The Qwen3.7 Flash release
Qwen3.7 Flash is a native vision-language model family for text, image and video understanding with textual responses. The maker’s release describes stronger multimodal perception and agent execution compared with Qwen3.6 Flash. Its practical task scope includes recognizing objects, understanding a visual scene, reasoning about spatial relationships and preparing code or explanations from visual material.
The official release names both qwen3.7-flash and the dated qwen3.7-flash-2026-07-15. Retain the exact model name when recording a result: the undated Flash name does not identify a fixed manufacturer snapshot. No open-checkpoint parameter count or numerical representation is established by the release description used here.
Object recognition, real-world perception and space
Give a scene image with a concrete question: which object matters, what relationship should be examined and which visible details should support the answer. For a diagram, preserve labels and supply the definitions needed to interpret them. A useful output separates observations from inferred relationships, making it easier to compare the explanation with the source.
For several images, label each input and request a comparison organized by those labels. For video, identify the relevant event and preserve the sequence or timing information. Review exact counts, spatial measurements and frame-level observations against the supplied material.
Multimodal agents
The release highlights Search Agent and code-interpreter agent scenarios, with more stable multi-step execution. In such a workflow, the application supplies the permitted tools, performs their actions and returns their observations. The model can use those results to update its plan. Describe the goal and the condition for completion, and ask for a final artifact plus any unresolved evidence. The producer lists function calling, structured outputs, prefix completion and context caching. Web search is supported in Beijing and Singapore and unsupported in the other listed regional scopes. Batch inference is supported for the Beijing alias and unsupported elsewhere; fine-tuning is unsupported.
A model’s agent specialization should not be confused with built-in access to current sources or an execution environment in every interface. When a task requires retrieval or running code, distinguish the result returned by an actual tool from a proposed action in the model’s text. This description does not establish which tools another application exposes.
Visual coding
Qwen describes improved coding informed by visual material. A useful request can combine a screenshot or layout with functional requirements and ask for editable code. Specify the framework or output form, interaction states and constraints in the supplied task. Request the generated artifact separately from the explanation so it can be reviewed or rendered by the development workflow.
For an existing interface, identify the intended change and the relevant source context rather than ask for an unrelated redesign. The model can connect a visual requirement with a coding proposal; that proposal is not evidence that the interface has been rendered or behaves correctly. These task examples apply the maker’s visual-coding scope without adding an execution guarantee.
Thinking and direct responses
The maker’s supported-model guide lists Qwen3.7 Flash as a hybrid-thinking family with thinking enabled by default. Its documented hybrid workflow can disable thinking for a direct answer. Keep the reasoning output distinct from the final answer when an interface provides both. Controls for a separately named Qwen-Omni model or an open dense model should not be imported solely because they share the Qwen name.
Use deeper analysis for a visual question that connects several observations; request a direct result for a straightforward description. Specify a checkable final structure, such as an observation table, a concise conclusion or code files, rather than rely on answer length as a quality signal.
Limits and input preparation
Alibaba’s dedicated Qwen3.7-Flash page gives a 1,000,000-token context, maximum input of 991,808 tokens for direct responses or 983,616 for thinking, and maximum output of 131,072 in either mode. It separately lists a maximum chain-of-thought length of 262,144 tokens. Keep the relevant visual detail readable, trim unrelated material and reserve space for the required result. Check object labels, spatial inferences, extracted text and code proposals against the supplied evidence. The useful description is the maker’s specific perception, agent and visual-coding scope, with its hybrid response mode preserved.
