GLM-4.7-Flash is the 30B-A3B mixture-of-experts edition of Z.ai’s GLM-4.7 family. Its sparse design has approximately 30 billion total parameters and three billion activated, and the maker presents it as a lightweight model balancing capability and efficiency. It accepts text and generates text. The producer specifically highlights software development, Chinese writing, translation, long-form text processing and role-based conversation. A useful brief can request a code proposal, a revised passage, an explanation or a structured result grounded in supplied material.
For development, Z.ai identifies both front-end and application-logic tasks for this Flash edition. Supply the behaviour to implement, the relevant source and the conditions that must remain intact. For a page or component, describe its states, layout and required interaction, then ask for editable code and an explanation of the important choices. For an existing function, include the observed failure and an example of the expected result. The model produces the proposed code; compiling it, running it or rendering the interface belongs to a connected application environment.
The producer-hosted GLM-4.7 series profile lists text input, text output, a 200K-token context and up to 128K output tokens for Flash. The open-model card and the hosted profile describe different aspects of the same named edition: checkpoint characteristics and a producer service configuration. Prepare long input with source headings, code identifiers and clear document boundaries, leaving room for reasoning and the requested answer. A text-only model can write code for an application that processes images or camera input, but that does not give this checkpoint a native visual-input mode.
Reasoning is enabled by default in the GLM-4.7 series. The producer documents a per-turn switch so a conversation can request reasoning for a difficult question and disable it for a straightforward rewrite or short answer. It also supports interleaved thinking between tool calls, allowing the model to interpret a returned observation before planning another step. Define the available tools and the required final artifact before starting such a task. A document assistant can ask for selected information, receive the actual retrieval result and then prepare an explanation supported by that result.
Preserved thinking is a distinct option for sustained coding or agent work. The maker’s guide uses clear_thinking=false and requires the complete, unmodified reasoning_content from earlier assistant turns to be returned in its original order. Changing or rearranging those blocks can degrade the result and affect cache behaviour. The default differs between the producer’s coding and standard interfaces, so the option is a configured workflow rather than an automatic property of every conversation. Keep the visible answer separate from retained reasoning, and preserve the evidence or tool output on which later steps depend.
The family’s documented interface includes streaming text, function calling, context caching and structured output such as JSON. For a structured result, provide the required fields and what each value represents; for a tool request, define the function’s purpose, arguments and completion condition. A generated call is a request for the application to act, rather than proof of execution. The final result can be a short report, a data object or a code artifact, with the information used to produce it still identifiable.
For writing or translation, specify the reader, language, tone and terms that should remain unchanged. The maker recommends trying Flash in Chinese writing and in narrative or role-based dialogue as well as technical work. An illustrative editing brief can provide a passage and ask for a concise revision that preserves its facts; a translation brief can supply a glossary and distinguish quoted text from instructions. In a longer conversation, retain the constraints and identify the next result needed, so the model’s response remains connected to the original task.
The exact open-model card publishes different generation settings for its evaluation tasks: a default temperature of 1.0 and top-p of 0.95, with separate software-task settings of 0.7 and 1.0. Its example generation lengths are part of those procedures, not additional universal limits. The checkpoint is distinct from GLM-4.7, GLM-4.7-FlashX and later GLM-5 models. Match the task and response mode to this edition’s documented text capabilities, then assess the delivered code, extracted values or revised prose against the input.
