Qwen2-7B-Instruct is the instruction-tuned, 7B-size edition of Qwen2 for conversation and tasks expressed in natural language. It is a text-input, text-output model: the answer can be an explanation, a translation, a document draft or program code. The maker identifies language understanding, generation, multilingual work, coding, mathematics and reasoning as its main areas of use.
Model details
Qwen2 includes separate base and instruction-tuned releases. This card concerns the Instruct edition, rather than the Qwen2-7B base model or the family's mixture-of-experts release. The maker's model-information table reports 7.07 billion parameters for the 7B-size model. Its decoder Transformer uses SwiGLU, attention QKV bias and grouped-query attention, with a tokenizer designed for natural languages and code. These are architecture and representation choices, not additional input modalities.
The release announcement describes training in English and Chinese plus 27 additional languages. Those include Russian, Czech and Polish; German, French and Spanish; Arabic, Persian and Turkish; Japanese and Korean; and further languages across South and Southeast Asia. A multilingual assistant can therefore receive an instruction and source material in different languages, but should still specify the language, terminology and audience of the final artifact.
Training and the Instruct distinction
After pretraining, the maker uses supervised fine-tuning and direct preference optimization. The instruction-tuned edition is intended to respond to a request in a conversation, while the base edition has a different role as a language-model foundation. Keep the edition name explicit when selecting a model or comparing prompt behavior. Training a model to follow instructions and supplying a precise instruction at use time are complementary parts of that workflow.
Preparing a conversational input
The model card's quick start separates a system instruction from the user's question and applies the matching chat template before generation. For an application-level task, the same practical distinction is useful: define the assistant's role and response rules separately from the source passage or code it must work on. A textual label written inside a document is not a substitute for correctly formatted conversation roles in the surrounding interface.
A technical explanation task can provide a function and one input example, then ask what each branch does and which conditions affect the result. A coding task can specify the accepted input, expected return value and constraints on changing existing behavior. Request the implementation followed by examples for a normal and an edge case. These are applications of the documented language and coding capabilities; generating code is a text result, while running it belongs to the application environment.
For multilingual editing, supply the original passage, the target audience and a small terminology list. Ask for a revision that retains the original names and conditions, then a short explanation of the changes. This is more specific than a request to improve the text: it defines which meaning must survive and what usable output should be returned.
Processing long texts
The maker documents context support up to 131,072 tokens, but the long-context instructions matter. Inputs beyond 32,768 tokens require the documented YaRN extension configuration. The published example uses a scaling factor of 4.0 with an original position setting of 32,768. The maker notes that the static extension setting can affect shorter-text behavior and recommends enabling it when long-context processing is actually needed.
Prepare a long document task with a focused question, named source sections and an explicit output structure. For example, provide several parts of a technical specification and ask for the requirements relevant to a particular change, with the source section kept beside each finding. A large input window is useful for retaining those parts together; the answer can still be a compact table rather than a retelling of the entire document.
Important boundaries
The 131,072-token figure is extended-context support, not permission to ignore the long-context configuration. The quick-start example's 512 generated tokens are an example setting, not a published maximum output capacity. This Instruct release is a text model and should not inherit image or video capabilities from Qwen-VL, or the specialized tool-integrated mathematical training of Qwen2.5-Math. Choose the named edition and prepare the text for the particular explanation, code or document you need.
", "aboutText": "Qwen2-7B-Instruct is the instruction-tuned, 7B-size edition of Qwen2 for conversation and tasks expressed in natural language. It is a text-input, text-output model: the answer can be an explanation, a translation, a document draft or program code. The maker identifies language understanding, generation, multilingual work, coding, mathematics and reasoning as its main areas of use.\n\nModel details\n\nQwen2 includes separate base and instruction-tuned releases. This card concerns the Instruct edition, rather than the Qwen2-7B base model or the family's mixture-of-experts release. The maker's model-information table reports 7.07 billion parameters for the 7B-size model. Its decoder Transformer uses SwiGLU, attention QKV bias and grouped-query attention, with a tokenizer designed for natural languages and code. These are architecture and representation choices, not additional input modalities.\n\nThe release announcement describes training in English and Chinese plus 27 additional languages. Those include Russian, Czech and Polish; German, French and Spanish; Arabic, Persian and Turkish; Japanese and Korean; and further languages across South and Southeast Asia. A multilingual assistant can therefore receive an instruction and source material in different languages, but should still specify the language, terminology and audience of the final artifact.\n\nTraining and the Instruct distinction\n\nAfter pretraining, the maker uses supervised fine-tuning and direct preference optimization. The instruction-tuned edition is intended to respond to a request in a conversation, while the base edition has a different role as a language-model foundation. Keep the edition name explicit when selecting a model or comparing prompt behavior. Training a model to follow instructions and supplying a precise instruction at use time are complementary parts of that workflow.\n\nPreparing a conversational input\n\nThe model card's quick start separates a system instruction from the user's question and applies the matching chat template before generation. For an application-level task, the same practical distinction is useful: define the assistant's role and response rules separately from the source passage or code it must work on. A textual label written inside a document is not a substitute for correctly formatted conversation roles in the surrounding interface.