Highlights: repository-scale coding
Qwen3-Coder-30B-A3B-Instruct is an instruction-focused text model for coding agents. Qwen documents coding, browser-agent use and repository-scale understanding, with a dedicated function-call format and integration through workflows such as Qwen Code. Its input and output are text. Preserve this exact Coder checkpoint rather than substitute the general Qwen3-30B-A3B-Instruct-2507 or Qwen3-Coder-Next, whose training focus and generation guidance differ.
The native context is 262,144 tokens, with the maker describing extension to approximately one million using YaRN. A large context can place more repository evidence together, but a clear task still needs relevant modules, interfaces and requirements. Provide the expected artifact and observable behavior before asking for a code change.
Model overview
The mixture-of-experts model has 30.5 billion parameters in total and activates 3.3 billion. It has 48 layers, 128 experts and eight experts selected per token. Total parameters and activated parameters have different meanings; the activated figure is not the complete checkpoint size. Its causal-language-model configuration is a text model, not a vision or speech interface.
Coder-30B-A3B-Instruct supports only non-thinking mode and does not generate explicit thinking blocks. Setting enable_thinking=False is unnecessary in the maker’s example. It can still explain an algorithm or justify a patch in ordinary text. A request for reasoning steps should not be confused with enabling the separate Thinking behavior of another Qwen edition.
Preparing a development request
Supply the relevant code, an input demonstrating the current behavior, the observed result and the intended change. For an algorithm, specify input constraints and the required output before asking for an approach. For a repository modification, identify the affected feature and interfaces the implementation must preserve. Request an editable patch or complete function separately from explanatory commentary.
A useful response can organize the diagnosis, proposed change and checks needed to review it. When a task is driven by a visual reference or recorded behavior, provide an appropriate textual representation and retain identifiers that allow the result to be compared with the original. Compare the proposed patch with the supplied code, expected behavior and results returned by connected checks.
Agentic coding and browser workflows
The maker highlights tool calling and a specially designed function-call format. A connected agent workflow supplies tool descriptions, input schemas and observations, and performs the actual operations. Define permitted actions and a condition for completion, then return actual inspection or execution results to the model so it can update its proposed work.
Browser-agent capability means participation in a workflow with a connected browser tool, not automatic access to a user’s browser or current pages. The same distinction applies to repository inspection and code execution. A proposed command, tool request and completed operation should remain separate in the final report. Keep the native model’s tool format and parsing recipe rather than assume another model’s template is interchangeable.
Long context and configuration
The maker describes YaRN extension from the native 262,144-token context to about one million for repository-scale tasks. Use a context configuration appropriate to the repository material, while reserving space for tool observations and the result. Its quickstart also suggests a smaller context, such as 32,768, when memory pressure prevents the larger setting from working.
Keep code paths, function names and relevant definitions in a long input. Remove unrelated generated files or repeated material and reserve space for the answer. Source text, history, tool observations and generated code share the configured sequence allowance; the largest possible input should not be treated as perfect recall of every dependency.
Generation guidance
Best Practices recommend temperature 0.7, top_p 0.8, top_k 20 and repetition penalty 1.05. The exact repetition-penalty recommendation differs from several other Qwen models and remains part of this Coder edition’s recipe. Qwen recommends a 65,536-token generation allowance for most queries, which is a recommendation rather than an independently established hard maximum.
State the output language and form, such as a patch, complete function or explanation, and check the artifact’s syntax and interfaces in the real development workflow. The maker’s function example illustrates the tool mechanism; a tool contract still needs internally consistent argument names and return semantics in the application using it.
Substantive limits and useful result
This checkpoint’s documented input is text. It does not directly establish image, audio or video understanding. Generated code and a confident explanation are draft artifacts until the relevant checks or observations are actually returned by the connected environment. The useful result is an inspectable implementation proposal tied to the supplied repository conditions, with its exact Coder identity, non-thinking mode and producer generation guidance preserved.
