Overview: repository-oriented coding
Qwen3-Coder-Flash is a Qwen3-based code-generation model. The maker says it inherits coding-agent capabilities from Qwen3-Coder-Plus and is optimized for repository-level understanding, stable tool calls and interaction over several turns. Its documented input and output are text. Use it for a coding task with supplied project context and a concrete artifact, such as a proposed patch, function or explanation.
The producer currently describes qwen3-coder-flash as functionally equivalent to qwen3-coder-flash-2025-07-28 and keeps that dated snapshot as a named version. Preserve the requested identity when recording model selection. The exact model page does not establish the parameter count or weight identity of an open Coder checkpoint, so the Flash name should not be converted into an unproved size or architecture claim.
Preparing repository evidence
Provide the relevant modules, interfaces, requirements and an input that demonstrates the behavior being discussed. Ask for an implementation proposal organized by affected components, then request the editable artifact separately from commentary. For a defect analysis, include the observed error or output and expected behavior. For a feature, describe the interactions and conditions the result must satisfy.
A useful response can show the diagnosis, proposed change and checks needed for review. If the task concerns a large project, keep file and function identifiers in the supplied material so the explanation can point to its evidence. Review the proposed changes against the supplied files, expected behavior and results returned by connected checks.
Multi-turn tools and feedback
The maker emphasizes tool interaction across several turns. A connected workflow can provide inspection or execution tools and return actual observations to the model. State the permitted actions and observable completion criteria. When a check fails, supply the real error and relevant code rather than merely ask for a retry. The model can revise its proposed work using that feedback; the application performs the actions.
The capability matrix supports Function Calling in Alibaba’s China (Beijing) profile and marks it unsupported in Singapore, Germany (Frankfurt) and US (Virginia). Tool availability is therefore conditional, not a promise from the model name alone. A text proposal, tool request and completed operation should remain distinguishable in the final report. Return a final report that separates the code proposal, requested tool calls and actual tool results.
Capabilities and result formatting
Enforced structured outputs and built-in web search are marked unsupported on the dedicated model page. A prompt may request a table or JSON-shaped text, but that does not create a schema-enforcement contract. A coding agent may receive current evidence from an application-supplied tool without the model itself having a built-in search capability.
Prefix Completion is unsupported in China (Beijing) and supported in Singapore, Germany (Frankfurt) and US (Virginia). Context Caching is supported for the undated alias in all four profiles, while the separately listed July 28 snapshot marks it unsupported. Both editions mark batch inference and fine-tuning unsupported. Ask for a final artifact that is easy to inspect and retain actual tool observations when a report claims something was checked.
Context and output limits
The specification gives a 1,000,000-token context window, a maximum input length of 997,952 tokens and a maximum output length of 65,536 tokens. These are separate limits; the largest input and largest output should not be assumed to fit together simultaneously within the context. Project text, history, tool results and generated source need room in the actual request budget.
A large context can place more repository evidence in one task. It remains useful to remove unrelated generated files, repeated material and irrelevant modules, while keeping the definitions and interfaces the change depends on. For a lengthy artifact, request the required files or functions explicitly and reserve enough response space for them. Keep code files and explanations separated so reviewers can inspect the proposed changes.
Practical result and substantive limits
For a repository change, request a patch with affected files, assumptions and real results returned by connected checks. For an algorithm, specify the input constraints and expected output before asking for code. The documented input is text, so a visual reference or recording needs an appropriate separate representation if the task is to use it as evidence.
Inspect generated syntax, interfaces and edge cases in the development workflow. A plausible explanation or tool-oriented model description is not evidence that code ran successfully. The practical result is a reviewable text or code artifact tied to supplied repository material, with the exact Flash identity, producer limits and conditional tool contract preserved.
