Qwen2.5-14B-Instruct is the general Qwen2.5 family's instruction-tuned 14B-size edition. It accepts a text conversation and returns text: an explanation, a document, program code or structured fields. Its maker emphasizes instruction following, coding, mathematics, understanding structured data such as tables, and generating structured answers, particularly JSON.
What the family improves
The maker describes broader knowledge and stronger coding and mathematical abilities than the preceding Qwen2 generation, together with long-answer generation and better handling of varied system instructions. The family uses a pretraining corpus described as reaching 18 trillion tokens. These capabilities support a subject-specific assistant whose role and output are defined by the task. This model remains the general Instruct edition; the separately named Qwen2.5-Coder and Qwen2.5-Math lines have their own specializations.
A process assistant can receive a procedure and a question about one stage. Define the reader's role, ask for the actions relevant to that stage and require the answer to retain the procedure's original conditions. A useful output can separate the next action, the condition that makes it applicable and the information still required. This turns a broad request for advice into a response tied to the supplied process.
For a coding explanation, provide the function, relevant helper definitions and the input that causes confusion. Ask for the sequence of operations and the value returned for that input. For a mathematical explanation, state the symbols, assumptions and target expression before requesting the derivation. Both tasks use text; executing the program or making a separate numerical tool available is work for the application around the model.
Tables and JSON
For a table question, preserve the column headings and units, name the relevant rows and specify the comparison. The desired output might list the matching row identifiers and explain which supplied condition each row satisfies. If the table has missing values, state whether the answer should leave them absent or represent them explicitly.
For structured extraction, show the field names and required types. An input such as an item identifier, a stock quantity and a warehouse label can be converted into a record with those same fields. Ask for only the record when an application will parse it; ask for a separate prose explanation when the user needs to inspect the source interpretation. The model's documented JSON-generation ability is distinct from a particular interface enforcing a schema.
Multilingual conversation is supported across more than 29 languages, including English, Chinese, Russian, German, French, Spanish, Portuguese, Italian, Japanese, Korean, Vietnamese, Thai and Arabic. Set the final language and provide any terminology that must remain unchanged. For a translated technical explanation, ask the model to retain variable names, quoted labels and units while adapting the surrounding prose to the reader.
The specific 14B release
The card reports 14.7 billion parameters, including 13.1 billion non-embedding parameters, and 48 Transformer layers. Its architecture uses rotary positional embeddings, SwiGLU, RMSNorm and attention QKV bias, with 40 query heads and 8 key/value heads in grouped-query attention. Pretraining and post-training produce this Instruct edition. Its parameter count and layer count differ from the 32B edition even where the family capabilities and published context figures coincide.
The model card lists a full context of 131,072 tokens and generation up to 8,192 tokens. The former concerns the conversation and material retained for a task; the latter concerns the generated answer. The quick-start's 512-token generation setting is only an example and does not replace the card's stated answer capacity. Image, video and audio understanding belong to separately named multimodal releases, not this text model.
Input format and tool-assisted tasks
The maker's example applies the matching chat template to distinct system and user messages. Define the assistant's role and response rules separately from the material being examined. Supply a complete question and label the source text so that an instruction quoted inside the source is not confused with the task given by the application.
The official Qwen2.5 announcement also describes tool-calling templates and compatible integrations. A tool-assisted task needs the surrounding application to supply function descriptions, execute the selected operation and provide its result for the next answer. For example, a conversation can ask for a calculation using a supplied calculation tool; the function result then becomes information the model can explain. Tool availability and execution come from that integration, while this release provides the conversational text behavior.
Long-text configuration
The published configuration initially covers 32,768 tokens. The documented extension for longer inputs uses YaRN, with an example scaling factor of 4.0 and an original maximum-position setting of 32,768. Static scaling may affect shorter-text behavior, so the maker recommends adding it when long contexts are needed.
When preparing a long source, identify the section to revise or the question to answer and keep the supporting parts together. A clear request can ask for a corrected passage, a table of changes and the original section references. This uses the extended context for a concrete artifact while keeping the answer within the separate generation limit.