", "aboutText": "Highlights: repository-scale coding\n\nQwen3-Coder-30B-A3B-Instruct is an instruction-focused text model for coding agents. Qwen documents coding, browser-agent use and repository-scale understanding, with a dedicated function-call format and integration through workflows such as Qwen Code. Its input and output are text. Preserve this exact Coder checkpoint rather than substitute the general Qwen3-30B-A3B-Instruct-2507 or Qwen3-Coder-Next, whose training focus and generation guidance differ.\n\nThe native context is 262,144 tokens, with the maker describing extension to approximately one million using YaRN. A large context can place more repository evidence together, but a clear task still needs relevant modules, interfaces and requirements. Provide the expected artifact and observable behavior before asking for a code change.\n\nModel overview\n\nThe mixture-of-experts model has 30.5 billion parameters in total and activates 3.3 billion. It has 48 layers, 128 experts and eight experts selected per token. Total parameters and activated parameters have different meanings; the activated figure is not the complete checkpoint size. Its causal-language-model configuration is a text model, not a vision or speech interface.\n\nCoder-30B-A3B-Instruct supports only non-thinking mode and does not generate explicit thinking blocks. Setting enable_thinking=False is unnecessary in the maker’s example. It can still explain an algorithm or justify a patch in ordinary text. A request for reasoning steps should not be confused with enabling the separate Thinking behavior of another Qwen edition.\n\nPreparing a development request\n\nSupply the relevant code, an input demonstrating the current behavior, the observed result and the intended change. For an algorithm, specify input constraints and the required output before asking for an approach. For a repository modification, identify the affected feature and interfaces the implementation must preserve. Request an editable patch or complete function separately from explanatory commentary.\n\nA useful response can organize the diagnosis, proposed change and checks needed to review it. When a task is driven by a visual reference or recorded behavior, provide an appropriate textual representation and retain identifiers that allow the result to be compared with the original. Compare the proposed patch with the supplied code, expected behavior and results returned by connected checks.\n\nAgentic coding and browser workflows\n\nThe maker highlights tool calling and a specially designed function-call format. A connected agent workflow supplies tool descriptions, input schemas and observations, and performs the actual operations. Define permitted actions and a condition for completion, then return actual inspection or execution results to the model so it can update its proposed work.\n\nBrowser-agent capability means participation in a workflow with a connected browser tool, not automatic access to a user’s browser or current pages. The same distinction applies to repository inspection and code execution. A proposed command, tool request and completed operation should remain separate in the final report. Keep the native model’s tool format and parsing recipe rather than assume another model’s template is interchangeable.\n\nLong context and configuration\n\nThe maker describes YaRN extension from the native 262,144-token context to about one million for repository-scale tasks. Use a context configuration appropriate to the repository material, while reserving space for tool observations and the result. Its quickstart also suggests a smaller context, such as 32,768, when memory pressure prevents the larger setting from working.\n\nKeep code paths, function names and relevant definitions in a long input. Remove unrelated generated files or repeated material and reserve space for the answer. Source text, history, tool observations and generated code share the configured sequence allowance; the largest possible input should not be treated as perfect recall of every dependency.\n\nGeneration guidance\n\nBest Practices recommend temperature 0.7, top_p 0.8, top_k 20 and repetition penalty 1.05. The exact repetition-penalty recommendation differs from several other Qwen models and remains part of this Coder edition’s recipe. Qwen recommends a 65,536-token generation allowance for most queries, which is a recommendation rather than an independently established hard maximum.\n\nState the output language and form, such as a patch, complete function or explanation, and check the artifact’s syntax and interfaces in the real development workflow. The maker’s function example illustrates the tool mechanism; a tool contract still needs internally consistent argument names and return semantics in the application using it.\n\nSubstantive limits and useful result\n\nThis checkpoint’s documented input is text. It does not directly establish image, audio or video understanding. Generated code and a confident explanation are draft artifacts until the relevant checks or observations are actually returned by the connected environment. The useful result is an inspectable implementation proposal tied to the supplied repository conditions, with its exact Coder identity, non-thinking mode and producer generation guidance preserved.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Implement interval overlap correctly\n\nImplement overlaps(a, b) for two half-open intervals [start, end), using numeric endpoints. Intervals touching at an endpoint do not overlap. Reject intervals with start greater than end; empty intervals never overlap. Return a complete Python function and tests for genuine overlap, touching, empty and reversed intervals. Keep the interface limited to two pairs.A complete Python function and four focused tests expressing the interval contract.Check that [1, 3) and [3, 5) return false and an empty interval cannot overlap a containing interval.qwen/qwen3-coder-30b-a3b-instructQwen3-Coder-30B-A3B-Instruct is Qwen’s non-thinking text coding model with 30.5 billion total and 3.3 billion activated parameters. It targets repository-scale development, coding and browser-agent workflows, with native 262,144-token context and a dedicated function-call format.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Highlights: repository-scale coding
Qwen3-Coder-30B-A3B-Instruct is an instruction-focused text model for coding agents. Qwen documents coding, browser-agent use and repository-scale understanding, with a dedicated function-call format and integration through workflows such as Qwen Code. Its input and output are text. Preserve this exact Coder checkpoint rather than substitute the general Qwen3-30B-A3B-Instruct-2507 or Qwen3-Coder-Next, whose training focus and generation guidance differ.
