Highlights: a model built for coding agents
Qwen3-Coder-Next is an open text model designed specifically for coding agents and development workflows. Qwen describes long-horizon problem solving, complex tool use and recovery from execution failures, together with adaptability to different development scaffolds. It accepts text and produces text, including code, explanations and tool requests. This exact Coder-Next checkpoint has its own non-thinking contract; the broader Next family’s Thinking editions should not be substituted for it.
For a development task, provide the relevant files or excerpts, the intended behavior and the input that demonstrates a problem. Ask for an editable change and an explanation tied to those conditions. For a task spanning several steps, define the goal, permitted tools and observations that would show completion. Review the proposed code change and its explanation against the supplied files, failing input and completion criteria.
Model overview
The model has 80 billion parameters in total and activates three billion. Its 48-layer hybrid layout repeats three Gated DeltaNet expert layers followed by one gated-attention expert layer. The maker lists 512 experts, ten activated experts and one shared expert. The small activated count is a computation characteristic of the sparse model, not the size of the complete checkpoint.
The native context is 262,144 tokens. The maker’s examples allow a smaller context, such as 32,768, when memory constraints prevent the larger configuration from working. Source code, history, tool observations and generated text must fit the configured sequence allowance. The card does not establish a default million-token extension for this checkpoint.
Using the non-thinking text interface
Coder-Next 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 a patch, discuss an algorithm or reason through ordinary text; non-thinking describes its output mode rather than forbidding an explanation.
The quickstart asks for a sorting algorithm and uses a 65,536-token generation allowance. That value is an example budget, not a separately published hard output ceiling. State the artifact’s format and constraints: the language, relevant interfaces, required behavior and whether the answer should contain a patch, complete function or explanation. Keep the editable result separate from commentary so it can be reviewed easily.
Development scaffolds and context
The maker emphasizes compatibility with CLI and IDE-style agent scaffolds, including Qwen Code. A scaffold supplies the project state, tool definitions, observations and conversation format. Preserve those inputs consistently during a multi-step task. When a tool reports a failing check, provide the actual error and relevant changed code rather than merely tell the model to try again.
Long-horizon work benefits from a visible state of the task: what was observed, what change is proposed and what condition remains unresolved. A tool observation is different from a claim in generated text. The model’s failure-recovery capability should not be treated as automatic permission to run commands or as a guarantee that every recovery will succeed.
Agentic coding and tool calls
Qwen documents function-style tool definitions with names, descriptions, input schemas and required fields. Provide a precise definition and the expected meaning of the return value. The application executes a selected tool and returns its result; the model then uses that result in the next step. Tool calling itself does not grant access to a filesystem, live sources or an execution environment.
For an agent editing a repository, constrain the permitted files and requested deliverable. A useful final report can identify affected modules, explain the change and list real results returned by the connected checks. Keep proposed commands, generated code and completed operations distinct. These are practical workflow examples grounded in the documented development and tool scope.
Generation recommendations
The maker recommends temperature 1.0, top_p 0.95 and top_k 40. These exact settings differ from several conversational Qwen models and should remain part of Coder-Next’s own recipe. The published configuration uses a Qwen3-Next causal-language-model architecture. Use this checkpoint’s documented model name and chat template consistently through the coding workflow.
Substantive limits
The documented input is text, so screenshots, audio or video require an appropriate separate representation before this coding workflow. Native context and example generation allowances are finite; trim unrelated code and reserve space for the requested artifact. Check generated syntax, interfaces, edge cases and proposed changes in the real development workflow. The useful output is an inspectable code or explanation artifact supported by actual task evidence, with this checkpoint’s text-only and non-thinking identity preserved.
