ocr-2',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-ocr-2
Use the method paths shown above.
deepseek/deepseek-ocr-2DeepSeek’s second OCR model converts document images into text or layout-aware Markdown. Its DeepEncoder V2 organises visual information by reading logic, supporting pages that combine text, formulas, tables and complex layouts.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
DeepSeek OCR 2 converts a document image and a text instruction into a textual result. Its main published prompts cover free OCR and converting a document to Markdown with grounding information. The second edition introduces DeepEncoder V2 and visual causal flow: the encoder learns a reading order shaped by the content of the image before the language decoder interprets it. This is especially relevant to pages with columns, tables, formulas and non-linear layouts.
Architecture and reading order. The model retains an encoder-and-decoder structure. DeepEncoder V2 replaces the earlier encoder’s CLIP component with a compact language-model-style encoder. Visual tokens can attend across the image, while learned causal queries progressively organise that information into a sequence for the decoder. The design addresses the difference between a page’s two-dimensional layout and the one-dimensional order required for generating its text.
Image preparation and resolution. The manufacturer’s default dynamic-resolution mode uses one 1024 × 1024 global view and zero to six 768 × 768 local views. The global view produces 256 visual tokens and each local view adds 144, giving 256–1,120 tokens per image in the described setup. These are published model-processing settings rather than a request to manually cut every page into that number of pieces. Supply a readable image that preserves the page boundaries and the relationships between headings, columns and tables.
The encoder includes a visual tokenizer based on SAM with convolutional compression and a compact encoder initialised from Qwen2 0.5B. The decoder remains the first OCR edition’s 3B mixture-of-experts model, with roughly 500 million active parameters. Training proceeds through encoder preparation, query enhancement and decoder specialisation; the final stage fixes the encoder and updates the decoder. The emphasis of this revision is better visual reading logic while retaining compressed image representations.
Choose the output task. Free OCR concentrates on the recognised text without layout. The Markdown prompt requests document conversion with layout information, making the result easier to use in a text-processing pipeline. For a report or paper, the resulting artifact can retain readable sections that you subsequently search, summarise or use as reference material. For a table, inspect whether row and column relationships survived conversion before extracting numerical fields from it.
For a collection of pages, prepare page images in their original order and retain a page identifier alongside each output. The official project describes both image OCR and PDF-processing workflows, including result saving and accelerated inference. Page rendering, iteration and assembly are responsibilities of the surrounding process. Keep the recognised output separate from any later summary so an extraction error can be traced back to its source page.
Document review. The research examines text, formulas, tables and reading order, and discusses particularly dense newspaper pages as an area that remains difficult. Preserve the clearest source image and check small text, table headings, subscripts and decisive values against the original. If a passage is unreadable, obtain a better scan or a focused view that retains enough surrounding layout to establish its role. Also inspect the output for repetition or omitted sections before treating it as a complete record.
OCR 2 supplies the recognised material for the next task. A downstream request can then extract fields, build a searchable note or answer a question from the converted text. The producer describes optical document reading as the present focus; broader visual reasoning and additional modalities are research directions. Keep the expected artifact specific to recognition and document conversion when selecting this edition.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits deepseek/deepseek-ocr-2 | 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 $0.000062 / 1K tokens Output · Output tokens $0.000062 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "deepseek/deepseek-ocr-2",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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-ocr-2', '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-ocr-2', '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-ocr-2
Use the method paths shown above.
Technical example in English
Structure supplied OCR text\n\nOrganize this already-transcribed page text as Markdown; do not claim to inspect an image. "STOCK COUNT / Item | Count / Washers | 18 / Bolts | 7 / Note: bolt count needs recount." Preserve the heading, table relationships and note. Do not silently correct the uncertain count or turn this into a summary.A Markdown heading, two-column table and separate note preserving the supplied wording and numbers.Verify that the bolt recount note remains attached to the table and both counts are retained.