Seed 1.6 is ByteDance Seed’s general-purpose multimodal model with adaptive thinking. The manufacturer develops it for text and visual reasoning, long-context questions and interactions grounded in an interface or document. It receives instructions and source material and returns text such as an answer, analysis or code. Its adaptive edition remains distinct from Seed1.6-Thinking, Flash and later Seed generations.
The producer describes a sparse mixture-of-experts model with 230 billion total parameters and 23 billion active parameters. Training begins with text, continues with mixed text and visual material, and then extends the sequence length from 32K to 256K. This gives the model a context in which a question can be joined with substantial source information. The context still contains the conversation and generated result together, so leave space for the answer rather than treating it as an independent output allowance.
For a document task, preserve section names, page labels, table headings and units. Ask for the comparison or extraction that the material should support. A useful brief is: “Compare the conditions in these two documents, identify every substantive difference and cite the relevant passage beside each finding.” For a screenshot, explain what the user is trying to achieve and ask for an interpretation based on the visible labels.
Seed1.6 introduces Adaptive Chain-of-Thought, with three producer modes. FullCoT reasons before replying to each prompt. NoCoT responds directly. AdaCoT decides whether to reason according to the question. The training rewards an appropriate amount of thinking rather than unnecessary long reasoning for every request.
Choose the task depth according to the required result: direct extraction or rewriting can have a concise output specification, while a mathematical condition, code defect or source comparison needs the relevant constraints. State the final artifact separately from the intermediate analysis. An extended reasoning process is useful only when it supports the answer you need.
The model’s multimodal training joins written and visual evidence. Supply a readable image and include the surrounding labels needed to interpret it. For a diagram, explain the question and preserve its annotations; for a chart, distinguish the visible values from the interpretation requested. The maker’s evaluation discussion identifies blurred diagrams as a source of lower visual performance, making clear source images an important practical input choice.
For an interface task, identify whether the screenshot shows the current state or the intended design. Ask for the visible controls or code needed for the specified behaviour, then use the application’s actual result as feedback. Text that proposes a click or produces code is distinct from a completed interface action.
The original producer profile documents structured output and tool use, with a 256K context, up to 224K input and up to 32K combined output including reasoning. The application supplies tool definitions and executes the chosen operations, returning observations for the next step. Use those results as evidence and keep the conversation focused on the task.
A practical final result can be a solved problem, a focused code proposal or a source-backed analytical record. Specify its language, mandatory terminology and completion criterion. Check extracted values against the source and preserve missing information explicitly. This keeps the adaptive model’s response connected to the actual question while retaining the exact Seed 1.6 edition and its documented mode distinctions.
", "aboutText": "Seed 1.6 is ByteDance Seed’s general-purpose multimodal model with adaptive thinking. The manufacturer develops it for text and visual reasoning, long-context questions and interactions grounded in an interface or document. It receives instructions and source material and returns text such as an answer, analysis or code. Its adaptive edition remains distinct from Seed1.6-Thinking, Flash and later Seed generations.\n\n### Multimodal training and long context\n\nThe producer describes a sparse mixture-of-experts model with 230 billion total parameters and 23 billion active parameters. Training begins with text, continues with mixed text and visual material, and then extends the sequence length from 32K to 256K. This gives the model a context in which a question can be joined with substantial source information. The context still contains the conversation and generated result together, so leave space for the answer rather than treating it as an independent output allowance.\n\nFor a document task, preserve section names, page labels, table headings and units. Ask for the comparison or extraction that the material should support. A useful brief is: “Compare the conditions in these two documents, identify every substantive difference and cite the relevant passage beside each finding.” For a screenshot, explain what the user is trying to achieve and ask for an interpretation based on the visible labels.\n\n### Adaptive thinking\n\nSeed1.6 introduces Adaptive Chain-of-Thought, with three producer modes. FullCoT reasons before replying to each prompt. NoCoT responds directly. AdaCoT decides whether to reason according to the question. The training rewards an appropriate amount of thinking rather than unnecessary long reasoning for every request.\n\nChoose the task depth according to the required result: direct extraction or rewriting can have a concise output specification, while a mathematical condition, code defect or source comparison needs the relevant constraints. State the final artifact separately from the intermediate analysis. An extended reasoning process is useful only when it supports the answer you need.