", "aboutText": "Highlights: a model built for coding agents\n\nQwen3-Coder-Next is an open text model designed specifically for coding agents and development workflows. Qwen describes long-horizon problem solving, complex tool use and recovery from execution failures, together with adaptability to different development scaffolds. It accepts text and produces text, including code, explanations and tool requests. This exact Coder-Next checkpoint has its own non-thinking contract; the broader Next family’s Thinking editions should not be substituted for it.\n\nFor a development task, provide the relevant files or excerpts, the intended behavior and the input that demonstrates a problem. Ask for an editable change and an explanation tied to those conditions. For a task spanning several steps, define the goal, permitted tools and observations that would show completion. Review the proposed code change and its explanation against the supplied files, failing input and completion criteria.\n\nModel overview\n\nThe model has 80 billion parameters in total and activates three billion. Its 48-layer hybrid layout repeats three Gated DeltaNet expert layers followed by one gated-attention expert layer. The maker lists 512 experts, ten activated experts and one shared expert. The small activated count is a computation characteristic of the sparse model, not the size of the complete checkpoint.\n\nThe native context is 262,144 tokens. The maker’s examples allow a smaller context, such as 32,768, when memory constraints prevent the larger configuration from working. Source code, history, tool observations and generated text must fit the configured sequence allowance. The card does not establish a default million-token extension for this checkpoint.\n\nUsing the non-thinking text interface\n\nCoder-Next 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 a patch, discuss an algorithm or reason through ordinary text; non-thinking describes its output mode rather than forbidding an explanation.\n\nThe quickstart asks for a sorting algorithm and uses a 65,536-token generation allowance. That value is an example budget, not a separately published hard output ceiling. State the artifact’s format and constraints: the language, relevant interfaces, required behavior and whether the answer should contain a patch, complete function or explanation. Keep the editable result separate from commentary so it can be reviewed easily.\n\nDevelopment scaffolds and context\n\nThe maker emphasizes compatibility with CLI and IDE-style agent scaffolds, including Qwen Code. A scaffold supplies the project state, tool definitions, observations and conversation format. Preserve those inputs consistently during a multi-step task. When a tool reports a failing check, provide the actual error and relevant changed code rather than merely tell the model to try again.\n\nLong-horizon work benefits from a visible state of the task: what was observed, what change is proposed and what condition remains unresolved. A tool observation is different from a claim in generated text. The model’s failure-recovery capability should not be treated as automatic permission to run commands or as a guarantee that every recovery will succeed.\n\nAgentic coding and tool calls\n\nQwen documents function-style tool definitions with names, descriptions, input schemas and required fields. Provide a precise definition and the expected meaning of the return value. The application executes a selected tool and returns its result; the model then uses that result in the next step. Tool calling itself does not grant access to a filesystem, live sources or an execution environment.\n\nFor an agent editing a repository, constrain the permitted files and requested deliverable. A useful final report can identify affected modules, explain the change and list real results returned by the connected checks. Keep proposed commands, generated code and completed operations distinct. These are practical workflow examples grounded in the documented development and tool scope.\n\nGeneration recommendations\n\nThe maker recommends temperature 1.0, top_p 0.95 and top_k 40. These exact settings differ from several conversational Qwen models and should remain part of Coder-Next’s own recipe. The published configuration uses a Qwen3-Next causal-language-model architecture. Use this checkpoint’s documented model name and chat template consistently through the coding workflow.\n\nSubstantive limits\n\nThe documented input is text, so screenshots, audio or video require an appropriate separate representation before this coding workflow. Native context and example generation allowances are finite; trim unrelated code and reserve space for the requested artifact. Check generated syntax, interfaces, edge cases and proposed changes in the real development workflow. The useful output is an inspectable code or explanation artifact supported by actual task evidence, with this checkpoint’s text-only and non-thinking identity preserved.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Implement a stable partition helper\n\nWrite a Python function partition_even(values) returning two new lists: even integers first and odd integers second. Preserve order within each list and do not mutate values. Provide tests for negative integers, repeated values and empty input. Return the complete function separately from the explanation, with no claim that tests have been executed.A complete function, tests for the named cases and a brief order-preservation explanation.Check that each input occurrence appears exactly once in the appropriate result list and that source order is retained.qwen/qwen3-coder-nextQwen3-Coder-Next is Qwen’s text-only coding-agent model with 80 billion total and 3 billion activated parameters. It uses non-thinking output, native 262,144-token context and tool calling for development workflows, including multi-step work and recovery from execution feedback.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Highlights: a model built for coding agents
Qwen3-Coder-Next is an open text model designed specifically for coding agents and development workflows. Qwen describes long-horizon problem solving, complex tool use and recovery from execution failures, together with adaptability to different development scaffolds. It accepts text and produces text, including code, explanations and tool requests. This exact Coder-Next checkpoint has its own non-thinking contract; the broader Next family’s Thinking editions should not be substituted for it.