", "aboutText": "Overview: repository-oriented coding\n\nQwen3-Coder-Flash is a Qwen3-based code-generation model. The maker says it inherits coding-agent capabilities from Qwen3-Coder-Plus and is optimized for repository-level understanding, stable tool calls and interaction over several turns. Its documented input and output are text. Use it for a coding task with supplied project context and a concrete artifact, such as a proposed patch, function or explanation.\n\nThe producer currently describes qwen3-coder-flash as functionally equivalent to qwen3-coder-flash-2025-07-28 and keeps that dated snapshot as a named version. Preserve the requested identity when recording model selection. The exact model page does not establish the parameter count or weight identity of an open Coder checkpoint, so the Flash name should not be converted into an unproved size or architecture claim.\n\nPreparing repository evidence\n\nProvide the relevant modules, interfaces, requirements and an input that demonstrates the behavior being discussed. Ask for an implementation proposal organized by affected components, then request the editable artifact separately from commentary. For a defect analysis, include the observed error or output and expected behavior. For a feature, describe the interactions and conditions the result must satisfy.\n\nA useful response can show the diagnosis, proposed change and checks needed for review. If the task concerns a large project, keep file and function identifiers in the supplied material so the explanation can point to its evidence. Review the proposed changes against the supplied files, expected behavior and results returned by connected checks.\n\nMulti-turn tools and feedback\n\nThe maker emphasizes tool interaction across several turns. A connected workflow can provide inspection or execution tools and return actual observations to the model. State the permitted actions and observable completion criteria. When a check fails, supply the real error and relevant code rather than merely ask for a retry. The model can revise its proposed work using that feedback; the application performs the actions.\n\nThe capability matrix supports Function Calling in Alibaba’s China (Beijing) profile and marks it unsupported in Singapore, Germany (Frankfurt) and US (Virginia). Tool availability is therefore conditional, not a promise from the model name alone. A text proposal, tool request and completed operation should remain distinguishable in the final report. Return a final report that separates the code proposal, requested tool calls and actual tool results.\n\nCapabilities and result formatting\n\nEnforced structured outputs and built-in web search are marked unsupported on the dedicated model page. A prompt may request a table or JSON-shaped text, but that does not create a schema-enforcement contract. A coding agent may receive current evidence from an application-supplied tool without the model itself having a built-in search capability.\n\nPrefix Completion is unsupported in China (Beijing) and supported in Singapore, Germany (Frankfurt) and US (Virginia). Context Caching is supported for the undated alias in all four profiles, while the separately listed July 28 snapshot marks it unsupported. Both editions mark batch inference and fine-tuning unsupported. Ask for a final artifact that is easy to inspect and retain actual tool observations when a report claims something was checked.\n\nContext and output limits\n\nThe specification gives a 1,000,000-token context window, a maximum input length of 997,952 tokens and a maximum output length of 65,536 tokens. These are separate limits; the largest input and largest output should not be assumed to fit together simultaneously within the context. Project text, history, tool results and generated source need room in the actual request budget.\n\nA large context can place more repository evidence in one task. It remains useful to remove unrelated generated files, repeated material and irrelevant modules, while keeping the definitions and interfaces the change depends on. For a lengthy artifact, request the required files or functions explicitly and reserve enough response space for them. Keep code files and explanations separated so reviewers can inspect the proposed changes.\n\nPractical result and substantive limits\n\nFor a repository change, request a patch with affected files, assumptions and real results returned by connected checks. For an algorithm, specify the input constraints and expected output before asking for code. The documented input is text, so a visual reference or recording needs an appropriate separate representation if the task is to use it as evidence.\n\nInspect generated syntax, interfaces and edge cases in the development workflow. A plausible explanation or tool-oriented model description is not evidence that code ran successfully. The practical result is a reviewable text or code artifact tied to supplied repository material, with the exact Flash identity, producer limits and conditional tool contract preserved.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Keep repository paths portable\n\nIn config.py, DATA_PATH = 'data/items.csv'. In runner.py, open(DATA_PATH) fails when the CLI is launched outside the repository directory. Propose a focused fix that anchors the resource path to the module location rather than the current working directory. Preserve the public CLI arguments and include a regression scenario launched from another directory.A small coordinated code proposal for the named modules and a regression scenario for an unrelated working directory.The proposed path does not depend on the launch directory and does not change the public CLI arguments.qwen/qwen3-coder-flashQwen3-Coder-Flash is Qwen’s text coding model for repository understanding and multi-turn tool interaction. Its specification lists a one-million-token context, a 997,952-token maximum input and a 65,536-token maximum output, with tool features scoped to the producer’s deployment profile.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Overview: repository-oriented coding
Qwen3-Coder-Flash is a Qwen3-based code-generation model. The maker says it inherits coding-agent capabilities from Qwen3-Coder-Plus and is optimized for repository-level understanding, stable tool calls and interaction over several turns. Its documented input and output are text. Use it for a coding task with supplied project context and a concrete artifact, such as a proposed patch, function or explanation.
