Highlights: the fixed Instruct-2507 update
Qwen3-30B-A3B-Instruct-2507 is the updated non-thinking edition of Qwen3-30B-A3B. The maker highlights improvements in instruction following, logical reasoning, text comprehension, mathematics, science, coding and tool use, with broader long-tail knowledge across multiple languages and better alignment for open-ended tasks. It accepts text and produces text: an answer, explanation, code proposal or requested writing artifact.
Keep the fixed 2507 identity distinct from the original hybrid Qwen3-30B-A3B, its FP8 build and the Thinking-2507 edition. The model’s multilingual knowledge description does not give a separate language-count guarantee for this snapshot. Specify the target language, audience and terms that should remain unchanged when the task involves translation or rewriting.
Model overview
The mixture-of-experts model has 30.5 billion total parameters and activates 3.3 billion. It has 48 layers, 128 experts and eight experts selected per token. Its native context is 262,144 tokens. Activated parameters are not the size of the complete checkpoint, and architecture alone does not establish a fixed response time in an application.
This edition supports only non-thinking mode and does not generate explicit thinking blocks. Setting enable_thinking=False is unnecessary in the maker’s recipe. It can still show calculations or explain code in ordinary text; a request for supporting steps does not convert it into the separate Thinking checkpoint.
Preparing a useful text request
For a coding task, provide the relevant function or module, input constraints, observed behavior and required result. Ask for a proposed patch or complete function with an explanation of affected assumptions. For a mathematical or scientific question, give the full statement, units and definitions, then request a clearly delimited final answer supported by the supplied conditions.
For an open-ended writing task, specify the audience, purpose, tone and information that must appear. A useful response can be an editable draft organized by the requested sections, with unsupported assumptions identified separately. Compare the returned draft, calculations or proposed code with the supplied facts, definitions and requirements.
Agentic use
Qwen documents tool calling and recommends Qwen-Agent for templates and parsing, with configured or MCP-connected tools. State the permitted actions and observable completion conditions. Connected tools perform external operations and return observations; the model can use that feedback in a subsequent answer. A proposed command or retrieved-source claim should remain distinct from a result actually returned by the workflow.
A clear final artifact can be a code proposal, evidence table or concise report. Tool support does not itself create access to current sources, files or an execution environment through every interface. Keep the exact model’s non-thinking response contract instead of importing a hybrid model’s prompt switches or a Thinking edition’s output allowances.
Processing ultra-long text
The maker documents an optional workflow reaching approximately one million tokens through Dual Chunk Attention and MInference sparse attention. The first divides a long sequence into manageable chunks while preserving cross-chunk interactions; the second focuses computation on selected attention relationships. This is an additional configuration path beyond the native 262,144 context, using a special long-context configuration.
The recipe estimates roughly 240 GB of total GPU memory for model weights, cached sequence state and peak activations. It also describes separate capacity failures from sequence cache, activation memory or an input exceeding the configured length. The million-token workflow therefore depends on the configuration and resources; the headline should not be treated as an unconditional default.
Prepare a long input with document boundaries, section names or code identifiers and a concrete question. Reserve room for the answer and request the evidence supporting each conclusion.
Generation recommendations
Best Practices recommend temperature 0.7, top_p 0.8, top_k 20 and min_p 0. Where supported, a presence penalty between zero and two can reduce repeated text, while higher values may mix languages or slightly lower quality. The maker recommends a 16,384-token output allowance for most queries, rather than the longer budgets documented for Thinking-2507. This is a recommendation, not an independently established hard output ceiling.
Specify the final format explicitly, such as a mathematical delimiter or an answer field. The model’s documented input is text, so visual or audio evidence requires an appropriate separate representation before this workflow. Check calculations, quotations and generated code against the source. The useful result is a complete, reviewable text artifact whose fixed Instruct-2507 identity, non-thinking mode and conditional long-context procedure remain clear.