For a development task, provide the relevant files or excerpts, the intended behavior and the input that demonstrates a problem. Ask for an editable change and an explanation tied to those conditions. For a task spanning several steps, define the goal, permitted tools and observations that would show completion. Review the proposed code change and its explanation against the supplied files, failing input and completion criteria.
Model overview
The model has 80 billion parameters in total and activates three billion. Its 48-layer hybrid layout repeats three Gated DeltaNet expert layers followed by one gated-attention expert layer. The maker lists 512 experts, ten activated experts and one shared expert. The small activated count is a computation characteristic of the sparse model, not the size of the complete checkpoint.
The native context is 262,144 tokens. The maker’s examples allow a smaller context, such as 32,768, when memory constraints prevent the larger configuration from working. Source code, history, tool observations and generated text must fit the configured sequence allowance. The card does not establish a default million-token extension for this checkpoint.
Using the non-thinking text interface
Coder-Next 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 a patch, discuss an algorithm or reason through ordinary text; non-thinking describes its output mode rather than forbidding an explanation.
The quickstart asks for a sorting algorithm and uses a 65,536-token generation allowance. That value is an example budget, not a separately published hard output ceiling. State the artifact’s format and constraints: the language, relevant interfaces, required behavior and whether the answer should contain a patch, complete function or explanation. Keep the editable result separate from commentary so it can be reviewed easily.
Development scaffolds and context
The maker emphasizes compatibility with CLI and IDE-style agent scaffolds, including Qwen Code. A scaffold supplies the project state, tool definitions, observations and conversation format. Preserve those inputs consistently during a multi-step task. When a tool reports a failing check, provide the actual error and relevant changed code rather than merely tell the model to try again.
Long-horizon work benefits from a visible state of the task: what was observed, what change is proposed and what condition remains unresolved. A tool observation is different from a claim in generated text. The model’s failure-recovery capability should not be treated as automatic permission to run commands or as a guarantee that every recovery will succeed.
Agentic coding and tool calls
Qwen documents function-style tool definitions with names, descriptions, input schemas and required fields. Provide a precise definition and the expected meaning of the return value. The application executes a selected tool and returns its result; the model then uses that result in the next step. Tool calling itself does not grant access to a filesystem, live sources or an execution environment.
For an agent editing a repository, constrain the permitted files and requested deliverable. A useful final report can identify affected modules, explain the change and list real results returned by the connected checks. Keep proposed commands, generated code and completed operations distinct. These are practical workflow examples grounded in the documented development and tool scope.
Generation recommendations
The maker recommends temperature 1.0, top_p 0.95 and top_k 40. These exact settings differ from several conversational Qwen models and should remain part of Coder-Next’s own recipe. The published configuration uses a Qwen3-Next causal-language-model architecture. Use this checkpoint’s documented model name and chat template consistently through the coding workflow.
Substantive limits
The documented input is text, so screenshots, audio or video require an appropriate separate representation before this coding workflow. Native context and example generation allowances are finite; trim unrelated code and reserve space for the requested artifact. Check generated syntax, interfaces, edge cases and proposed changes in the real development workflow. The useful output is an inspectable code or explanation artifact supported by actual task evidence, with this checkpoint’s text-only and non-thinking identity preserved.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qwen/qwen3-coder-next | 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 $0.00024 / 1K tokens Output · Output tokens $0.0016 / 1K tokens Input · Cache read $0.00014 / 1K tokens Input · Cache write — / 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 $0.00024 / 1K tokens Output · Output tokens $0.0016 / 1K tokens Input · Cache read $0.00014 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${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-next", "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-next',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-next',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-next
Use the method paths shown above.
qwen/qwen3-coder-nextQwen3-Coder-Next is Qwen’s text-only coding-agent model with 80 billion total and 3 billion activated parameters. It uses non-thinking output, native 262,144-token context and tool calling for development workflows, including multi-step work and recovery from execution feedback.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Highlights: a model built for coding agents
Qwen3-Coder-Next is an open text model designed specifically for coding agents and development workflows. Qwen describes long-horizon problem solving, complex tool use and recovery from execution failures, together with adaptability to different development scaffolds. It accepts text and produces text, including code, explanations and tool requests. This exact Coder-Next checkpoint has its own non-thinking contract; the broader Next family’s Thinking editions should not be substituted for it.