\n\n### Visual reasoning and preparation\n\nThe model’s multimodal training joins written and visual evidence. Supply a readable image and include the surrounding labels needed to interpret it. For a diagram, explain the question and preserve its annotations; for a chart, distinguish the visible values from the interpretation requested. The maker’s evaluation discussion identifies blurred diagrams as a source of lower visual performance, making clear source images an important practical input choice.\n\nFor an interface task, identify whether the screenshot shows the current state or the intended design. Ask for the visible controls or code needed for the specified behaviour, then use the application’s actual result as feedback. Text that proposes a click or produces code is distinct from a completed interface action.\n\n### Tool use and response limits\n\nThe original producer profile documents structured output and tool use, with a 256K context, up to 224K input and up to 32K combined output including reasoning. The application supplies tool definitions and executes the chosen operations, returning observations for the next step. Use those results as evidence and keep the conversation focused on the task.\n\nA practical final result can be a solved problem, a focused code proposal or a source-backed analytical record. Specify its language, mandatory terminology and completion criterion. Check extracted values against the source and preserve missing information explicitly. This keeps the adaptive model’s response connected to the actual question while retaining the exact Seed 1.6 edition and its documented mode distinctions.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Resolve conflicting return rules\n\nCompare two text excerpts. Policy: unopened items may be returned within 21 calendar days; customised items are excluded. FAQ: all items can be returned within 30 days. List the substantive conflicts, cite the exact phrases, and draft a replacement FAQ sentence that follows the policy without adding exceptions.Two conflict entries with quoted evidence, then one corrected FAQ sentence.The proposed FAQ retains both the 21-day limit and the customised-item exclusion.bytedance-seed/seed-1.6Seed 1.6 combines text and visual understanding with adaptive reasoning and a 256K context. Its FullCoT, NoCoT and AdaCoT modes let the producer profile match deeper analysis or direct answers to the task, producing explanations, code and source-based findings.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Seed 1.6 is ByteDance Seed’s general-purpose multimodal model with adaptive thinking. The manufacturer develops it for text and visual reasoning, long-context questions and interactions grounded in an interface or document. It receives instructions and source material and returns text such as an answer, analysis or code. Its adaptive edition remains distinct from Seed1.6-Thinking, Flash and later Seed generations.
The producer describes a sparse mixture-of-experts model with 230 billion total parameters and 23 billion active parameters. Training begins with text, continues with mixed text and visual material, and then extends the sequence length from 32K to 256K. This gives the model a context in which a question can be joined with substantial source information. The context still contains the conversation and generated result together, so leave space for the answer rather than treating it as an independent output allowance.
For a document task, preserve section names, page labels, table headings and units. Ask for the comparison or extraction that the material should support. A useful brief is: “Compare the conditions in these two documents, identify every substantive difference and cite the relevant passage beside each finding.” For a screenshot, explain what the user is trying to achieve and ask for an interpretation based on the visible labels.
Seed1.6 introduces Adaptive Chain-of-Thought, with three producer modes. FullCoT reasons before replying to each prompt. NoCoT responds directly. AdaCoT decides whether to reason according to the question. The training rewards an appropriate amount of thinking rather than unnecessary long reasoning for every request.
Choose the task depth according to the required result: direct extraction or rewriting can have a concise output specification, while a mathematical condition, code defect or source comparison needs the relevant constraints. State the final artifact separately from the intermediate analysis. An extended reasoning process is useful only when it supports the answer you need.
The model’s multimodal training joins written and visual evidence. Supply a readable image and include the surrounding labels needed to interpret it. For a diagram, explain the question and preserve its annotations; for a chart, distinguish the visible values from the interpretation requested. The maker’s evaluation discussion identifies blurred diagrams as a source of lower visual performance, making clear source images an important practical input choice.
For an interface task, identify whether the screenshot shows the current state or the intended design. Ask for the visible controls or code needed for the specified behaviour, then use the application’s actual result as feedback. Text that proposes a click or produces code is distinct from a completed interface action.
The original producer profile documents structured output and tool use, with a 256K context, up to 224K input and up to 32K combined output including reasoning. The application supplies tool definitions and executes the chosen operations, returning observations for the next step. Use those results as evidence and keep the conversation focused on the task.