", "aboutText": "Highlights: the fixed Instruct-2507 update\n\nQwen3-30B-A3B-Instruct-2507 is the updated non-thinking edition of Qwen3-30B-A3B. The maker highlights improvements in instruction following, logical reasoning, text comprehension, mathematics, science, coding and tool use, with broader long-tail knowledge across multiple languages and better alignment for open-ended tasks. It accepts text and produces text: an answer, explanation, code proposal or requested writing artifact.\n\nKeep the fixed 2507 identity distinct from the original hybrid Qwen3-30B-A3B, its FP8 build and the Thinking-2507 edition. The model’s multilingual knowledge description does not give a separate language-count guarantee for this snapshot. Specify the target language, audience and terms that should remain unchanged when the task involves translation or rewriting.\n\nModel overview\n\nThe mixture-of-experts model has 30.5 billion total parameters and activates 3.3 billion. It has 48 layers, 128 experts and eight experts selected per token. Its native context is 262,144 tokens. Activated parameters are not the size of the complete checkpoint, and architecture alone does not establish a fixed response time in an application.\n\nThis edition supports only non-thinking mode and does not generate explicit thinking blocks. Setting enable_thinking=False is unnecessary in the maker’s recipe. It can still show calculations or explain code in ordinary text; a request for supporting steps does not convert it into the separate Thinking checkpoint.\n\nPreparing a useful text request\n\nFor a coding task, provide the relevant function or module, input constraints, observed behavior and required result. Ask for a proposed patch or complete function with an explanation of affected assumptions. For a mathematical or scientific question, give the full statement, units and definitions, then request a clearly delimited final answer supported by the supplied conditions.\n\nFor an open-ended writing task, specify the audience, purpose, tone and information that must appear. A useful response can be an editable draft organized by the requested sections, with unsupported assumptions identified separately. Compare the returned draft, calculations or proposed code with the supplied facts, definitions and requirements.\n\nAgentic use\n\nQwen documents tool calling and recommends Qwen-Agent for templates and parsing, with configured or MCP-connected tools. State the permitted actions and observable completion conditions. Connected tools perform external operations and return observations; the model can use that feedback in a subsequent answer. A proposed command or retrieved-source claim should remain distinct from a result actually returned by the workflow.\n\nA clear final artifact can be a code proposal, evidence table or concise report. Tool support does not itself create access to current sources, files or an execution environment through every interface. Keep the exact model’s non-thinking response contract instead of importing a hybrid model’s prompt switches or a Thinking edition’s output allowances.\n\nProcessing ultra-long text\n\nThe maker documents an optional workflow reaching approximately one million tokens through Dual Chunk Attention and MInference sparse attention. The first divides a long sequence into manageable chunks while preserving cross-chunk interactions; the second focuses computation on selected attention relationships. This is an additional configuration path beyond the native 262,144 context, using a special long-context configuration.\n\nThe recipe estimates roughly 240 GB of total GPU memory for model weights, cached sequence state and peak activations. It also describes separate capacity failures from sequence cache, activation memory or an input exceeding the configured length. The million-token workflow therefore depends on the configuration and resources; the headline should not be treated as an unconditional default.\n\nPrepare a long input with document boundaries, section names or code identifiers and a concrete question. Reserve room for the answer and request the evidence supporting each conclusion.\n\nGeneration recommendations\n\nBest Practices recommend temperature 0.7, top_p 0.8, top_k 20 and min_p 0. Where supported, a presence penalty between zero and two can reduce repeated text, while higher values may mix languages or slightly lower quality. The maker recommends a 16,384-token output allowance for most queries, rather than the longer budgets documented for Thinking-2507. This is a recommendation, not an independently established hard output ceiling.\n\nSpecify the final format explicitly, such as a mathematical delimiter or an answer field. The model’s documented input is text, so visual or audio evidence requires an appropriate separate representation before this workflow. Check calculations, quotations and generated code against the source. The useful result is a complete, reviewable text artifact whose fixed Instruct-2507 identity, non-thinking mode and conditional long-context procedure remain clear.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Draft a bounded project brief\n\nWrite a one-page-style brief in at most 170 words for a library's room-booking page. Facts: two rooms, maximum two-hour bookings, no recurring reservations, and a staff review for groups larger than eight. Use sections Goal, User steps, Rules and Open question. Include no payment features or assumed room capacities beyond the stated review threshold.An editable four-section project brief preserving the booking rules and one genuinely unanswered design question.The group-size threshold triggers staff review rather than being invented as an absolute room-capacity limit.qwen/qwen3-30b-a3b-instruct-2507Qwen3-30B-A3B-Instruct-2507 is Qwen’s fixed non-thinking July 2507 text edition, with 30.5 billion total and 3.3 billion activated parameters. It improves instruction following, coding, multilingual knowledge and open-ended writing, with a native 262,144-token context.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Highlights: the fixed Instruct-2507 update
Qwen3-30B-A3B-Instruct-2507 is the updated non-thinking edition of Qwen3-30B-A3B. The maker highlights improvements in instruction following, logical reasoning, text comprehension, mathematics, science, coding and tool use, with broader long-tail knowledge across multiple languages and better alignment for open-ended tasks. It accepts text and produces text: an answer, explanation, code proposal or requested writing artifact.