The native context is 262,144 tokens, with the maker describing extension to approximately one million using YaRN. A large context can place more repository evidence together, but a clear task still needs relevant modules, interfaces and requirements. Provide the expected artifact and observable behavior before asking for a code change.
Model overview
The mixture-of-experts model has 30.5 billion parameters in total and activates 3.3 billion. It has 48 layers, 128 experts and eight experts selected per token. Total parameters and activated parameters have different meanings; the activated figure is not the complete checkpoint size. Its causal-language-model configuration is a text model, not a vision or speech interface.
Coder-30B-A3B-Instruct supports only non-thinking mode and does not generate explicit thinking blocks. Setting enable_thinking=False is unnecessary in the maker’s example. It can still explain an algorithm or justify a patch in ordinary text. A request for reasoning steps should not be confused with enabling the separate Thinking behavior of another Qwen edition.
Preparing a development request
Supply the relevant code, an input demonstrating the current behavior, the observed result and the intended change. For an algorithm, specify input constraints and the required output before asking for an approach. For a repository modification, identify the affected feature and interfaces the implementation must preserve. Request an editable patch or complete function separately from explanatory commentary.
A useful response can organize the diagnosis, proposed change and checks needed to review it. When a task is driven by a visual reference or recorded behavior, provide an appropriate textual representation and retain identifiers that allow the result to be compared with the original. Compare the proposed patch with the supplied code, expected behavior and results returned by connected checks.
Agentic coding and browser workflows
The maker highlights tool calling and a specially designed function-call format. A connected agent workflow supplies tool descriptions, input schemas and observations, and performs the actual operations. Define permitted actions and a condition for completion, then return actual inspection or execution results to the model so it can update its proposed work.
Browser-agent capability means participation in a workflow with a connected browser tool, not automatic access to a user’s browser or current pages. The same distinction applies to repository inspection and code execution. A proposed command, tool request and completed operation should remain separate in the final report. Keep the native model’s tool format and parsing recipe rather than assume another model’s template is interchangeable.
Long context and configuration
The maker describes YaRN extension from the native 262,144-token context to about one million for repository-scale tasks. Use a context configuration appropriate to the repository material, while reserving space for tool observations and the result. Its quickstart also suggests a smaller context, such as 32,768, when memory pressure prevents the larger setting from working.
Keep code paths, function names and relevant definitions in a long input. Remove unrelated generated files or repeated material and reserve space for the answer. Source text, history, tool observations and generated code share the configured sequence allowance; the largest possible input should not be treated as perfect recall of every dependency.
Generation guidance
Best Practices recommend temperature 0.7, top_p 0.8, top_k 20 and repetition penalty 1.05. The exact repetition-penalty recommendation differs from several other Qwen models and remains part of this Coder edition’s recipe. Qwen recommends a 65,536-token generation allowance for most queries, which is a recommendation rather than an independently established hard maximum.
State the output language and form, such as a patch, complete function or explanation, and check the artifact’s syntax and interfaces in the real development workflow. The maker’s function example illustrates the tool mechanism; a tool contract still needs internally consistent argument names and return semantics in the application using it.
