qwen2-0.5b-instruct is the exact model selection for this Tongyi Qianwen text conversation profile. Send the instructions and source material as text and request a concrete written result. Practical prompts can turn a customer message into a proposed reply, reorganise meeting notes, or extract a small set of facts from a supplied passage. Specify the audience and the desired answer structure so the application has a clear result to consume.
Use POST /v1/chat/completions with model set to qwen2-0.5b-instruct and a nonempty messages array. Each message supplies a role and text content. Include the relevant earlier turns when a follow-up relies on the conversation. For document work, read the relevant UTF-8 text from the document and place that actual text in the message. Keep a section title or source label with each excerpt when the answer needs to distinguish several passages.
The text input allowance is 32,000 tokens. Keep the instructions, source passages and conversation history within that input budget. For a lengthy document, select the sections needed for the current question or process clearly labelled excerpts as separate tasks. State which passage the answer should use and what to return when a requested field is absent from it.
For a reply-drafting task, provide the customer’s wording together with the approved product information and ask for a response with a specific next step. For extraction, list fields such as issue, requested action and quoted evidence, then ask the model to return only facts found in the supplied text. For code explanation, paste the function and request a description of its inputs, transformations and output. These instructions define the task in the prompt and keep the result tied to the material you provide.
The optional boolean stream control selects response delivery: stream:false, the default, returns the assembled JSON response; stream:true delivers events as the response is produced. For JSON, read the returned choices and message content and retain usage when supplied. For streaming, assemble content deltas for each choice and retain the final finish information before storing the answer as complete. Keep the original response and request identity when a request ends ambiguously.
", "aboutText": "qwen2-0.5b-instruct is the exact model selection for this Tongyi Qianwen text conversation profile. Send the instructions and source material as text and request a concrete written result. Practical prompts can turn a customer message into a proposed reply, reorganise meeting notes, or extract a small set of facts from a supplied passage. Specify the audience and the desired answer structure so the application has a clear result to consume.\n\nUse POST /v1/chat/completions with model set to qwen2-0.5b-instruct and a nonempty messages array. Each message supplies a role and text content. Include the relevant earlier turns when a follow-up relies on the conversation. For document work, read the relevant UTF-8 text from the document and place that actual text in the message. Keep a section title or source label with each excerpt when the answer needs to distinguish several passages.\n\nThe text input allowance is 32,000 tokens. Keep the instructions, source passages and conversation history within that input budget. For a lengthy document, select the sections needed for the current question or process clearly labelled excerpts as separate tasks. State which passage the answer should use and what to return when a requested field is absent from it.\n\nFor a reply-drafting task, provide the customer’s wording together with the approved product information and ask for a response with a specific next step. For extraction, list fields such as issue, requested action and quoted evidence, then ask the model to return only facts found in the supplied text. For code explanation, paste the function and request a description of its inputs, transformations and output. These instructions define the task in the prompt and keep the result tied to the material you provide.\n\nThe optional boolean stream control selects response delivery: stream:false, the default, returns the assembled JSON response; stream:true delivers events as the response is produced. For JSON, read the returned choices and message content and retain usage when supplied. For streaming, assemble content deltas for each choice and retain the final finish information before storing the answer as complete. Keep the original response and request identity when a request ends ambiguously.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "0d725a0a4ab87ffd3895192601fa3a2d888df9c64e2c290d1c368738af2d1558", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "en", "methods": [ { "html": "qwen2-0.5b-instructqwen2-0.5b-instruct is a Tongyi Qianwen text model for message-based requests. Use its exact ID with Chat Completions to work on supplied passages: draft a reply, turn notes into a checklist, extract named fields or explain a short code fragment. Its text input allowance is 32,000 tokens.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
qwen2-0.5b-instruct is the exact model selection for this Tongyi Qianwen text conversation profile. Send the instructions and source material as text and request a concrete written result. Practical prompts can turn a customer message into a proposed reply, reorganise meeting notes, or extract a small set of facts from a supplied passage. Specify the audience and the desired answer structure so the application has a clear result to consume.
Use POST /v1/chat/completions with model set to qwen2-0.5b-instruct and a nonempty messages array. Each message supplies a role and text content. Include the relevant earlier turns when a follow-up relies on the conversation. For document work, read the relevant UTF-8 text from the document and place that actual text in the message. Keep a section title or source label with each excerpt when the answer needs to distinguish several passages.
The text input allowance is 32,000 tokens. Keep the instructions, source passages and conversation history within that input budget. For a lengthy document, select the sections needed for the current question or process clearly labelled excerpts as separate tasks. State which passage the answer should use and what to return when a requested field is absent from it.
For a reply-drafting task, provide the customer’s wording together with the approved product information and ask for a response with a specific next step. For extraction, list fields such as issue, requested action and quoted evidence, then ask the model to return only facts found in the supplied text. For code explanation, paste the function and request a description of its inputs, transformations and output. These instructions define the task in the prompt and keep the result tied to the material you provide.
The optional boolean stream control selects response delivery: stream:false, the default, returns the assembled JSON response; stream:true delivers events as the response is produced. For JSON, read the returned choices and message content and retain usage when supplied. For streaming, assemble content deltas for each choice and retain the final finish information before storing the answer as complete. Keep the original response and request identity when a request ends ambiguously.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qwen2-0.5b-instruct | Default— |
Fieldmessages | Typearray | RequirementRequired | Values & limits | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
Fieldmax_tokens | Typeinteger | RequirementOptional | Values & limits Minimum: 1 | Default— |
Fieldmax_completion_tokens | Typeinteger | RequirementOptional | Values & limits Minimum: 1 | Default— |
Fieldn | Typeinteger | RequirementOptional | Values & limits Minimum: 1 | Default— |
Fieldtemperature | Typenumber | RequirementOptional | Values & limits | Default— |
Fieldtop_p | Typenumber | RequirementOptional | Values & limits | Default— |
Fieldseed | Typeinteger | RequirementOptional | Values & limits | Default— |
Fieldstop | Type | RequirementOptional | Values & limits | Default— |
Fieldfrequency_penalty | Typenumber | RequirementOptional | Values & limits | Default— |
Fieldpresence_penalty | Typenumber | RequirementOptional | Values & limits | Default— |
Fielduser | Typestring | RequirementOptional | Values & limits | Default— |
Fieldtools | Typearray | RequirementOptional | Values & limits | Default— |
Fieldservice_tier | Typestring | RequirementOptional | Values & limits , auto, default | Default— |
Fieldmodalities | Typearray | RequirementOptional | Values & limits | Default— |
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, messages |
Parameteroptional | Contractstream, max_tokens, max_completion_tokens, n, temperature, top_p, seed, stop, frequency_penalty, presence_penalty, user, tools, service_tier, modalities |
Parametermaterial_types | Contracttext |
Parameterconditions | ContractUse text input and text output. Explicit cache, hosted tools and media are unavailable. Standard function tools remain a protocol feature and run in the client. |
Lifecycle: synchronous_json_or_sse
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 / 1K tokens Output · Output tokens $0 / 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}"\nexport AILOOT_API_KEY\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "qwen2-0.5b-instruct", "messages": [{"role": "user", "content": "Summarize the supplied text in three concise points."}], "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\n# Submit once. Retain the complete result, original identifiers and every response header.\nJSON or supported SSE
Keep every complete returned response, file and content part.
Retain the complete response, all actual results, original identifiers, usage and response headers.
Preserve the original response, headers and X-Client-Request-ID. An uncertain outcome does not authorize another creation.
Ailoot Ultra qwen2-0.5b-instruct
Use the method paths shown above.