The producer currently describes qwen3-coder-flash as functionally equivalent to qwen3-coder-flash-2025-07-28 and keeps that dated snapshot as a named version. Preserve the requested identity when recording model selection. The exact model page does not establish the parameter count or weight identity of an open Coder checkpoint, so the Flash name should not be converted into an unproved size or architecture claim.
Preparing repository evidence
Provide the relevant modules, interfaces, requirements and an input that demonstrates the behavior being discussed. Ask for an implementation proposal organized by affected components, then request the editable artifact separately from commentary. For a defect analysis, include the observed error or output and expected behavior. For a feature, describe the interactions and conditions the result must satisfy.
A useful response can show the diagnosis, proposed change and checks needed for review. If the task concerns a large project, keep file and function identifiers in the supplied material so the explanation can point to its evidence. Review the proposed changes against the supplied files, expected behavior and results returned by connected checks.
Multi-turn tools and feedback
The maker emphasizes tool interaction across several turns. A connected workflow can provide inspection or execution tools and return actual observations to the model. State the permitted actions and observable completion criteria. When a check fails, supply the real error and relevant code rather than merely ask for a retry. The model can revise its proposed work using that feedback; the application performs the actions.
The capability matrix supports Function Calling in Alibaba’s China (Beijing) profile and marks it unsupported in Singapore, Germany (Frankfurt) and US (Virginia). Tool availability is therefore conditional, not a promise from the model name alone. A text proposal, tool request and completed operation should remain distinguishable in the final report. Return a final report that separates the code proposal, requested tool calls and actual tool results.
Capabilities and result formatting
Enforced structured outputs and built-in web search are marked unsupported on the dedicated model page. A prompt may request a table or JSON-shaped text, but that does not create a schema-enforcement contract. A coding agent may receive current evidence from an application-supplied tool without the model itself having a built-in search capability.
Prefix Completion is unsupported in China (Beijing) and supported in Singapore, Germany (Frankfurt) and US (Virginia). Context Caching is supported for the undated alias in all four profiles, while the separately listed July 28 snapshot marks it unsupported. Both editions mark batch inference and fine-tuning unsupported. Ask for a final artifact that is easy to inspect and retain actual tool observations when a report claims something was checked.
Context and output limits
The specification gives a 1,000,000-token context window, a maximum input length of 997,952 tokens and a maximum output length of 65,536 tokens. These are separate limits; the largest input and largest output should not be assumed to fit together simultaneously within the context. Project text, history, tool results and generated source need room in the actual request budget.
A large context can place more repository evidence in one task. It remains useful to remove unrelated generated files, repeated material and irrelevant modules, while keeping the definitions and interfaces the change depends on. For a lengthy artifact, request the required files or functions explicitly and reserve enough response space for them. Keep code files and explanations separated so reviewers can inspect the proposed changes.
Practical result and substantive limits
For a repository change, request a patch with affected files, assumptions and real results returned by connected checks. For an algorithm, specify the input constraints and expected output before asking for code. The documented input is text, so a visual reference or recording needs an appropriate separate representation if the task is to use it as evidence.
Inspect generated syntax, interfaces and edge cases in the development workflow. A plausible explanation or tool-oriented model description is not evidence that code ran successfully. The practical result is a reviewable text or code artifact tied to supplied repository material, with the exact Flash identity, producer limits and conditional tool contract preserved.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qwen/qwen3-coder-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 $0.00039 / 1K tokens Output · Output tokens $0.00195 / 1K tokens Input · Cache read $0.000078 / 1K tokens Input · Cache write $0.0004875 / 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 $0.00039 / 1K tokens Output · Output tokens $0.00195 / 1K tokens Input · Cache read $0.000078 / 1K tokens Input · Cache write $0.0004875 / 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 including128,000 | Charge Input · Input tokens $0.00065 / 1K tokens Output · Output tokens $0.00325 / 1K tokens Input · Cache read $0.00013 / 1K tokens Input · Cache write $0.0008125 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationRequest-length tier 3 | Rate schedule— | Context tokens, more than128,000 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.00104 / 1K tokens Output · Output tokens $0.0052 / 1K tokens Input · Cache read $0.000208 / 1K tokens Input · Cache write $0.0013 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "qwen/qwen3-coder-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-coder-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-coder-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-coder-flash, qwen3-coder-flash
/chat/completions
qwen/qwen3-coder-flashQwen3-Coder-Flash is Qwen’s text coding model for repository understanding and multi-turn tool interaction. Its specification lists a one-million-token context, a 997,952-token maximum input and a 65,536-token maximum output, with tool features scoped to the producer’s deployment profile.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Overview: repository-oriented coding
Qwen3-Coder-Flash is a Qwen3-based code-generation model. The maker says it inherits coding-agent capabilities from Qwen3-Coder-Plus and is optimized for repository-level understanding, stable tool calls and interaction over several turns. Its documented input and output are text. Use it for a coding task with supplied project context and a concrete artifact, such as a proposed patch, function or explanation.