Substantive limits and useful result
This checkpoint’s documented input is text. It does not directly establish image, audio or video understanding. Generated code and a confident explanation are draft artifacts until the relevant checks or observations are actually returned by the connected environment. The useful result is an inspectable implementation proposal tied to the supplied repository conditions, with its exact Coder identity, non-thinking mode and producer generation guidance preserved.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qwen/qwen3-coder-30b-a3b-instruct | Default— |
Fieldmessages | Typemessage[] | RequirementRequired | Values & limits Minimum items: 1 | Default— |
Fieldmessages[].role | Typestring | RequirementRequired | Values & limits Examples: system, user, assistant, tool, function Conditions: These roles are explicitly represented by Source compatibility types; the exact model role set remains model-specific. Model-specific | Default— |
Fieldmessages[].content | Typestring|content_part[]|null | RequirementOptional | Values & limits | Default— |
Fieldmessages[].tool_calls | Typetool_call[] | RequirementOptional | Values & limits | Default— |
Fieldmessages[].tool_call_id | Typestring | RequirementOptional | Values & limits Applies when: role=tool; use actual returned ID | Default— |
Fieldmessages[].name | Typestring | RequirementOptional | Values & limits | Default— |
Fieldmessages[].reasoning_content | Typestring | RequirementOptional | Values & limits Applies when: Round-trip actual returned reasoning where this model uses it | Default— |
Fieldmessages[].reasoning_details | Typeobject|array | RequirementOptional | Values & limits Model-specific | Default— |
Fieldmax_tokens | Typeinteger | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
Fieldmax_completion_tokens | Typeinteger | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
Fieldstream_options.include_usage | Typeboolean | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtemperature | Typenumber | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtop_p | Typenumber | RequirementOptional | Values & limits Model-specific | Default— |
Fieldstop | Typestring|string[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtools | Typefunction_tool[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtools[].type | Typestring | RequirementOptional | Values & limits function Model-specific | Default— |
Fieldtools[].function.name | Typestring | RequirementRequired | Values & limits Applies when: function tool supplied | Default— |
Fieldtools[].function.description | Typestring | RequirementOptional | Values & limits | Default— |
Fieldtools[].function.parameters | TypeJSON_schema | RequirementOptional | Values & limits | Default— |
Fieldtool_choice | Typestring|object | RequirementOptional | Values & limits Model-specific | Default— |
Fieldparallel_tool_calls | Typeboolean | RequirementOptional | Values & limits Model-specific | Default— |
Fieldresponse_format | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldreasoning_effort | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
Fieldreasoning | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldservice_tier | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
Fieldinstructions | Typestring | RequirementOptional | Values & limits Compatibility field | Default— |
Fieldfunctions | Typefunction[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldfunction_call | Typestring|object | RequirementOptional | Values & limits Model-specific | Default— |
Fieldprompt_cache_options | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldmodalities | Typestring[] | RequirementOptional | Values & limits text | Default— |
Fieldprovider | Typeobject | RequirementOptional | Values & limits Conditions: provider.options is rejected on this Ultra text route | Default— |
Fieldcache_control.ttl | Typestring | RequirementOptional | Values & limits Conditions: 1h is rejected in actual prompt-cache locations | Default— |
Text · UTF8 text
messages[].content
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, messages |
Parametermaterial_types | Contracttext |
Parametermessages | Contractmessage array with role/content shape |
Parameterfile_material | Contractactual UTF-8 document inserted as literal text; no file ID inferred |
Parameteroptional_controls | Contractstream, temperature, top_p, stop, max_tokens, max_completion_tokens, reasoning, response_format, tools, tool_choice |
Parametercontrol_scope | Contractmodel-specific; user function tools differ from hosted tools |
Parameteroutput_modalities | Contracttext |
Parameterhosted_operations | Contractfalse |
Parametermultimodal_input_binding | Contractnull |
Lifecycle: synchronous_or_streamed
Send exact model ID with messages.
Context length is not an output cap.
A text file may supply literal text; image/audio/file-object inputs need exact binding.
Tariff references do not add request options. Supported parameters are listed for the selected method.
Match each charge to the conditions shown. Use one rate for each set of alternative configurations.
| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
|---|---|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0002 / 1K tokens Output · Output tokens $0.0008 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0002 / 1K tokens Output · Output tokens $0.0008 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "qwen/qwen3-coder-30b-a3b-instruct", "messages": [{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}]}')\n\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path("result.json").read_text())\nfor x in r.get("choices",[]):\n if x.get("message",{}).get("content"): print(x["message"]["content"])\nPY_RESULT\nfrom openai import OpenAI\nimport os\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nresult=client.chat.completions.create(model='qwen/qwen3-coder-30b-a3b-instruct',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}])\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(result.to_dict(mode="json"))\nfrom openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nwith client.chat.completions.stream(model='qwen/qwen3-coder-30b-a3b-instruct',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:\n with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:\n for event in stream:\n payload=event.to_dict(mode="json")\n log.write(json.dumps(payload,ensure_ascii=False)+"\\n"); log.flush()\n print(json.dumps(payload,ensure_ascii=False))\n final=stream.get_final_completion()\n save_result(final.to_dict(mode="json"),"stream-result")\njson or SSE
Keep every complete returned response, file and content part.
Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.