\n\nA technical explanation task can provide a function and one input example, then ask what each branch does and which conditions affect the result. A coding task can specify the accepted input, expected return value and constraints on changing existing behavior. Request the implementation followed by examples for a normal and an edge case. These are applications of the documented language and coding capabilities; generating code is a text result, while running it belongs to the application environment.\n\nFor multilingual editing, supply the original passage, the target audience and a small terminology list. Ask for a revision that retains the original names and conditions, then a short explanation of the changes. This is more specific than a request to improve the text: it defines which meaning must survive and what usable output should be returned.\n\nProcessing long texts\n\nThe maker documents context support up to 131,072 tokens, but the long-context instructions matter. Inputs beyond 32,768 tokens require the documented YaRN extension configuration. The published example uses a scaling factor of 4.0 with an original position setting of 32,768. The maker notes that the static extension setting can affect shorter-text behavior and recommends enabling it when long-context processing is actually needed.\n\nPrepare a long document task with a focused question, named source sections and an explicit output structure. For example, provide several parts of a technical specification and ask for the requirements relevant to a particular change, with the source section kept beside each finding. A large input window is useful for retaining those parts together; the answer can still be a compact table rather than a retelling of the entire document.\n\nImportant boundaries\n\nThe 131,072-token figure is extended-context support, not permission to ignore the long-context configuration. The quick-start example's 512 generated tokens are an example setting, not a published maximum output capacity. This Instruct release is a text model and should not inherit image or video capabilities from Qwen-VL, or the specialized tool-integrated mathematical training of Qwen2.5-Math. Choose the named edition and prepare the text for the particular explanation, code or document you need.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Translate a terminology-bound notice\n\nTranslate this notice into German for office staff: 'The access badge expires on 30 April. Collect a replacement from Reception before your next shift. Temporary passes are valid for one day.' Use Zugangskarte for access badge and Empfang for Reception. Preserve the date and conditions, then explain one translation choice in English.A complete German notice followed by one short English explanation of terminology or phrasing.The replacement is collected before the next shift and the temporary pass remains valid for one day.Qwen/Qwen2-7B-InstructQwen2-7B-Instruct is an instruction-tuned text model for multilingual dialogue, coding, mathematics and reasoning. Its maker documents context up to 131,072 tokens when the long-context configuration is enabled.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Qwen2-7B-Instruct is the instruction-tuned, 7B-size edition of Qwen2 for conversation and tasks expressed in natural language. It is a text-input, text-output model: the answer can be an explanation, a translation, a document draft or program code. The maker identifies language understanding, generation, multilingual work, coding, mathematics and reasoning as its main areas of use.
Model details
Qwen2 includes separate base and instruction-tuned releases. This card concerns the Instruct edition, rather than the Qwen2-7B base model or the family's mixture-of-experts release. The maker's model-information table reports 7.07 billion parameters for the 7B-size model. Its decoder Transformer uses SwiGLU, attention QKV bias and grouped-query attention, with a tokenizer designed for natural languages and code. These are architecture and representation choices, not additional input modalities.
The release announcement describes training in English and Chinese plus 27 additional languages. Those include Russian, Czech and Polish; German, French and Spanish; Arabic, Persian and Turkish; Japanese and Korean; and further languages across South and Southeast Asia. A multilingual assistant can therefore receive an instruction and source material in different languages, but should still specify the language, terminology and audience of the final artifact.
Training and the Instruct distinction
After pretraining, the maker uses supervised fine-tuning and direct preference optimization. The instruction-tuned edition is intended to respond to a request in a conversation, while the base edition has a different role as a language-model foundation. Keep the edition name explicit when selecting a model or comparing prompt behavior. Training a model to follow instructions and supplying a precise instruction at use time are complementary parts of that workflow.
Preparing a conversational input
The model card's quick start separates a system instruction from the user's question and applies the matching chat template before generation. For an application-level task, the same practical distinction is useful: define the assistant's role and response rules separately from the source passage or code it must work on. A textual label written inside a document is not a substitute for correctly formatted conversation roles in the surrounding interface.
A technical explanation task can provide a function and one input example, then ask what each branch does and which conditions affect the result. A coding task can specify the accepted input, expected return value and constraints on changing existing behavior. Request the implementation followed by examples for a normal and an edge case. These are applications of the documented language and coding capabilities; generating code is a text result, while running it belongs to the application environment.
For multilingual editing, supply the original passage, the target audience and a small terminology list. Ask for a revision that retains the original names and conditions, then a short explanation of the changes. This is more specific than a request to improve the text: it defines which meaning must survive and what usable output should be returned.
Processing long texts
The maker documents context support up to 131,072 tokens, but the long-context instructions matter. Inputs beyond 32,768 tokens require the documented YaRN extension configuration. The published example uses a scaling factor of 4.0 with an original position setting of 32,768. The maker notes that the static extension setting can affect shorter-text behavior and recommends enabling it when long-context processing is actually needed.