", "aboutText": "The Qwen3.7 Flash release\n\nQwen3.7 Flash is a native vision-language model family for text, image and video understanding with textual responses. The maker’s release describes stronger multimodal perception and agent execution compared with Qwen3.6 Flash. Its practical task scope includes recognizing objects, understanding a visual scene, reasoning about spatial relationships and preparing code or explanations from visual material.\n\nThe official release names both qwen3.7-flash and the dated qwen3.7-flash-2026-07-15. Retain the exact model name when recording a result: the undated Flash name does not identify a fixed manufacturer snapshot. No open-checkpoint parameter count or numerical representation is established by the release description used here.\n\nObject recognition, real-world perception and space\n\nGive a scene image with a concrete question: which object matters, what relationship should be examined and which visible details should support the answer. For a diagram, preserve labels and supply the definitions needed to interpret them. A useful output separates observations from inferred relationships, making it easier to compare the explanation with the source.\n\nFor several images, label each input and request a comparison organized by those labels. For video, identify the relevant event and preserve the sequence or timing information. Review exact counts, spatial measurements and frame-level observations against the supplied material.\n\nMultimodal agents\n\nThe release highlights Search Agent and code-interpreter agent scenarios, with more stable multi-step execution. In such a workflow, the application supplies the permitted tools, performs their actions and returns their observations. The model can use those results to update its plan. Describe the goal and the condition for completion, and ask for a final artifact plus any unresolved evidence. The producer lists function calling, structured outputs, prefix completion and context caching. Web search is supported in Beijing and Singapore and unsupported in the other listed regional scopes. Batch inference is supported for the Beijing alias and unsupported elsewhere; fine-tuning is unsupported.\n\nA model’s agent specialization should not be confused with built-in access to current sources or an execution environment in every interface. When a task requires retrieval or running code, distinguish the result returned by an actual tool from a proposed action in the model’s text. This description does not establish which tools another application exposes.\n\nVisual coding\n\nQwen describes improved coding informed by visual material. A useful request can combine a screenshot or layout with functional requirements and ask for editable code. Specify the framework or output form, interaction states and constraints in the supplied task. Request the generated artifact separately from the explanation so it can be reviewed or rendered by the development workflow.\n\nFor an existing interface, identify the intended change and the relevant source context rather than ask for an unrelated redesign. The model can connect a visual requirement with a coding proposal; that proposal is not evidence that the interface has been rendered or behaves correctly. These task examples apply the maker’s visual-coding scope without adding an execution guarantee.\n\nThinking and direct responses\n\nThe maker’s supported-model guide lists Qwen3.7 Flash as a hybrid-thinking family with thinking enabled by default. Its documented hybrid workflow can disable thinking for a direct answer. Keep the reasoning output distinct from the final answer when an interface provides both. Controls for a separately named Qwen-Omni model or an open dense model should not be imported solely because they share the Qwen name.\n\nUse deeper analysis for a visual question that connects several observations; request a direct result for a straightforward description. Specify a checkable final structure, such as an observation table, a concise conclusion or code files, rather than rely on answer length as a quality signal.\n\nLimits and input preparation\n\nAlibaba’s dedicated Qwen3.7-Flash page gives a 1,000,000-token context, maximum input of 991,808 tokens for direct responses or 983,616 for thinking, and maximum output of 131,072 in either mode. It separately lists a maximum chain-of-thought length of 262,144 tokens. Keep the relevant visual detail readable, trim unrelated material and reserve space for the required result. Check object labels, spatial inferences, extracted text and code proposals against the supplied evidence. The useful description is the maker’s specific perception, agent and visual-coding scope, with its hybrid response mode preserved.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Check a spatial claim from a text grid\n\nUse this written grid description: the red box is at row 2, column 1; the blue box is at row 2, column 3; the green box is at row 1, column 3. Rows increase downward and columns increase rightward. Describe their relative positions and assess the claim that green is directly above red.A relative-position description and a supported assessment of the claim, citing grid coordinates.Check that directly above requires the same column and that the stated row direction is respected.qwen/qwen3.7-flashQwen3.7 Flash is Qwen’s vision-language model family for text, images and video, returning text. The maker highlights stronger object recognition, spatial understanding, multimodal agent work and visual coding, with thinking enabled by default and an optional direct-answer mode.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
The Qwen3.7 Flash release
Qwen3.7 Flash is a native vision-language model family for text, image and video understanding with textual responses. The maker’s release describes stronger multimodal perception and agent execution compared with Qwen3.6 Flash. Its practical task scope includes recognizing objects, understanding a visual scene, reasoning about spatial relationships and preparing code or explanations from visual material.
The official release names both qwen3.7-flash and the dated qwen3.7-flash-2026-07-15. Retain the exact model name when recording a result: the undated Flash name does not identify a fixed manufacturer snapshot. No open-checkpoint parameter count or numerical representation is established by the release description used here.
Object recognition, real-world perception and space
Give a scene image with a concrete question: which object matters, what relationship should be examined and which visible details should support the answer. For a diagram, preserve labels and supply the definitions needed to interpret them. A useful output separates observations from inferred relationships, making it easier to compare the explanation with the source.
For several images, label each input and request a comparison organized by those labels. For video, identify the relevant event and preserve the sequence or timing information. Review exact counts, spatial measurements and frame-level observations against the supplied material.