The producer currently describes qwen3-coder-flash as functionally equivalent to qwen3-coder-flash-2025-07-28 and keeps that dated snapshot as a named version. Preserve the requested identity when recording model selection. The exact model page does not establish the parameter count or weight identity of an open Coder checkpoint, so the Flash name should not be converted into an unproved size or architecture claim.
Preparing repository evidence
Provide the relevant modules, interfaces, requirements and an input that demonstrates the behavior being discussed. Ask for an implementation proposal organized by affected components, then request the editable artifact separately from commentary. For a defect analysis, include the observed error or output and expected behavior. For a feature, describe the interactions and conditions the result must satisfy.
A useful response can show the diagnosis, proposed change and checks needed for review. If the task concerns a large project, keep file and function identifiers in the supplied material so the explanation can point to its evidence. Review the proposed changes against the supplied files, expected behavior and results returned by connected checks.
Multi-turn tools and feedback
The maker emphasizes tool interaction across several turns. A connected workflow can provide inspection or execution tools and return actual observations to the model. State the permitted actions and observable completion criteria. When a check fails, supply the real error and relevant code rather than merely ask for a retry. The model can revise its proposed work using that feedback; the application performs the actions.
The capability matrix supports Function Calling in Alibaba’s China (Beijing) profile and marks it unsupported in Singapore, Germany (Frankfurt) and US (Virginia). Tool availability is therefore conditional, not a promise from the model name alone. A text proposal, tool request and completed operation should remain distinguishable in the final report. Return a final report that separates the code proposal, requested tool calls and actual tool results.
Capabilities and result formatting
Enforced structured outputs and built-in web search are marked unsupported on the dedicated model page. A prompt may request a table or JSON-shaped text, but that does not create a schema-enforcement contract. A coding agent may receive current evidence from an application-supplied tool without the model itself having a built-in search capability.
Prefix Completion is unsupported in China (Beijing) and supported in Singapore, Germany (Frankfurt) and US (Virginia). Context Caching is supported for the undated alias in all four profiles, while the separately listed July 28 snapshot marks it unsupported. Both editions mark batch inference and fine-tuning unsupported. Ask for a final artifact that is easy to inspect and retain actual tool observations when a report claims something was checked.
Context and output limits
The specification gives a 1,000,000-token context window, a maximum input length of 997,952 tokens and a maximum output length of 65,536 tokens. These are separate limits; the largest input and largest output should not be assumed to fit together simultaneously within the context. Project text, history, tool results and generated source need room in the actual request budget.
A large context can place more repository evidence in one task. It remains useful to remove unrelated generated files, repeated material and irrelevant modules, while keeping the definitions and interfaces the change depends on. For a lengthy artifact, request the required files or functions explicitly and reserve enough response space for them. Keep code files and explanations separated so reviewers can inspect the proposed changes.
Practical result and substantive limits
For a repository change, request a patch with affected files, assumptions and real results returned by connected checks. For an algorithm, specify the input constraints and expected output before asking for code. The documented input is text, so a visual reference or recording needs an appropriate separate representation if the task is to use it as evidence.