Keep the fixed 2507 identity distinct from the original hybrid Qwen3-30B-A3B, its FP8 build and the Thinking-2507 edition. The model’s multilingual knowledge description does not give a separate language-count guarantee for this snapshot. Specify the target language, audience and terms that should remain unchanged when the task involves translation or rewriting.
Model overview
The mixture-of-experts model has 30.5 billion total parameters and activates 3.3 billion. It has 48 layers, 128 experts and eight experts selected per token. Its native context is 262,144 tokens. Activated parameters are not the size of the complete checkpoint, and architecture alone does not establish a fixed response time in an application.
This edition supports only non-thinking mode and does not generate explicit thinking blocks. Setting enable_thinking=False is unnecessary in the maker’s recipe. It can still show calculations or explain code in ordinary text; a request for supporting steps does not convert it into the separate Thinking checkpoint.
Preparing a useful text request
For a coding task, provide the relevant function or module, input constraints, observed behavior and required result. Ask for a proposed patch or complete function with an explanation of affected assumptions. For a mathematical or scientific question, give the full statement, units and definitions, then request a clearly delimited final answer supported by the supplied conditions.
For an open-ended writing task, specify the audience, purpose, tone and information that must appear. A useful response can be an editable draft organized by the requested sections, with unsupported assumptions identified separately. Compare the returned draft, calculations or proposed code with the supplied facts, definitions and requirements.
Agentic use
Qwen documents tool calling and recommends Qwen-Agent for templates and parsing, with configured or MCP-connected tools. State the permitted actions and observable completion conditions. Connected tools perform external operations and return observations; the model can use that feedback in a subsequent answer. A proposed command or retrieved-source claim should remain distinct from a result actually returned by the workflow.
A clear final artifact can be a code proposal, evidence table or concise report. Tool support does not itself create access to current sources, files or an execution environment through every interface. Keep the exact model’s non-thinking response contract instead of importing a hybrid model’s prompt switches or a Thinking edition’s output allowances.
Processing ultra-long text
The maker documents an optional workflow reaching approximately one million tokens through Dual Chunk Attention and MInference sparse attention. The first divides a long sequence into manageable chunks while preserving cross-chunk interactions; the second focuses computation on selected attention relationships. This is an additional configuration path beyond the native 262,144 context, using a special long-context configuration.
The recipe estimates roughly 240 GB of total GPU memory for model weights, cached sequence state and peak activations. It also describes separate capacity failures from sequence cache, activation memory or an input exceeding the configured length. The million-token workflow therefore depends on the configuration and resources; the headline should not be treated as an unconditional default.
Prepare a long input with document boundaries, section names or code identifiers and a concrete question. Reserve room for the answer and request the evidence supporting each conclusion.
Generation recommendations
Best Practices recommend temperature 0.7, top_p 0.8, top_k 20 and min_p 0. Where supported, a presence penalty between zero and two can reduce repeated text, while higher values may mix languages or slightly lower quality. The maker recommends a 16,384-token output allowance for most queries, rather than the longer budgets documented for Thinking-2507. This is a recommendation, not an independently established hard output ceiling.
Specify the final format explicitly, such as a mathematical delimiter or an answer field. The model’s documented input is text, so visual or audio evidence requires an appropriate separate representation before this workflow. Check calculations, quotations and generated code against the source. The useful result is a complete, reviewable text artifact whose fixed Instruct-2507 identity, non-thinking mode and conditional long-context procedure remain clear.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qwen/qwen3-30b-a3b-instruct-2507 | Default— |
Fieldmessages | Typemessage[] | RequirementRequired | Values & limits Minimum items: 1 | Default— |
Fieldmessages[].role | Typestring | RequirementRequired | Values & limits Examples: system, user, assistant, tool, function Conditions: These roles are explicitly represented by Source compatibility types; the exact model role set remains model-specific. Model-specific | Default— |
Fieldmessages[].content | Typestring|content_part[]|null | RequirementOptional | Values & limits | Default— |
Fieldmessages[].tool_calls | Typetool_call[] | RequirementOptional | Values & limits | Default— |
Fieldmessages[].tool_call_id | Typestring | RequirementOptional | Values & limits Applies when: role=tool; use actual returned ID | Default— |
Fieldmessages[].name | Typestring | RequirementOptional | Values & limits | Default— |
Fieldmessages[].reasoning_content | Typestring | RequirementOptional | Values & limits Applies when: Round-trip actual returned reasoning where this model uses it | Default— |