", "aboutText": "Qwen2.5-14B-Instruct is the general Qwen2.5 family's instruction-tuned 14B-size edition. It accepts a text conversation and returns text: an explanation, a document, program code or structured fields. Its maker emphasizes instruction following, coding, mathematics, understanding structured data such as tables, and generating structured answers, particularly JSON.\n\nWhat the family improves\n\nThe maker describes broader knowledge and stronger coding and mathematical abilities than the preceding Qwen2 generation, together with long-answer generation and better handling of varied system instructions. The family uses a pretraining corpus described as reaching 18 trillion tokens. These capabilities support a subject-specific assistant whose role and output are defined by the task. This model remains the general Instruct edition; the separately named Qwen2.5-Coder and Qwen2.5-Math lines have their own specializations.\n\nA process assistant can receive a procedure and a question about one stage. Define the reader's role, ask for the actions relevant to that stage and require the answer to retain the procedure's original conditions. A useful output can separate the next action, the condition that makes it applicable and the information still required. This turns a broad request for advice into a response tied to the supplied process.\n\nFor a coding explanation, provide the function, relevant helper definitions and the input that causes confusion. Ask for the sequence of operations and the value returned for that input. For a mathematical explanation, state the symbols, assumptions and target expression before requesting the derivation. Both tasks use text; executing the program or making a separate numerical tool available is work for the application around the model.\n\nTables and JSON\n\nFor a table question, preserve the column headings and units, name the relevant rows and specify the comparison. The desired output might list the matching row identifiers and explain which supplied condition each row satisfies. If the table has missing values, state whether the answer should leave them absent or represent them explicitly.\n\nFor structured extraction, show the field names and required types. An input such as an item identifier, a stock quantity and a warehouse label can be converted into a record with those same fields. Ask for only the record when an application will parse it; ask for a separate prose explanation when the user needs to inspect the source interpretation. The model's documented JSON-generation ability is distinct from a particular interface enforcing a schema.\n\nMultilingual conversation is supported across more than 29 languages, including English, Chinese, Russian, German, French, Spanish, Portuguese, Italian, Japanese, Korean, Vietnamese, Thai and Arabic. Set the final language and provide any terminology that must remain unchanged. For a translated technical explanation, ask the model to retain variable names, quoted labels and units while adapting the surrounding prose to the reader.\n\nThe specific 14B release\n\nThe card reports 14.7 billion parameters, including 13.1 billion non-embedding parameters, and 48 Transformer layers. Its architecture uses rotary positional embeddings, SwiGLU, RMSNorm and attention QKV bias, with 40 query heads and 8 key/value heads in grouped-query attention. Pretraining and post-training produce this Instruct edition. Its parameter count and layer count differ from the 32B edition even where the family capabilities and published context figures coincide.\n\nThe model card lists a full context of 131,072 tokens and generation up to 8,192 tokens. The former concerns the conversation and material retained for a task; the latter concerns the generated answer. The quick-start's 512-token generation setting is only an example and does not replace the card's stated answer capacity. Image, video and audio understanding belong to separately named multimodal releases, not this text model.\n\nInput format and tool-assisted tasks\n\nThe maker's example applies the matching chat template to distinct system and user messages. Define the assistant's role and response rules separately from the material being examined. Supply a complete question and label the source text so that an instruction quoted inside the source is not confused with the task given by the application.\n\nThe official Qwen2.5 announcement also describes tool-calling templates and compatible integrations. A tool-assisted task needs the surrounding application to supply function descriptions, execute the selected operation and provide its result for the next answer. For example, a conversation can ask for a calculation using a supplied calculation tool; the function result then becomes information the model can explain. Tool availability and execution come from that integration, while this release provides the conversational text behavior.\n\nLong-text configuration\n\nThe published configuration initially covers 32,768 tokens. The documented extension for longer inputs uses YaRN, with an example scaling factor of 4.0 and an original maximum-position setting of 32,768. Static scaling may affect shorter-text behavior, so the maker recommends adding it when long contexts are needed.\n\nWhen preparing a long source, identify the section to revise or the question to answer and keep the supporting parts together. A clear request can ask for a corrected passage, a table of changes and the original section references. This uses the extended context for a concrete artifact while keeping the answer within the separate generation limit.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Filter a stock table with missing values\n\nUse this stock table: item_id | stock | reorder_at; A7 | 3 | 5; B2 | 8 | 4; C9 | unknown | 6. Return the identifiers requiring reorder under stock < reorder_at, then list rows that cannot be decided. Preserve identifiers and explain the condition for each selected or unresolved row.A reorder list and a separate unresolved-row list, each with a short source-based reason.Check that equality would not trigger reorder and that unknown stock is not treated as zero.Qwen/Qwen2.5-14B-InstructQwen2.5-14B-Instruct is a multilingual text model for instruction-based assistants, code and mathematics. Its own 14.7-billion-parameter release supports table interpretation, JSON generation and an 8,192-token answer limit, with extended-context configuration for long inputs.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Qwen2.5-14B-Instruct is the general Qwen2.5 family's instruction-tuned 14B-size edition. It accepts a text conversation and returns text: an explanation, a document, program code or structured fields. Its maker emphasizes instruction following, coding, mathematics, understanding structured data such as tables, and generating structured answers, particularly JSON.