For a development task, provide the relevant files or excerpts, the intended behavior and the input that demonstrates a problem. Ask for an editable change and an explanation tied to those conditions. For a task spanning several steps, define the goal, permitted tools and observations that would show completion. Review the proposed code change and its explanation against the supplied files, failing input and completion criteria.
Model overview
The model has 80 billion parameters in total and activates three billion. Its 48-layer hybrid layout repeats three Gated DeltaNet expert layers followed by one gated-attention expert layer. The maker lists 512 experts, ten activated experts and one shared expert. The small activated count is a computation characteristic of the sparse model, not the size of the complete checkpoint.
The native context is 262,144 tokens. The maker’s examples allow a smaller context, such as 32,768, when memory constraints prevent the larger configuration from working. Source code, history, tool observations and generated text must fit the configured sequence allowance. The card does not establish a default million-token extension for this checkpoint.
Using the non-thinking text interface
Coder-Next 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 a patch, discuss an algorithm or reason through ordinary text; non-thinking describes its output mode rather than forbidding an explanation.
The quickstart asks for a sorting algorithm and uses a 65,536-token generation allowance. That value is an example budget, not a separately published hard output ceiling. State the artifact’s format and constraints: the language, relevant interfaces, required behavior and whether the answer should contain a patch, complete function or explanation. Keep the editable result separate from commentary so it can be reviewed easily.
Development scaffolds and context
The maker emphasizes compatibility with CLI and IDE-style agent scaffolds, including Qwen Code. A scaffold supplies the project state, tool definitions, observations and conversation format. Preserve those inputs consistently during a multi-step task. When a tool reports a failing check, provide the actual error and relevant changed code rather than merely tell the model to try again.
Long-horizon work benefits from a visible state of the task: what was observed, what change is proposed and what condition remains unresolved. A tool observation is different from a claim in generated text. The model’s failure-recovery capability should not be treated as automatic permission to run commands or as a guarantee that every recovery will succeed.
Agentic coding and tool calls
Qwen documents function-style tool definitions with names, descriptions, input schemas and required fields. Provide a precise definition and the expected meaning of the return value. The application executes a selected tool and returns its result; the model then uses that result in the next step. Tool calling itself does not grant access to a filesystem, live sources or an execution environment.
For an agent editing a repository, constrain the permitted files and requested deliverable. A useful final report can identify affected modules, explain the change and list real results returned by the connected checks. Keep proposed commands, generated code and completed operations distinct. These are practical workflow examples grounded in the documented development and tool scope.
Generation recommendations
The maker recommends temperature 1.0, top_p 0.95 and top_k 40. These exact settings differ from several conversational Qwen models and should remain part of Coder-Next’s own recipe. The published configuration uses a Qwen3-Next causal-language-model architecture. Use this checkpoint’s documented model name and chat template consistently through the coding workflow.
Substantive limits
The documented input is text, so screenshots, audio or video require an appropriate separate representation before this coding workflow. Native context and example generation allowances are finite; trim unrelated code and reserve space for the requested artifact. Check generated syntax, interfaces, edge cases and proposed changes in the real development workflow. The useful output is an inspectable code or explanation artifact supported by actual task evidence, with this checkpoint’s text-only and non-thinking identity preserved.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qwen/qwen3-coder-next | 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 $0.00024 / 1K tokens Output · Output tokens $0.0016 / 1K tokens Input · Cache read $0.00014 / 1K tokens Input · Cache write — / 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 $0.00024 / 1K tokens Output · Output tokens $0.0016 / 1K tokens Input · Cache read $0.00014 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "qwen/qwen3-coder-next",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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-next', '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-next', '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-next
Use the method paths shown above.
Technical example in English
Implement a stable partition helper\n\nWrite a Python function partition_even(values) returning two new lists: even integers first and odd integers second. Preserve order within each list and do not mutate values. Provide tests for negative integers, repeated values and empty input. Return the complete function separately from the explanation, with no claim that tests have been executed.A complete function, tests for the named cases and a brief order-preservation explanation.Check that each input occurrence appears exactly once in the appropriate result list and that source order is retained.