Fieldmessages[].reasoning_details | Typeobject|array | RequirementOptional | Values & limits Model-specific | Default— |
Fieldmax_tokens | Typeinteger | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
Fieldmax_completion_tokens | Typeinteger | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
Fieldstream_options.include_usage | Typeboolean | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtemperature | Typenumber | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtop_p | Typenumber | RequirementOptional | Values & limits Model-specific | Default— |
Fieldstop | Typestring|string[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtools | Typefunction_tool[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtools[].type | Typestring | RequirementOptional | Values & limits function Model-specific | Default— |
Fieldtools[].function.name | Typestring | RequirementRequired | Values & limits Applies when: function tool supplied | Default— |
Fieldtools[].function.description | Typestring | RequirementOptional | Values & limits | Default— |
Fieldtools[].function.parameters | TypeJSON_schema | RequirementOptional | Values & limits | Default— |
Fieldtool_choice | Typestring|object | RequirementOptional | Values & limits Model-specific | Default— |
Fieldparallel_tool_calls | Typeboolean | RequirementOptional | Values & limits Model-specific | Default— |
Fieldresponse_format | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldreasoning_effort | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
Fieldreasoning | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldservice_tier | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
Fieldinstructions | Typestring | RequirementOptional | Values & limits Compatibility field | Default— |
Fieldfunctions | Typefunction[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldfunction_call | Typestring|object | RequirementOptional | Values & limits Model-specific | Default— |
Fieldprompt_cache_options | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldmodalities | Typestring[] | RequirementOptional | Values & limits text | Default— |
Fieldprovider | Typeobject | RequirementOptional | Values & limits Conditions: provider.options is rejected on this Ultra text route | Default— |
Fieldcache_control.ttl | Typestring | RequirementOptional | Values & limits Conditions: 1h is rejected in actual prompt-cache locations | Default— |
Text · UTF8 text
messages[].content
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, messages |
Parametermaterial_types | Contracttext |
Parametermessages | Contractmessage array with role/content shape |
Parameterfile_material | Contractactual UTF-8 document inserted as literal text; no file ID inferred |
Parameteroptional_controls | Contractstream, temperature, top_p, stop, max_tokens, max_completion_tokens, reasoning, response_format, tools, tool_choice |
Parametercontrol_scope | Contractmodel-specific; user function tools differ from hosted tools |
Parameteroutput_modalities | Contracttext |
Parameterhosted_operations | Contractfalse |
Parametermultimodal_input_binding | Contractnull |
Lifecycle: synchronous_or_streamed
Send exact model ID with messages.
Context length is not an output cap.
A text file may supply literal text; image/audio/file-object inputs need exact binding.
Tariff references do not add request options. Supported parameters are listed for the selected method.
Match each charge to the conditions shown. Use one rate for each set of alternative configurations.
| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
|---|---|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0002 / 1K tokens Output · Output tokens $0.0008 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0002 / 1K tokens Output · Output tokens $0.0008 / 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/qwen3-30b-a3b-instruct-2507", "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/qwen3-30b-a3b-instruct-2507',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/qwen3-30b-a3b-instruct-2507',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/qwen3-30b-a3b-instruct-2507
Use the method paths shown above.
qwen/qwen3-30b-a3b-instruct-2507Qwen3-30B-A3B-Instruct-2507 is Qwen’s fixed non-thinking July 2507 text edition, with 30.5 billion total and 3.3 billion activated parameters. It improves instruction following, coding, multilingual knowledge and open-ended writing, with a native 262,144-token context.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Highlights: the fixed Instruct-2507 update
Qwen3-30B-A3B-Instruct-2507 is the updated non-thinking edition of Qwen3-30B-A3B. The maker highlights improvements in instruction following, logical reasoning, text comprehension, mathematics, science, coding and tool use, with broader long-tail knowledge across multiple languages and better alignment for open-ended tasks. It accepts text and produces text: an answer, explanation, code proposal or requested writing artifact.
Keep the fixed 2507 identity distinct from the original hybrid Qwen3-30B-A3B, its FP8 build and the Thinking-2507 edition. The model’s multilingual knowledge description does not give a separate language-count guarantee for this snapshot. Specify the target language, audience and terms that should remain unchanged when the task involves translation or rewriting.
Model overview
The mixture-of-experts model has 30.5 billion total parameters and activates 3.3 billion. It has 48 layers, 128 experts and eight experts selected per token. Its native context is 262,144 tokens. Activated parameters are not the size of the complete checkpoint, and architecture alone does not establish a fixed response time in an application.