Multimodal agents
The release highlights Search Agent and code-interpreter agent scenarios, with more stable multi-step execution. In such a workflow, the application supplies the permitted tools, performs their actions and returns their observations. The model can use those results to update its plan. Describe the goal and the condition for completion, and ask for a final artifact plus any unresolved evidence. The producer lists function calling, structured outputs, prefix completion and context caching. Web search is supported in Beijing and Singapore and unsupported in the other listed regional scopes. Batch inference is supported for the Beijing alias and unsupported elsewhere; fine-tuning is unsupported.
A model’s agent specialization should not be confused with built-in access to current sources or an execution environment in every interface. When a task requires retrieval or running code, distinguish the result returned by an actual tool from a proposed action in the model’s text. This description does not establish which tools another application exposes.
Visual coding
Qwen describes improved coding informed by visual material. A useful request can combine a screenshot or layout with functional requirements and ask for editable code. Specify the framework or output form, interaction states and constraints in the supplied task. Request the generated artifact separately from the explanation so it can be reviewed or rendered by the development workflow.
For an existing interface, identify the intended change and the relevant source context rather than ask for an unrelated redesign. The model can connect a visual requirement with a coding proposal; that proposal is not evidence that the interface has been rendered or behaves correctly. These task examples apply the maker’s visual-coding scope without adding an execution guarantee.
Thinking and direct responses
The maker’s supported-model guide lists Qwen3.7 Flash as a hybrid-thinking family with thinking enabled by default. Its documented hybrid workflow can disable thinking for a direct answer. Keep the reasoning output distinct from the final answer when an interface provides both. Controls for a separately named Qwen-Omni model or an open dense model should not be imported solely because they share the Qwen name.
Use deeper analysis for a visual question that connects several observations; request a direct result for a straightforward description. Specify a checkable final structure, such as an observation table, a concise conclusion or code files, rather than rely on answer length as a quality signal.
Limits and input preparation
Alibaba’s dedicated Qwen3.7-Flash page gives a 1,000,000-token context, maximum input of 991,808 tokens for direct responses or 983,616 for thinking, and maximum output of 131,072 in either mode. It separately lists a maximum chain-of-thought length of 262,144 tokens. Keep the relevant visual detail readable, trim unrelated material and reserve space for the required result. Check object labels, spatial inferences, extracted text and code proposals against the supplied evidence. The useful description is the maker’s specific perception, agent and visual-coding scope, with its hybrid response mode preserved.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qwen/qwen3.7-flash | 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 $0.00006 / 1K tokens Output · Output tokens $0.00026 / 1K tokens Input · Cache read $0.000012 / 1K tokens Input · Cache write $0.000076 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and including32,000 | Charge Input · Input tokens $0.00006 / 1K tokens Output · Output tokens $0.00026 / 1K tokens Input · Cache read $0.000012 / 1K tokens Input · Cache write $0.000076 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationRequest-length tier 2 | Rate schedule— | Context tokens, more than32,000 | Context tokens, up to and including256,000 | Charge Input · Input tokens $0.0002 / 1K tokens Output · Output tokens $0.0008 / 1K tokens Input · Cache read $0.00004 / 1K tokens Input · Cache write $0.00025 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationRequest-length tier 3 | Rate schedule— | Context tokens, more than256,000 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0004 / 1K tokens Output · Output tokens $0.0016 / 1K tokens Input · Cache read $0.00008 / 1K tokens Input · Cache write $0.0005 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "qwen/qwen3.7-flash", "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/qwen3.7-flash',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/qwen3.7-flash',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/qwen3.7-flash
Use the method paths shown above.
qwen/qwen3.7-flashQwen3.7 Flash is Qwen’s vision-language model family for text, images and video, returning text. The maker highlights stronger object recognition, spatial understanding, multimodal agent work and visual coding, with thinking enabled by default and an optional direct-answer mode.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
The Qwen3.7 Flash release
Qwen3.7 Flash is a native vision-language model family for text, image and video understanding with textual responses. The maker’s release describes stronger multimodal perception and agent execution compared with Qwen3.6 Flash. Its practical task scope includes recognizing objects, understanding a visual scene, reasoning about spatial relationships and preparing code or explanations from visual material.
The official release names both qwen3.7-flash and the dated qwen3.7-flash-2026-07-15. Retain the exact model name when recording a result: the undated Flash name does not identify a fixed manufacturer snapshot. No open-checkpoint parameter count or numerical representation is established by the release description used here.