What the family improves
The maker describes broader knowledge and stronger coding and mathematical abilities than the preceding Qwen2 generation, together with long-answer generation and better handling of varied system instructions. The family uses a pretraining corpus described as reaching 18 trillion tokens. These capabilities support a subject-specific assistant whose role and output are defined by the task. This model remains the general Instruct edition; the separately named Qwen2.5-Coder and Qwen2.5-Math lines have their own specializations.
A process assistant can receive a procedure and a question about one stage. Define the reader's role, ask for the actions relevant to that stage and require the answer to retain the procedure's original conditions. A useful output can separate the next action, the condition that makes it applicable and the information still required. This turns a broad request for advice into a response tied to the supplied process.
For a coding explanation, provide the function, relevant helper definitions and the input that causes confusion. Ask for the sequence of operations and the value returned for that input. For a mathematical explanation, state the symbols, assumptions and target expression before requesting the derivation. Both tasks use text; executing the program or making a separate numerical tool available is work for the application around the model.
Tables and JSON
For a table question, preserve the column headings and units, name the relevant rows and specify the comparison. The desired output might list the matching row identifiers and explain which supplied condition each row satisfies. If the table has missing values, state whether the answer should leave them absent or represent them explicitly.
For structured extraction, show the field names and required types. An input such as an item identifier, a stock quantity and a warehouse label can be converted into a record with those same fields. Ask for only the record when an application will parse it; ask for a separate prose explanation when the user needs to inspect the source interpretation. The model's documented JSON-generation ability is distinct from a particular interface enforcing a schema.
Multilingual conversation is supported across more than 29 languages, including English, Chinese, Russian, German, French, Spanish, Portuguese, Italian, Japanese, Korean, Vietnamese, Thai and Arabic. Set the final language and provide any terminology that must remain unchanged. For a translated technical explanation, ask the model to retain variable names, quoted labels and units while adapting the surrounding prose to the reader.
The specific 14B release
The card reports 14.7 billion parameters, including 13.1 billion non-embedding parameters, and 48 Transformer layers. Its architecture uses rotary positional embeddings, SwiGLU, RMSNorm and attention QKV bias, with 40 query heads and 8 key/value heads in grouped-query attention. Pretraining and post-training produce this Instruct edition. Its parameter count and layer count differ from the 32B edition even where the family capabilities and published context figures coincide.
The model card lists a full context of 131,072 tokens and generation up to 8,192 tokens. The former concerns the conversation and material retained for a task; the latter concerns the generated answer. The quick-start's 512-token generation setting is only an example and does not replace the card's stated answer capacity. Image, video and audio understanding belong to separately named multimodal releases, not this text model.
Input format and tool-assisted tasks
The maker's example applies the matching chat template to distinct system and user messages. Define the assistant's role and response rules separately from the material being examined. Supply a complete question and label the source text so that an instruction quoted inside the source is not confused with the task given by the application.
The official Qwen2.5 announcement also describes tool-calling templates and compatible integrations. A tool-assisted task needs the surrounding application to supply function descriptions, execute the selected operation and provide its result for the next answer. For example, a conversation can ask for a calculation using a supplied calculation tool; the function result then becomes information the model can explain. Tool availability and execution come from that integration, while this release provides the conversational text behavior.
Long-text configuration
The published configuration initially covers 32,768 tokens. The documented extension for longer inputs uses YaRN, with an example scaling factor of 4.0 and an original maximum-position setting of 32,768. Static scaling may affect shorter-text behavior, so the maker recommends adding it when long contexts are needed.