Keep request/response IDs and headers. No generic text job retrieval URL is supplied.
| Field | Type |
|---|---|
Fieldchoices[].index | Typeinteger |
Fieldchoices[].message.content | Typestring|null |
Fieldchoices[].message.tool_calls | Typetool_call[] |
Fieldchoices[].message.reasoning_content | Typestring |
Fieldchoices[].message.reasoning_details | Typeobject|array |
Fieldchoices[].finish_reason | Typestring|null |
Fieldusage | Typeobject |
| Response | Condition | Next step |
|---|---|---|
Response400 · invalid_request_error | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |
Ailoot Ultra qwen/qwen3-coder-30b-a3b-instruct
Use the method paths shown above.
qwen/qwen3-coder-30b-a3b-instructQwen3-Coder-30B-A3B-Instruct is Qwen’s non-thinking text coding model with 30.5 billion total and 3.3 billion activated parameters. It targets repository-scale development, coding and browser-agent workflows, with native 262,144-token context and a dedicated function-call format.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Highlights: repository-scale coding
Qwen3-Coder-30B-A3B-Instruct is an instruction-focused text model for coding agents. Qwen documents coding, browser-agent use and repository-scale understanding, with a dedicated function-call format and integration through workflows such as Qwen Code. Its input and output are text. Preserve this exact Coder checkpoint rather than substitute the general Qwen3-30B-A3B-Instruct-2507 or Qwen3-Coder-Next, whose training focus and generation guidance differ.
The native context is 262,144 tokens, with the maker describing extension to approximately one million using YaRN. A large context can place more repository evidence together, but a clear task still needs relevant modules, interfaces and requirements. Provide the expected artifact and observable behavior before asking for a code change.
Model overview
The mixture-of-experts model has 30.5 billion parameters in total and activates 3.3 billion. It has 48 layers, 128 experts and eight experts selected per token. Total parameters and activated parameters have different meanings; the activated figure is not the complete checkpoint size. Its causal-language-model configuration is a text model, not a vision or speech interface.
Coder-30B-A3B-Instruct supports only non-thinking mode and does not generate explicit thinking blocks. Setting enable_thinking=False is unnecessary in the maker’s example. It can still explain an algorithm or justify a patch in ordinary text. A request for reasoning steps should not be confused with enabling the separate Thinking behavior of another Qwen edition.
Preparing a development request
Supply the relevant code, an input demonstrating the current behavior, the observed result and the intended change. For an algorithm, specify input constraints and the required output before asking for an approach. For a repository modification, identify the affected feature and interfaces the implementation must preserve. Request an editable patch or complete function separately from explanatory commentary.
A useful response can organize the diagnosis, proposed change and checks needed to review it. When a task is driven by a visual reference or recorded behavior, provide an appropriate textual representation and retain identifiers that allow the result to be compared with the original. Compare the proposed patch with the supplied code, expected behavior and results returned by connected checks.
Agentic coding and browser workflows
The maker highlights tool calling and a specially designed function-call format. A connected agent workflow supplies tool descriptions, input schemas and observations, and performs the actual operations. Define permitted actions and a condition for completion, then return actual inspection or execution results to the model so it can update its proposed work.
Browser-agent capability means participation in a workflow with a connected browser tool, not automatic access to a user’s browser or current pages. The same distinction applies to repository inspection and code execution. A proposed command, tool request and completed operation should remain separate in the final report. Keep the native model’s tool format and parsing recipe rather than assume another model’s template is interchangeable.
Long context and configuration
The maker describes YaRN extension from the native 262,144-token context to about one million for repository-scale tasks. Use a context configuration appropriate to the repository material, while reserving space for tool observations and the result. Its quickstart also suggests a smaller context, such as 32,768, when memory pressure prevents the larger setting from working.
Keep code paths, function names and relevant definitions in a long input. Remove unrelated generated files or repeated material and reserve space for the answer. Source text, history, tool observations and generated code share the configured sequence allowance; the largest possible input should not be treated as perfect recall of every dependency.
Generation guidance
Best Practices recommend temperature 0.7, top_p 0.8, top_k 20 and repetition penalty 1.05. The exact repetition-penalty recommendation differs from several other Qwen models and remains part of this Coder edition’s recipe. Qwen recommends a 65,536-token generation allowance for most queries, which is a recommendation rather than an independently established hard maximum.
State the output language and form, such as a patch, complete function or explanation, and check the artifact’s syntax and interfaces in the real development workflow. The maker’s function example illustrates the tool mechanism; a tool contract still needs internally consistent argument names and return semantics in the application using it.