Object recognition, real-world perception and space
Give a scene image with a concrete question: which object matters, what relationship should be examined and which visible details should support the answer. For a diagram, preserve labels and supply the definitions needed to interpret them. A useful output separates observations from inferred relationships, making it easier to compare the explanation with the source.
For several images, label each input and request a comparison organized by those labels. For video, identify the relevant event and preserve the sequence or timing information. Review exact counts, spatial measurements and frame-level observations against the supplied material.
Multimodal agents
The release highlights Search Agent and code-interpreter agent scenarios, with more stable multi-step execution. In such a workflow, the application supplies the permitted tools, performs their actions and returns their observations. The model can use those results to update its plan. Describe the goal and the condition for completion, and ask for a final artifact plus any unresolved evidence. The producer lists function calling, structured outputs, prefix completion and context caching. Web search is supported in Beijing and Singapore and unsupported in the other listed regional scopes. Batch inference is supported for the Beijing alias and unsupported elsewhere; fine-tuning is unsupported.
A model’s agent specialization should not be confused with built-in access to current sources or an execution environment in every interface. When a task requires retrieval or running code, distinguish the result returned by an actual tool from a proposed action in the model’s text. This description does not establish which tools another application exposes.
Visual coding
Qwen describes improved coding informed by visual material. A useful request can combine a screenshot or layout with functional requirements and ask for editable code. Specify the framework or output form, interaction states and constraints in the supplied task. Request the generated artifact separately from the explanation so it can be reviewed or rendered by the development workflow.
For an existing interface, identify the intended change and the relevant source context rather than ask for an unrelated redesign. The model can connect a visual requirement with a coding proposal; that proposal is not evidence that the interface has been rendered or behaves correctly. These task examples apply the maker’s visual-coding scope without adding an execution guarantee.
Thinking and direct responses
The maker’s supported-model guide lists Qwen3.7 Flash as a hybrid-thinking family with thinking enabled by default. Its documented hybrid workflow can disable thinking for a direct answer. Keep the reasoning output distinct from the final answer when an interface provides both. Controls for a separately named Qwen-Omni model or an open dense model should not be imported solely because they share the Qwen name.
Use deeper analysis for a visual question that connects several observations; request a direct result for a straightforward description. Specify a checkable final structure, such as an observation table, a concise conclusion or code files, rather than rely on answer length as a quality signal.
Limits and input preparation
Alibaba’s dedicated Qwen3.7-Flash page gives a 1,000,000-token context, maximum input of 991,808 tokens for direct responses or 983,616 for thinking, and maximum output of 131,072 in either mode. It separately lists a maximum chain-of-thought length of 262,144 tokens. Keep the relevant visual detail readable, trim unrelated material and reserve space for the required result. Check object labels, spatial inferences, extracted text and code proposals against the supplied evidence. The useful description is the maker’s specific perception, agent and visual-coding scope, with its hybrid response mode preserved.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qwen/qwen3.7-flash | 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 $0.00006 / 1K tokens Output · Output tokens $0.00026 / 1K tokens Input · Cache read $0.000012 / 1K tokens Input · Cache write $0.000076 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and including32,000 | Charge Input · Input tokens $0.00006 / 1K tokens Output · Output tokens $0.00026 / 1K tokens Input · Cache read $0.000012 / 1K tokens Input · Cache write $0.000076 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationRequest-length tier 2 | Rate schedule— | Context tokens, more than32,000 | Context tokens, up to and including256,000 | Charge Input · Input tokens $0.0002 / 1K tokens Output · Output tokens $0.0008 / 1K tokens Input · Cache read $0.00004 / 1K tokens Input · Cache write $0.00025 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationRequest-length tier 3 | Rate schedule— | Context tokens, more than256,000 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0004 / 1K tokens Output · Output tokens $0.0016 / 1K tokens Input · Cache read $0.00008 / 1K tokens Input · Cache write $0.0005 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "qwen/qwen3.7-flash",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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/qwen3.7-flash', '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/qwen3.7-flash', '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/qwen3.7-flash
Use the method paths shown above.
Technical example in English
Check a spatial claim from a text grid\n\nUse this written grid description: the red box is at row 2, column 1; the blue box is at row 2, column 3; the green box is at row 1, column 3. Rows increase downward and columns increase rightward. Describe their relative positions and assess the claim that green is directly above red.A relative-position description and a supported assessment of the claim, citing grid coordinates.Check that directly above requires the same column and that the stated row direction is respected.