Prepare a long document task with a focused question, named source sections and an explicit output structure. For example, provide several parts of a technical specification and ask for the requirements relevant to a particular change, with the source section kept beside each finding. A large input window is useful for retaining those parts together; the answer can still be a compact table rather than a retelling of the entire document.
Important boundaries
The 131,072-token figure is extended-context support, not permission to ignore the long-context configuration. The quick-start example's 512 generated tokens are an example setting, not a published maximum output capacity. This Instruct release is a text model and should not inherit image or video capabilities from Qwen-VL, or the specialized tool-integrated mathematical training of Qwen2.5-Math. Choose the named edition and prepare the text for the particular explanation, code or document you need.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits Qwen/Qwen2-7B-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 $0.0001 / 1K tokens Output · Output tokens $0.0001 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "Qwen/Qwen2-7B-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/Qwen2-7B-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/Qwen2-7B-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/Qwen2-7B-Instruct
Use the method paths shown above.
Qwen/Qwen2-7B-InstructQwen2-7B-Instruct is an instruction-tuned text model for multilingual dialogue, coding, mathematics and reasoning. Its maker documents context up to 131,072 tokens when the long-context configuration is enabled.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Qwen2-7B-Instruct is the instruction-tuned, 7B-size edition of Qwen2 for conversation and tasks expressed in natural language. It is a text-input, text-output model: the answer can be an explanation, a translation, a document draft or program code. The maker identifies language understanding, generation, multilingual work, coding, mathematics and reasoning as its main areas of use.
Model details
Qwen2 includes separate base and instruction-tuned releases. This card concerns the Instruct edition, rather than the Qwen2-7B base model or the family's mixture-of-experts release. The maker's model-information table reports 7.07 billion parameters for the 7B-size model. Its decoder Transformer uses SwiGLU, attention QKV bias and grouped-query attention, with a tokenizer designed for natural languages and code. These are architecture and representation choices, not additional input modalities.
The release announcement describes training in English and Chinese plus 27 additional languages. Those include Russian, Czech and Polish; German, French and Spanish; Arabic, Persian and Turkish; Japanese and Korean; and further languages across South and Southeast Asia. A multilingual assistant can therefore receive an instruction and source material in different languages, but should still specify the language, terminology and audience of the final artifact.
Training and the Instruct distinction
After pretraining, the maker uses supervised fine-tuning and direct preference optimization. The instruction-tuned edition is intended to respond to a request in a conversation, while the base edition has a different role as a language-model foundation. Keep the edition name explicit when selecting a model or comparing prompt behavior. Training a model to follow instructions and supplying a precise instruction at use time are complementary parts of that workflow.
Preparing a conversational input
The model card's quick start separates a system instruction from the user's question and applies the matching chat template before generation. For an application-level task, the same practical distinction is useful: define the assistant's role and response rules separately from the source passage or code it must work on. A textual label written inside a document is not a substitute for correctly formatted conversation roles in the surrounding interface.
A technical explanation task can provide a function and one input example, then ask what each branch does and which conditions affect the result. A coding task can specify the accepted input, expected return value and constraints on changing existing behavior. Request the implementation followed by examples for a normal and an edge case. These are applications of the documented language and coding capabilities; generating code is a text result, while running it belongs to the application environment.
For multilingual editing, supply the original passage, the target audience and a small terminology list. Ask for a revision that retains the original names and conditions, then a short explanation of the changes. This is more specific than a request to improve the text: it defines which meaning must survive and what usable output should be returned.
Processing long texts
The maker documents context support up to 131,072 tokens, but the long-context instructions matter. Inputs beyond 32,768 tokens require the documented YaRN extension configuration. The published example uses a scaling factor of 4.0 with an original position setting of 32,768. The maker notes that the static extension setting can affect shorter-text behavior and recommends enabling it when long-context processing is actually needed.
Prepare a long document task with a focused question, named source sections and an explicit output structure. For example, provide several parts of a technical specification and ask for the requirements relevant to a particular change, with the source section kept beside each finding. A large input window is useful for retaining those parts together; the answer can still be a compact table rather than a retelling of the entire document.
Important boundaries
The 131,072-token figure is extended-context support, not permission to ignore the long-context configuration. The quick-start example's 512 generated tokens are an example setting, not a published maximum output capacity. This Instruct release is a text model and should not inherit image or video capabilities from Qwen-VL, or the specialized tool-integrated mathematical training of Qwen2.5-Math. Choose the named edition and prepare the text for the particular explanation, code or document you need.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits Qwen/Qwen2-7B-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 $0.0001 / 1K tokens Output · Output tokens $0.0001 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "Qwen/Qwen2-7B-Instruct",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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/Qwen2-7B-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/Qwen2-7B-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/Qwen2-7B-Instruct
Use the method paths shown above.
Technical example in English
Translate a terminology-bound notice\n\nTranslate this notice into German for office staff: 'The access badge expires on 30 April. Collect a replacement from Reception before your next shift. Temporary passes are valid for one day.' Use Zugangskarte for access badge and Empfang for Reception. Preserve the date and conditions, then explain one translation choice in English.A complete German notice followed by one short English explanation of terminology or phrasing.The replacement is collected before the next shift and the temporary pass remains valid for one day.