When preparing a long source, identify the section to revise or the question to answer and keep the supporting parts together. A clear request can ask for a corrected passage, a table of changes and the original section references. This uses the extended context for a concrete artifact while keeping the answer within the separate generation limit.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits Qwen/Qwen2.5-14B-Instruct | 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 $0.0002 / 1K tokens Output · Output tokens $0.0002 / 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": "Qwen/Qwen2.5-14B-Instruct", "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='Qwen/Qwen2.5-14B-Instruct',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='Qwen/Qwen2.5-14B-Instruct',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 Qwen/Qwen2.5-14B-Instruct, qwen2.5-14b-instruct
/chat/completions
Qwen/Qwen2.5-14B-InstructQwen2.5-14B-Instruct is a multilingual text model for instruction-based assistants, code and mathematics. Its own 14.7-billion-parameter release supports table interpretation, JSON generation and an 8,192-token answer limit, with extended-context configuration for long inputs.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Qwen2.5-14B-Instruct is the general Qwen2.5 family's instruction-tuned 14B-size edition. It accepts a text conversation and returns text: an explanation, a document, program code or structured fields. Its maker emphasizes instruction following, coding, mathematics, understanding structured data such as tables, and generating structured answers, particularly JSON.
What the family improves
The maker describes broader knowledge and stronger coding and mathematical abilities than the preceding Qwen2 generation, together with long-answer generation and better handling of varied system instructions. The family uses a pretraining corpus described as reaching 18 trillion tokens. These capabilities support a subject-specific assistant whose role and output are defined by the task. This model remains the general Instruct edition; the separately named Qwen2.5-Coder and Qwen2.5-Math lines have their own specializations.
A process assistant can receive a procedure and a question about one stage. Define the reader's role, ask for the actions relevant to that stage and require the answer to retain the procedure's original conditions. A useful output can separate the next action, the condition that makes it applicable and the information still required. This turns a broad request for advice into a response tied to the supplied process.
For a coding explanation, provide the function, relevant helper definitions and the input that causes confusion. Ask for the sequence of operations and the value returned for that input. For a mathematical explanation, state the symbols, assumptions and target expression before requesting the derivation. Both tasks use text; executing the program or making a separate numerical tool available is work for the application around the model.
Tables and JSON
For a table question, preserve the column headings and units, name the relevant rows and specify the comparison. The desired output might list the matching row identifiers and explain which supplied condition each row satisfies. If the table has missing values, state whether the answer should leave them absent or represent them explicitly.
For structured extraction, show the field names and required types. An input such as an item identifier, a stock quantity and a warehouse label can be converted into a record with those same fields. Ask for only the record when an application will parse it; ask for a separate prose explanation when the user needs to inspect the source interpretation. The model's documented JSON-generation ability is distinct from a particular interface enforcing a schema.
Multilingual conversation is supported across more than 29 languages, including English, Chinese, Russian, German, French, Spanish, Portuguese, Italian, Japanese, Korean, Vietnamese, Thai and Arabic. Set the final language and provide any terminology that must remain unchanged. For a translated technical explanation, ask the model to retain variable names, quoted labels and units while adapting the surrounding prose to the reader.
The specific 14B release
The card reports 14.7 billion parameters, including 13.1 billion non-embedding parameters, and 48 Transformer layers. Its architecture uses rotary positional embeddings, SwiGLU, RMSNorm and attention QKV bias, with 40 query heads and 8 key/value heads in grouped-query attention. Pretraining and post-training produce this Instruct edition. Its parameter count and layer count differ from the 32B edition even where the family capabilities and published context figures coincide.
The model card lists a full context of 131,072 tokens and generation up to 8,192 tokens. The former concerns the conversation and material retained for a task; the latter concerns the generated answer. The quick-start's 512-token generation setting is only an example and does not replace the card's stated answer capacity. Image, video and audio understanding belong to separately named multimodal releases, not this text model.
Input format and tool-assisted tasks
The maker's example applies the matching chat template to distinct system and user messages. Define the assistant's role and response rules separately from the material being examined. Supply a complete question and label the source text so that an instruction quoted inside the source is not confused with the task given by the application.
The official Qwen2.5 announcement also describes tool-calling templates and compatible integrations. A tool-assisted task needs the surrounding application to supply function descriptions, execute the selected operation and provide its result for the next answer. For example, a conversation can ask for a calculation using a supplied calculation tool; the function result then becomes information the model can explain. Tool availability and execution come from that integration, while this release provides the conversational text behavior.