Inspect generated syntax, interfaces and edge cases in the development workflow. A plausible explanation or tool-oriented model description is not evidence that code ran successfully. The practical result is a reviewable text or code artifact tied to supplied repository material, with the exact Flash identity, producer limits and conditional tool contract preserved.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qwen/qwen3-coder-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 $0.00039 / 1K tokens Output · Output tokens $0.00195 / 1K tokens Input · Cache read $0.000078 / 1K tokens Input · Cache write $0.0004875 / 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 $0.00039 / 1K tokens Output · Output tokens $0.00195 / 1K tokens Input · Cache read $0.000078 / 1K tokens Input · Cache write $0.0004875 / 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 including128,000 | Charge Input · Input tokens $0.00065 / 1K tokens Output · Output tokens $0.00325 / 1K tokens Input · Cache read $0.00013 / 1K tokens Input · Cache write $0.0008125 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationRequest-length tier 3 | Rate schedule— | Context tokens, more than128,000 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.00104 / 1K tokens Output · Output tokens $0.0052 / 1K tokens Input · Cache read $0.000208 / 1K tokens Input · Cache write $0.0013 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "qwen/qwen3-coder-flash",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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-coder-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-coder-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-coder-flash, qwen3-coder-flash
/chat/completions
qwen3-coder-flashQwen3-Coder-Flash is Qwen’s text coding model for repository understanding and multi-turn tool interaction. Its specification lists a one-million-token context, a 997,952-token maximum input and a 65,536-token maximum output, with tool features scoped to the producer’s deployment profile.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Overview: repository-oriented coding
Qwen3-Coder-Flash is a Qwen3-based code-generation model. The maker says it inherits coding-agent capabilities from Qwen3-Coder-Plus and is optimized for repository-level understanding, stable tool calls and interaction over several turns. Its documented input and output are text. Use it for a coding task with supplied project context and a concrete artifact, such as a proposed patch, function or explanation.
The producer currently describes qwen3-coder-flash as functionally equivalent to qwen3-coder-flash-2025-07-28 and keeps that dated snapshot as a named version. Preserve the requested identity when recording model selection. The exact model page does not establish the parameter count or weight identity of an open Coder checkpoint, so the Flash name should not be converted into an unproved size or architecture claim.
Preparing repository evidence
Provide the relevant modules, interfaces, requirements and an input that demonstrates the behavior being discussed. Ask for an implementation proposal organized by affected components, then request the editable artifact separately from commentary. For a defect analysis, include the observed error or output and expected behavior. For a feature, describe the interactions and conditions the result must satisfy.
A useful response can show the diagnosis, proposed change and checks needed for review. If the task concerns a large project, keep file and function identifiers in the supplied material so the explanation can point to its evidence. Review the proposed changes against the supplied files, expected behavior and results returned by connected checks.
Multi-turn tools and feedback
The maker emphasizes tool interaction across several turns. A connected workflow can provide inspection or execution tools and return actual observations to the model. State the permitted actions and observable completion criteria. When a check fails, supply the real error and relevant code rather than merely ask for a retry. The model can revise its proposed work using that feedback; the application performs the actions.
The capability matrix supports Function Calling in Alibaba’s China (Beijing) profile and marks it unsupported in Singapore, Germany (Frankfurt) and US (Virginia). Tool availability is therefore conditional, not a promise from the model name alone. A text proposal, tool request and completed operation should remain distinguishable in the final report. Return a final report that separates the code proposal, requested tool calls and actual tool results.
Capabilities and result formatting
Enforced structured outputs and built-in web search are marked unsupported on the dedicated model page. A prompt may request a table or JSON-shaped text, but that does not create a schema-enforcement contract. A coding agent may receive current evidence from an application-supplied tool without the model itself having a built-in search capability.
Prefix Completion is unsupported in China (Beijing) and supported in Singapore, Germany (Frankfurt) and US (Virginia). Context Caching is supported for the undated alias in all four profiles, while the separately listed July 28 snapshot marks it unsupported. Both editions mark batch inference and fine-tuning unsupported. Ask for a final artifact that is easy to inspect and retain actual tool observations when a report claims something was checked.
Context and output limits
The specification gives a 1,000,000-token context window, a maximum input length of 997,952 tokens and a maximum output length of 65,536 tokens. These are separate limits; the largest input and largest output should not be assumed to fit together simultaneously within the context. Project text, history, tool results and generated source need room in the actual request budget.
A large context can place more repository evidence in one task. It remains useful to remove unrelated generated files, repeated material and irrelevant modules, while keeping the definitions and interfaces the change depends on. For a lengthy artifact, request the required files or functions explicitly and reserve enough response space for them. Keep code files and explanations separated so reviewers can inspect the proposed changes.
Practical result and substantive limits
For a repository change, request a patch with affected files, assumptions and real results returned by connected checks. For an algorithm, specify the input constraints and expected output before asking for code. The documented input is text, so a visual reference or recording needs an appropriate separate representation if the task is to use it as evidence.