Substantive limits and useful result
This checkpoint’s documented input is text. It does not directly establish image, audio or video understanding. Generated code and a confident explanation are draft artifacts until the relevant checks or observations are actually returned by the connected environment. The useful result is an inspectable implementation proposal tied to the supplied repository conditions, with its exact Coder identity, non-thinking mode and producer generation guidance preserved.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qwen/qwen3-coder-30b-a3b-instruct | Default— |
Fieldmessages | Typemessage[] | RequirementRequired | Values & limits | Default— |
Fieldmessages[].role | Typestring | RequirementRequired | Values & limits user, assistant | Default— |
Fieldmessages[].content | Typestring | RequirementRequired | Values & limits | Default— |
Fieldmax_tokens | Typeinteger | RequirementRequired | Values & limits | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
Text · UTF-8 text
messages[].content string
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, messages, max_tokens |
Parameteroptional_controls | Contractstream |
Parametermaterial_types | Contracttext |
Parametertext_file_material | ContractRead the actual UTF-8 document and put its text in the indicated input or message content string. |
Lifecycle: synchronous_or_streamed
Tariff references do not add request options. Supported parameters are listed for the selected method.
Match each charge to the conditions shown. Use one rate for each set of alternative configurations.
| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
|---|---|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0002 / 1K tokens Output · Output tokens $0.0008 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0002 / 1K tokens Output · Output tokens $0.0008 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "qwen/qwen3-coder-30b-a3b-instruct",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 document}"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ['AILOOT_TEXT_FILE'])\nif not source_file.is_file():\n raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')\ntext = source_file.read_text(encoding='utf-8')\nif not text.strip():\n raise SystemExit('Choose a document containing text')\npayload = {'model': 'qwen/qwen3-coder-30b-a3b-instruct', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}\npayload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\\n\\n' + text\nPath('request.json').write_text(json.dumps(payload, ensure_ascii=False), encoding='utf-8')\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path('result.json').read_text(encoding='utf-8'))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\nPY_RESULT\nimport json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ['AILOOT_TEXT_FILE'])\nif not source_file.is_file():\n raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')\ntext = source_file.read_text(encoding='utf-8')\nif not text.strip():\n raise SystemExit('Choose a document containing text')\npayload = {'model': 'qwen/qwen3-coder-30b-a3b-instruct', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}\npayload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\\n\\n' + text\nfrom urllib.request import Request, urlopen\nfrom urllib.error import HTTPError\n\napi_key = os.environ['AILOOT_API_KEY']\nif not api_key.strip():\n raise SystemExit('Set AILOOT_API_KEY before making a request')\nheaders = {'x-api-key': 'PLACEHOLDER_KEY', 'anthropic-version': '2023-06-01', 'Content-Type': 'application/json'}\nheaders['x-api-key'] = api_key\nrequest = Request('https://api.ailoot.ai/v1/messages', data=json.dumps(payload, ensure_ascii=False).encode('utf-8'), headers=headers, method='POST')\ntry:\n with urlopen(request, timeout=120) as response:\n raw = response.read()\n Path('response-headers.txt').write_text(str(response.headers), encoding='utf-8')\nexcept HTTPError as error:\n Path('result.json').write_bytes(error.read())\n Path('response-headers.txt').write_text(str(error.headers), encoding='utf-8')\n raise\nPath('result.json').write_bytes(raw)\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path('result.json').read_text(encoding='utf-8'))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\nJSON or SSE
Keep every complete returned response, file and content part.
Keep all content blocks, thinking signatures and actual tool-use IDs. Assemble all SSE block deltas; a first text block is not the complete output.
Keep request/response IDs and headers. No generic text job retrieval URL is supplied.
| Field | Type |
|---|---|
Fieldid | Typestring |
Fieldmodel | Typestring |
Fieldcontent[] | Typetext|thinking|tool_use|other content block |
Fieldstop_reason | Typestring|null |
Fieldusage | Typeobject |
| Response | Condition | Next step |
|---|---|---|
Response400 · invalid_request_error | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |
Ailoot Ultra qwen/qwen3-coder-30b-a3b-instruct
Use the method paths shown above.
Technical example in English
Implement interval overlap correctly\n\nImplement overlaps(a, b) for two half-open intervals [start, end), using numeric endpoints. Intervals touching at an endpoint do not overlap. Reject intervals with start greater than end; empty intervals never overlap. Return a complete Python function and tests for genuine overlap, touching, empty and reversed intervals. Keep the interface limited to two pairs.A complete Python function and four focused tests expressing the interval contract.Check that [1, 3) and [3, 5) return false and an empty interval cannot overlap a containing interval.