Long-text configuration
The published configuration initially covers 32,768 tokens. The documented extension for longer inputs uses YaRN, with an example scaling factor of 4.0 and an original maximum-position setting of 32,768. Static scaling may affect shorter-text behavior, so the maker recommends adding it when long contexts are needed.
When preparing a long source, identify the section to revise or the question to answer and keep the supporting parts together. A clear request can ask for a corrected passage, a table of changes and the original section references. This uses the extended context for a concrete artifact while keeping the answer within the separate generation limit.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits Qwen/Qwen2.5-14B-Instruct | 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 $0.0002 / 1K tokens Output · Output tokens $0.0002 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "Qwen/Qwen2.5-14B-Instruct",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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': 'Qwen/Qwen2.5-14B-Instruct', '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': 'Qwen/Qwen2.5-14B-Instruct', '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 Qwen/Qwen2.5-14B-Instruct, qwen2.5-14b-instruct
/chat/completions
qwen2.5-14b-instructQwen2.5-14B-Instruct is a multilingual text model for instruction-based assistants, code and mathematics. Its own 14.7-billion-parameter release supports table interpretation, JSON generation and an 8,192-token answer limit, with extended-context configuration for long inputs.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Qwen2.5-14B-Instruct is the general Qwen2.5 family's instruction-tuned 14B-size edition. It accepts a text conversation and returns text: an explanation, a document, program code or structured fields. Its maker emphasizes instruction following, coding, mathematics, understanding structured data such as tables, and generating structured answers, particularly JSON.
What the family improves
The maker describes broader knowledge and stronger coding and mathematical abilities than the preceding Qwen2 generation, together with long-answer generation and better handling of varied system instructions. The family uses a pretraining corpus described as reaching 18 trillion tokens. These capabilities support a subject-specific assistant whose role and output are defined by the task. This model remains the general Instruct edition; the separately named Qwen2.5-Coder and Qwen2.5-Math lines have their own specializations.
A process assistant can receive a procedure and a question about one stage. Define the reader's role, ask for the actions relevant to that stage and require the answer to retain the procedure's original conditions. A useful output can separate the next action, the condition that makes it applicable and the information still required. This turns a broad request for advice into a response tied to the supplied process.
For a coding explanation, provide the function, relevant helper definitions and the input that causes confusion. Ask for the sequence of operations and the value returned for that input. For a mathematical explanation, state the symbols, assumptions and target expression before requesting the derivation. Both tasks use text; executing the program or making a separate numerical tool available is work for the application around the model.
Tables and JSON
For a table question, preserve the column headings and units, name the relevant rows and specify the comparison. The desired output might list the matching row identifiers and explain which supplied condition each row satisfies. If the table has missing values, state whether the answer should leave them absent or represent them explicitly.
For structured extraction, show the field names and required types. An input such as an item identifier, a stock quantity and a warehouse label can be converted into a record with those same fields. Ask for only the record when an application will parse it; ask for a separate prose explanation when the user needs to inspect the source interpretation. The model's documented JSON-generation ability is distinct from a particular interface enforcing a schema.
Multilingual conversation is supported across more than 29 languages, including English, Chinese, Russian, German, French, Spanish, Portuguese, Italian, Japanese, Korean, Vietnamese, Thai and Arabic. Set the final language and provide any terminology that must remain unchanged. For a translated technical explanation, ask the model to retain variable names, quoted labels and units while adapting the surrounding prose to the reader.
The specific 14B release
The card reports 14.7 billion parameters, including 13.1 billion non-embedding parameters, and 48 Transformer layers. Its architecture uses rotary positional embeddings, SwiGLU, RMSNorm and attention QKV bias, with 40 query heads and 8 key/value heads in grouped-query attention. Pretraining and post-training produce this Instruct edition. Its parameter count and layer count differ from the 32B edition even where the family capabilities and published context figures coincide.
The model card lists a full context of 131,072 tokens and generation up to 8,192 tokens. The former concerns the conversation and material retained for a task; the latter concerns the generated answer. The quick-start's 512-token generation setting is only an example and does not replace the card's stated answer capacity. Image, video and audio understanding belong to separately named multimodal releases, not this text model.
Input format and tool-assisted tasks
The maker's example applies the matching chat template to distinct system and user messages. Define the assistant's role and response rules separately from the material being examined. Supply a complete question and label the source text so that an instruction quoted inside the source is not confused with the task given by the application.