Inspect generated syntax, interfaces and edge cases in the development workflow. A plausible explanation or tool-oriented model description is not evidence that code ran successfully. The practical result is a reviewable text or code artifact tied to supplied repository material, with the exact Flash identity, producer limits and conditional tool contract preserved.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qwen3-coder-flash | Default— |
Fieldmessages | Typemessage[] | RequirementRequired | Values & limits Minimum items: 1 | Default— |
Fieldmessages[].role | Typestring | RequirementRequired | Values & limits Model-specific | Default— |
Fieldmessages[].content | Typestring | RequirementOptional | Values & limits Applies when: Text conversation | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
Text · UTF8 text
messages[].content
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, messages |
Parametermaterial_types | Contracttext |
Parametermessages | Contractmessage array with role/content shape |
Parameterfile_material | Contractactual UTF-8 document inserted as literal text; no file ID inferred |
Parameteroptional_controls | Contractstream |
Parametercontrol_scope | ContractText conversation; stream is a boolean and defaults to false. |
Parameteroutput_modalities | Contracttext |
Parameterhosted_operations | Contractfalse |
Parametermultimodal_input_binding | Contractnull |
Method aliases: /chat/completions
Lifecycle: synchronous_or_streamed
Send exact model ID with messages.
Context length is not an output cap.
A text file may supply literal text; image/audio/file-object inputs need exact binding.
Tariff references do not add request options. Supported parameters are listed for the selected method.
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 $0.00039 / 1K tokens Output · Output tokens $0.00195 / 1K tokens Input · Cache read $0.000078 / 1K tokens Input · Cache write $0.0004875 / 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 $0.00039 / 1K tokens Output · Output tokens $0.00195 / 1K tokens Input · Cache read $0.000078 / 1K tokens Input · Cache write $0.0004875 / 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 including128,000 | Charge Input · Input tokens $0.00065 / 1K tokens Output · Output tokens $0.00325 / 1K tokens Input · Cache read $0.00013 / 1K tokens Input · Cache write $0.0008125 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationRequest-length tier 3 | Rate schedule— | Context tokens, more than128,000 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.00104 / 1K tokens Output · Output tokens $0.0052 / 1K tokens Input · Cache read $0.000208 / 1K tokens Input · Cache write $0.0013 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model":"qwen3-coder-flash","messages":[{"role":"user","content":"hello"}],"stream":false}')\n\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path("result.json").read_text())\nfor x in r.get("choices",[]):\n if x.get("message",{}).get("content"): print(x["message"]["content"])\nPY_RESULT\nfrom openai import OpenAI\nimport os\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nresult=client.chat.completions.create(model="qwen3-coder-flash", messages=[{"role":"user","content":"hello"}], stream=False)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(result.to_dict(mode="json"))\njson or SSE
Keep every complete returned response, file and content part.
Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.
Keep request/response IDs and headers. No generic text job retrieval URL is supplied.
| Field | Type |
|---|---|
Fieldchoices[].index | Typeinteger |
Fieldchoices[].message.content | Typestring|null |
Fieldchoices[].message.tool_calls | Typetool_call[] |
Fieldchoices[].message.reasoning_content | Typestring |
Fieldchoices[].message.reasoning_details | Typeobject|array |
Fieldchoices[].finish_reason | Typestring|null |
Fieldusage | Typeobject |
| Response | Condition | Next step |
|---|---|---|
Response400 · invalid_request_error | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |
Ailoot Ultra qwen/qwen3-coder-flash, qwen3-coder-flash
/chat/completions
qwen3-coder-flashQwen3-Coder-Flash is Qwen’s text coding model for repository understanding and multi-turn tool interaction. Its specification lists a one-million-token context, a 997,952-token maximum input and a 65,536-token maximum output, with tool features scoped to the producer’s deployment profile.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Overview: repository-oriented coding
Qwen3-Coder-Flash is a Qwen3-based code-generation model. The maker says it inherits coding-agent capabilities from Qwen3-Coder-Plus and is optimized for repository-level understanding, stable tool calls and interaction over several turns. Its documented input and output are text. Use it for a coding task with supplied project context and a concrete artifact, such as a proposed patch, function or explanation.
The producer currently describes qwen3-coder-flash as functionally equivalent to qwen3-coder-flash-2025-07-28 and keeps that dated snapshot as a named version. Preserve the requested identity when recording model selection. The exact model page does not establish the parameter count or weight identity of an open Coder checkpoint, so the Flash name should not be converted into an unproved size or architecture claim.