This edition supports only non-thinking mode and does not generate explicit thinking blocks. Setting enable_thinking=False is unnecessary in the maker’s recipe. It can still show calculations or explain code in ordinary text; a request for supporting steps does not convert it into the separate Thinking checkpoint.
Preparing a useful text request
For a coding task, provide the relevant function or module, input constraints, observed behavior and required result. Ask for a proposed patch or complete function with an explanation of affected assumptions. For a mathematical or scientific question, give the full statement, units and definitions, then request a clearly delimited final answer supported by the supplied conditions.
For an open-ended writing task, specify the audience, purpose, tone and information that must appear. A useful response can be an editable draft organized by the requested sections, with unsupported assumptions identified separately. Compare the returned draft, calculations or proposed code with the supplied facts, definitions and requirements.
Agentic use
Qwen documents tool calling and recommends Qwen-Agent for templates and parsing, with configured or MCP-connected tools. State the permitted actions and observable completion conditions. Connected tools perform external operations and return observations; the model can use that feedback in a subsequent answer. A proposed command or retrieved-source claim should remain distinct from a result actually returned by the workflow.
A clear final artifact can be a code proposal, evidence table or concise report. Tool support does not itself create access to current sources, files or an execution environment through every interface. Keep the exact model’s non-thinking response contract instead of importing a hybrid model’s prompt switches or a Thinking edition’s output allowances.
Processing ultra-long text
The maker documents an optional workflow reaching approximately one million tokens through Dual Chunk Attention and MInference sparse attention. The first divides a long sequence into manageable chunks while preserving cross-chunk interactions; the second focuses computation on selected attention relationships. This is an additional configuration path beyond the native 262,144 context, using a special long-context configuration.
The recipe estimates roughly 240 GB of total GPU memory for model weights, cached sequence state and peak activations. It also describes separate capacity failures from sequence cache, activation memory or an input exceeding the configured length. The million-token workflow therefore depends on the configuration and resources; the headline should not be treated as an unconditional default.
Prepare a long input with document boundaries, section names or code identifiers and a concrete question. Reserve room for the answer and request the evidence supporting each conclusion.
Generation recommendations
Best Practices recommend temperature 0.7, top_p 0.8, top_k 20 and min_p 0. Where supported, a presence penalty between zero and two can reduce repeated text, while higher values may mix languages or slightly lower quality. The maker recommends a 16,384-token output allowance for most queries, rather than the longer budgets documented for Thinking-2507. This is a recommendation, not an independently established hard output ceiling.
Specify the final format explicitly, such as a mathematical delimiter or an answer field. The model’s documented input is text, so visual or audio evidence requires an appropriate separate representation before this workflow. Check calculations, quotations and generated code against the source. The useful result is a complete, reviewable text artifact whose fixed Instruct-2507 identity, non-thinking mode and conditional long-context procedure remain clear.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qwen/qwen3-30b-a3b-instruct-2507 | Default— |
Fieldmessages | Typemessage[] | RequirementRequired | Values & limits | Default— |
Fieldmessages[].role | Typestring | RequirementRequired | Values & limits user, assistant | Default— |
Fieldmessages[].content | Typestring | RequirementRequired | Values & limits | Default— |
Fieldmax_tokens | Typeinteger | RequirementRequired | Values & limits | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
Text · UTF-8 text
messages[].content string
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, messages, max_tokens |
Parameteroptional_controls | Contractstream |
Parametermaterial_types | Contracttext |
Parametertext_file_material | ContractRead the actual UTF-8 document and put its text in the indicated input or message content string. |
Lifecycle: synchronous_or_streamed
Tariff references do not add request options. Supported parameters are listed for the selected method.
Match each charge to the conditions shown. Use one rate for each set of alternative configurations.
| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
|---|---|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0002 / 1K tokens Output · Output tokens $0.0008 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0002 / 1K tokens Output · Output tokens $0.0008 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "qwen/qwen3-30b-a3b-instruct-2507",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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/qwen3-30b-a3b-instruct-2507', '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/qwen3-30b-a3b-instruct-2507', '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/qwen3-30b-a3b-instruct-2507
Use the method paths shown above.
Technical example in English
Draft a bounded project brief\n\nWrite a one-page-style brief in at most 170 words for a library's room-booking page. Facts: two rooms, maximum two-hour bookings, no recurring reservations, and a staff review for groups larger than eight. Use sections Goal, User steps, Rules and Open question. Include no payment features or assumed room capacities beyond the stated review threshold.An editable four-section project brief preserving the booking rules and one genuinely unanswered design question.The group-size threshold triggers staff review rather than being invented as an absolute room-capacity limit.