The official Qwen2.5 announcement also describes tool-calling templates and compatible integrations. A tool-assisted task needs the surrounding application to supply function descriptions, execute the selected operation and provide its result for the next answer. For example, a conversation can ask for a calculation using a supplied calculation tool; the function result then becomes information the model can explain. Tool availability and execution come from that integration, while this release provides the conversational text behavior.
Long-text configuration
The published configuration initially covers 32,768 tokens. The documented extension for longer inputs uses YaRN, with an example scaling factor of 4.0 and an original maximum-position setting of 32,768. Static scaling may affect shorter-text behavior, so the maker recommends adding it when long contexts are needed.
When preparing a long source, identify the section to revise or the question to answer and keep the supporting parts together. A clear request can ask for a corrected passage, a table of changes and the original section references. This uses the extended context for a concrete artifact while keeping the answer within the separate generation limit.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qwen2.5-14b-instruct | Default— |
Fieldmessages | Typemessage[] | RequirementRequired | Values & limits Minimum items: 1 | Default— |
Fieldmessages[].role | Typestring | RequirementRequired | Values & limits Model-specific | Default— |
Fieldmessages[].content | Typestring | RequirementOptional | Values & limits Applies when: Text conversation | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
Text · UTF8 text
messages[].content
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, messages |
Parametermaterial_types | Contracttext |
Parametermessages | Contractmessage array with role/content shape |
Parameterfile_material | Contractactual UTF-8 document inserted as literal text; no file ID inferred |
Parameteroptional_controls | Contractstream |
Parametercontrol_scope | ContractText conversation; stream is a boolean and defaults to false. |
Parameteroutput_modalities | Contracttext |
Parameterhosted_operations | Contractfalse |
Parametermultimodal_input_binding | Contractnull |
Method aliases: /chat/completions
Lifecycle: synchronous_or_streamed
Send exact model ID with messages.
Context length is not an output cap.
A text file may supply literal text; image/audio/file-object inputs need exact binding.
Tariff references do not add request options. Supported parameters are listed for the selected method.
| Configuration | Rate schedule | Charge |
|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Charge Input · Input tokens $0.0002 / 1K tokens Output · Output tokens $0.0002 / 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":"qwen2.5-14b-instruct","messages":[{"role":"user","content":"hello"}],"stream":false}')\n\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path("result.json").read_text())\nfor x in r.get("choices",[]):\n if x.get("message",{}).get("content"): print(x["message"]["content"])\nPY_RESULT\nfrom openai import OpenAI\nimport os\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nresult=client.chat.completions.create(model="qwen2.5-14b-instruct", messages=[{"role":"user","content":"hello"}], stream=False)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(result.to_dict(mode="json"))\njson or SSE
Keep every complete returned response, file and content part.
Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.
Keep request/response IDs and headers. No generic text job retrieval URL is supplied.
| Field | Type |
|---|---|
Fieldchoices[].index | Typeinteger |
Fieldchoices[].message.content | Typestring|null |
Fieldchoices[].message.tool_calls | Typetool_call[] |
Fieldchoices[].message.reasoning_content | Typestring |
Fieldchoices[].message.reasoning_details | Typeobject|array |
Fieldchoices[].finish_reason | Typestring|null |
Fieldusage | Typeobject |
| Response | Condition | Next step |
|---|---|---|
Response400 · invalid_request_error | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |
Ailoot Ultra Qwen/Qwen2.5-14B-Instruct, qwen2.5-14b-instruct
/chat/completions
qwen2.5-14b-instructQwen2.5-14B-Instruct is a multilingual text model for instruction-based assistants, code and mathematics. Its own 14.7-billion-parameter release supports table interpretation, JSON generation and an 8,192-token answer limit, with extended-context configuration for long inputs.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Qwen2.5-14B-Instruct is the general Qwen2.5 family's instruction-tuned 14B-size edition. It accepts a text conversation and returns text: an explanation, a document, program code or structured fields. Its maker emphasizes instruction following, coding, mathematics, understanding structured data such as tables, and generating structured answers, particularly JSON.
What the family improves
The maker describes broader knowledge and stronger coding and mathematical abilities than the preceding Qwen2 generation, together with long-answer generation and better handling of varied system instructions. The family uses a pretraining corpus described as reaching 18 trillion tokens. These capabilities support a subject-specific assistant whose role and output are defined by the task. This model remains the general Instruct edition; the separately named Qwen2.5-Coder and Qwen2.5-Math lines have their own specializations.