Preparing repository evidence
Provide the relevant modules, interfaces, requirements and an input that demonstrates the behavior being discussed. Ask for an implementation proposal organized by affected components, then request the editable artifact separately from commentary. For a defect analysis, include the observed error or output and expected behavior. For a feature, describe the interactions and conditions the result must satisfy.
A useful response can show the diagnosis, proposed change and checks needed for review. If the task concerns a large project, keep file and function identifiers in the supplied material so the explanation can point to its evidence. Review the proposed changes against the supplied files, expected behavior and results returned by connected checks.
Multi-turn tools and feedback
The maker emphasizes tool interaction across several turns. A connected workflow can provide inspection or execution tools and return actual observations to the model. State the permitted actions and observable completion criteria. When a check fails, supply the real error and relevant code rather than merely ask for a retry. The model can revise its proposed work using that feedback; the application performs the actions.
The capability matrix supports Function Calling in Alibaba’s China (Beijing) profile and marks it unsupported in Singapore, Germany (Frankfurt) and US (Virginia). Tool availability is therefore conditional, not a promise from the model name alone. A text proposal, tool request and completed operation should remain distinguishable in the final report. Return a final report that separates the code proposal, requested tool calls and actual tool results.
Capabilities and result formatting
Enforced structured outputs and built-in web search are marked unsupported on the dedicated model page. A prompt may request a table or JSON-shaped text, but that does not create a schema-enforcement contract. A coding agent may receive current evidence from an application-supplied tool without the model itself having a built-in search capability.
Prefix Completion is unsupported in China (Beijing) and supported in Singapore, Germany (Frankfurt) and US (Virginia). Context Caching is supported for the undated alias in all four profiles, while the separately listed July 28 snapshot marks it unsupported. Both editions mark batch inference and fine-tuning unsupported. Ask for a final artifact that is easy to inspect and retain actual tool observations when a report claims something was checked.
Context and output limits
The specification gives a 1,000,000-token context window, a maximum input length of 997,952 tokens and a maximum output length of 65,536 tokens. These are separate limits; the largest input and largest output should not be assumed to fit together simultaneously within the context. Project text, history, tool results and generated source need room in the actual request budget.
A large context can place more repository evidence in one task. It remains useful to remove unrelated generated files, repeated material and irrelevant modules, while keeping the definitions and interfaces the change depends on. For a lengthy artifact, request the required files or functions explicitly and reserve enough response space for them. Keep code files and explanations separated so reviewers can inspect the proposed changes.
Practical result and substantive limits
For a repository change, request a patch with affected files, assumptions and real results returned by connected checks. For an algorithm, specify the input constraints and expected output before asking for code. The documented input is text, so a visual reference or recording needs an appropriate separate representation if the task is to use it as evidence.
Inspect generated syntax, interfaces and edge cases in the development workflow. A plausible explanation or tool-oriented model description is not evidence that code ran successfully. The practical result is a reviewable text or code artifact tied to supplied repository material, with the exact Flash identity, producer limits and conditional tool contract preserved.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qwen3-coder-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 $0.00039 / 1K tokens Output · Output tokens $0.00195 / 1K tokens Input · Cache read $0.000078 / 1K tokens Input · Cache write $0.0004875 / 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 $0.00039 / 1K tokens Output · Output tokens $0.00195 / 1K tokens Input · Cache read $0.000078 / 1K tokens Input · Cache write $0.0004875 / 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 including128,000 | Charge Input · Input tokens $0.00065 / 1K tokens Output · Output tokens $0.00325 / 1K tokens Input · Cache read $0.00013 / 1K tokens Input · Cache write $0.0008125 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationRequest-length tier 3 | Rate schedule— | Context tokens, more than128,000 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.00104 / 1K tokens Output · Output tokens $0.0052 / 1K tokens Input · Cache read $0.000208 / 1K tokens Input · Cache write $0.0013 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "qwen3-coder-flash",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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': 'qwen3-coder-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': 'qwen3-coder-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-coder-flash, qwen3-coder-flash
/chat/completions
Technical example in English
Keep repository paths portable\n\nIn config.py, DATA_PATH = 'data/items.csv'. In runner.py, open(DATA_PATH) fails when the CLI is launched outside the repository directory. Propose a focused fix that anchors the resource path to the module location rather than the current working directory. Preserve the public CLI arguments and include a regression scenario launched from another directory.A small coordinated code proposal for the named modules and a regression scenario for an unrelated working directory.The proposed path does not depend on the launch directory and does not change the public CLI arguments.