A practical final result can be a solved problem, a focused code proposal or a source-backed analytical record. Specify its language, mandatory terminology and completion criterion. Check extracted values against the source and preserve missing information explicitly. This keeps the adaptive model’s response connected to the actual question while retaining the exact Seed 1.6 edition and its documented mode distinctions.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits bytedance-seed/seed-1.6 | 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 $0.0005 / 1K tokens Output · Output tokens $0.004 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and including128,000 | Charge Input · Input tokens $0.0005 / 1K tokens Output · Output tokens $0.004 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationRequest-length tier 2 | Rate schedule— | Context tokens, more than128,000 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.001 / 1K tokens Output · Output tokens $0.008 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "bytedance-seed/seed-1.6", "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='bytedance-seed/seed-1.6',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='bytedance-seed/seed-1.6',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 bytedance-seed/seed-1.6
Use the method paths shown above.
bytedance-seed/seed-1.6Seed 1.6 combines text and visual understanding with adaptive reasoning and a 256K context. Its FullCoT, NoCoT and AdaCoT modes let the producer profile match deeper analysis or direct answers to the task, producing explanations, code and source-based findings.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Seed 1.6 is ByteDance Seed’s general-purpose multimodal model with adaptive thinking. The manufacturer develops it for text and visual reasoning, long-context questions and interactions grounded in an interface or document. It receives instructions and source material and returns text such as an answer, analysis or code. Its adaptive edition remains distinct from Seed1.6-Thinking, Flash and later Seed generations.
The producer describes a sparse mixture-of-experts model with 230 billion total parameters and 23 billion active parameters. Training begins with text, continues with mixed text and visual material, and then extends the sequence length from 32K to 256K. This gives the model a context in which a question can be joined with substantial source information. The context still contains the conversation and generated result together, so leave space for the answer rather than treating it as an independent output allowance.
For a document task, preserve section names, page labels, table headings and units. Ask for the comparison or extraction that the material should support. A useful brief is: “Compare the conditions in these two documents, identify every substantive difference and cite the relevant passage beside each finding.” For a screenshot, explain what the user is trying to achieve and ask for an interpretation based on the visible labels.
Seed1.6 introduces Adaptive Chain-of-Thought, with three producer modes. FullCoT reasons before replying to each prompt. NoCoT responds directly. AdaCoT decides whether to reason according to the question. The training rewards an appropriate amount of thinking rather than unnecessary long reasoning for every request.
Choose the task depth according to the required result: direct extraction or rewriting can have a concise output specification, while a mathematical condition, code defect or source comparison needs the relevant constraints. State the final artifact separately from the intermediate analysis. An extended reasoning process is useful only when it supports the answer you need.
The model’s multimodal training joins written and visual evidence. Supply a readable image and include the surrounding labels needed to interpret it. For a diagram, explain the question and preserve its annotations; for a chart, distinguish the visible values from the interpretation requested. The maker’s evaluation discussion identifies blurred diagrams as a source of lower visual performance, making clear source images an important practical input choice.
For an interface task, identify whether the screenshot shows the current state or the intended design. Ask for the visible controls or code needed for the specified behaviour, then use the application’s actual result as feedback. Text that proposes a click or produces code is distinct from a completed interface action.
The original producer profile documents structured output and tool use, with a 256K context, up to 224K input and up to 32K combined output including reasoning. The application supplies tool definitions and executes the chosen operations, returning observations for the next step. Use those results as evidence and keep the conversation focused on the task.
A practical final result can be a solved problem, a focused code proposal or a source-backed analytical record. Specify its language, mandatory terminology and completion criterion. Check extracted values against the source and preserve missing information explicitly. This keeps the adaptive model’s response connected to the actual question while retaining the exact Seed 1.6 edition and its documented mode distinctions.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits bytedance-seed/seed-1.6 | 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 $0.0005 / 1K tokens Output · Output tokens $0.004 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and including128,000 | Charge Input · Input tokens $0.0005 / 1K tokens Output · Output tokens $0.004 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationRequest-length tier 2 | Rate schedule— | Context tokens, more than128,000 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.001 / 1K tokens Output · Output tokens $0.008 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "bytedance-seed/seed-1.6",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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': 'bytedance-seed/seed-1.6', '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': 'bytedance-seed/seed-1.6', '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 bytedance-seed/seed-1.6
Use the method paths shown above.
Technical example in English
Resolve conflicting return rules\n\nCompare two text excerpts. Policy: unopened items may be returned within 21 calendar days; customised items are excluded. FAQ: all items can be returned within 30 days. List the substantive conflicts, cite the exact phrases, and draft a replacement FAQ sentence that follows the policy without adding exceptions.Two conflict entries with quoted evidence, then one corrected FAQ sentence.The proposed FAQ retains both the 21-day limit and the customised-item exclusion.