A process assistant can receive a procedure and a question about one stage. Define the reader's role, ask for the actions relevant to that stage and require the answer to retain the procedure's original conditions. A useful output can separate the next action, the condition that makes it applicable and the information still required. This turns a broad request for advice into a response tied to the supplied process.
For a coding explanation, provide the function, relevant helper definitions and the input that causes confusion. Ask for the sequence of operations and the value returned for that input. For a mathematical explanation, state the symbols, assumptions and target expression before requesting the derivation. Both tasks use text; executing the program or making a separate numerical tool available is work for the application around the model.
Tables and JSON
For a table question, preserve the column headings and units, name the relevant rows and specify the comparison. The desired output might list the matching row identifiers and explain which supplied condition each row satisfies. If the table has missing values, state whether the answer should leave them absent or represent them explicitly.
For structured extraction, show the field names and required types. An input such as an item identifier, a stock quantity and a warehouse label can be converted into a record with those same fields. Ask for only the record when an application will parse it; ask for a separate prose explanation when the user needs to inspect the source interpretation. The model's documented JSON-generation ability is distinct from a particular interface enforcing a schema.
Multilingual conversation is supported across more than 29 languages, including English, Chinese, Russian, German, French, Spanish, Portuguese, Italian, Japanese, Korean, Vietnamese, Thai and Arabic. Set the final language and provide any terminology that must remain unchanged. For a translated technical explanation, ask the model to retain variable names, quoted labels and units while adapting the surrounding prose to the reader.
The specific 14B release
The card reports 14.7 billion parameters, including 13.1 billion non-embedding parameters, and 48 Transformer layers. Its architecture uses rotary positional embeddings, SwiGLU, RMSNorm and attention QKV bias, with 40 query heads and 8 key/value heads in grouped-query attention. Pretraining and post-training produce this Instruct edition. Its parameter count and layer count differ from the 32B edition even where the family capabilities and published context figures coincide.
The model card lists a full context of 131,072 tokens and generation up to 8,192 tokens. The former concerns the conversation and material retained for a task; the latter concerns the generated answer. The quick-start's 512-token generation setting is only an example and does not replace the card's stated answer capacity. Image, video and audio understanding belong to separately named multimodal releases, not this text model.
Input format and tool-assisted tasks
The maker's example applies the matching chat template to distinct system and user messages. Define the assistant's role and response rules separately from the material being examined. Supply a complete question and label the source text so that an instruction quoted inside the source is not confused with the task given by the application.
The official Qwen2.5 announcement also describes tool-calling templates and compatible integrations. A tool-assisted task needs the surrounding application to supply function descriptions, execute the selected operation and provide its result for the next answer. For example, a conversation can ask for a calculation using a supplied calculation tool; the function result then becomes information the model can explain. Tool availability and execution come from that integration, while this release provides the conversational text behavior.
Long-text configuration
The published configuration initially covers 32,768 tokens. The documented extension for longer inputs uses YaRN, with an example scaling factor of 4.0 and an original maximum-position setting of 32,768. Static scaling may affect shorter-text behavior, so the maker recommends adding it when long contexts are needed.
When preparing a long source, identify the section to revise or the question to answer and keep the supporting parts together. A clear request can ask for a corrected passage, a table of changes and the original section references. This uses the extended context for a concrete artifact while keeping the answer within the separate generation limit.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qwen2.5-14b-instruct | 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 $0.0002 / 1K tokens Output · Output tokens $0.0002 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "qwen2.5-14b-instruct",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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': 'qwen2.5-14b-instruct', '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': 'qwen2.5-14b-instruct', '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 Qwen/Qwen2.5-14B-Instruct, qwen2.5-14b-instruct
/chat/completions
Technical example in English
Filter a stock table with missing values\n\nUse this stock table: item_id | stock | reorder_at; A7 | 3 | 5; B2 | 8 | 4; C9 | unknown | 6. Return the identifiers requiring reorder under stock < reorder_at, then list rows that cannot be decided. Preserve identifiers and explain the condition for each selected or unresolved row.A reorder list and a separate unresolved-row list, each with a short source-based reason.Check that equality would not trigger reorder and that unknown stock is not treated as zero.