", "aboutText": "GLM-4.7-Flash is the 30B-A3B mixture-of-experts edition of Z.ai’s GLM-4.7 family. Its sparse design has approximately 30 billion total parameters and three billion activated, and the maker presents it as a lightweight model balancing capability and efficiency. It accepts text and generates text. The producer specifically highlights software development, Chinese writing, translation, long-form text processing and role-based conversation. A useful brief can request a code proposal, a revised passage, an explanation or a structured result grounded in supplied material.\n\nFor development, Z.ai identifies both front-end and application-logic tasks for this Flash edition. Supply the behaviour to implement, the relevant source and the conditions that must remain intact. For a page or component, describe its states, layout and required interaction, then ask for editable code and an explanation of the important choices. For an existing function, include the observed failure and an example of the expected result. The model produces the proposed code; compiling it, running it or rendering the interface belongs to a connected application environment.\n\nThe producer-hosted GLM-4.7 series profile lists text input, text output, a 200K-token context and up to 128K output tokens for Flash. The open-model card and the hosted profile describe different aspects of the same named edition: checkpoint characteristics and a producer service configuration. Prepare long input with source headings, code identifiers and clear document boundaries, leaving room for reasoning and the requested answer. A text-only model can write code for an application that processes images or camera input, but that does not give this checkpoint a native visual-input mode.\n\nReasoning is enabled by default in the GLM-4.7 series. The producer documents a per-turn switch so a conversation can request reasoning for a difficult question and disable it for a straightforward rewrite or short answer. It also supports interleaved thinking between tool calls, allowing the model to interpret a returned observation before planning another step. Define the available tools and the required final artifact before starting such a task. A document assistant can ask for selected information, receive the actual retrieval result and then prepare an explanation supported by that result.\n\nPreserved thinking is a distinct option for sustained coding or agent work. The maker’s guide uses clear_thinking=false and requires the complete, unmodified reasoning_content from earlier assistant turns to be returned in its original order. Changing or rearranging those blocks can degrade the result and affect cache behaviour. The default differs between the producer’s coding and standard interfaces, so the option is a configured workflow rather than an automatic property of every conversation. Keep the visible answer separate from retained reasoning, and preserve the evidence or tool output on which later steps depend.\n\nThe family’s documented interface includes streaming text, function calling, context caching and structured output such as JSON. For a structured result, provide the required fields and what each value represents; for a tool request, define the function’s purpose, arguments and completion condition. A generated call is a request for the application to act, rather than proof of execution. The final result can be a short report, a data object or a code artifact, with the information used to produce it still identifiable.\n\nFor writing or translation, specify the reader, language, tone and terms that should remain unchanged. The maker recommends trying Flash in Chinese writing and in narrative or role-based dialogue as well as technical work. An illustrative editing brief can provide a passage and ask for a concise revision that preserves its facts; a translation brief can supply a glossary and distinguish quoted text from instructions. In a longer conversation, retain the constraints and identify the next result needed, so the model’s response remains connected to the original task.\n\nThe exact open-model card publishes different generation settings for its evaluation tasks: a default temperature of 1.0 and top-p of 0.95, with separate software-task settings of 0.7 and 1.0. Its example generation lengths are part of those procedures, not additional universal limits. The checkpoint is distinct from GLM-4.7, GLM-4.7-FlashX and later GLM-5 models. Match the task and response mode to this edition’s documented text capabilities, then assess the delivered code, extracted values or revised prose against the input.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Translate a notice with a fixed glossary\n\nTranslate this Chinese notice into English: '订单已审核，但尚未发货。更改收货地址需要重新审核。' Use this glossary consistently: 审核 = review; 发货 = dispatch; 收货地址 = delivery address. Write a clear customer-facing notice and preserve the distinction between completed review and pending dispatch. Do not add a dispatch date or an approval guarantee.A concise English notice applying the glossary and preserving the two different order states.The translation retains the requirement for another review after an address change and does not state that dispatch occurred.z-ai/glm-4.7-flashGLM-4.7-Flash is Z.ai’s 30B-A3B mixture-of-experts text model for coding, long-form text, Chinese writing and translation. It supports reasoning and tool-directed workflows, with a producer-hosted profile of 200K context tokens and up to 128K output.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
GLM-4.7-Flash is the 30B-A3B mixture-of-experts edition of Z.ai’s GLM-4.7 family. Its sparse design has approximately 30 billion total parameters and three billion activated, and the maker presents it as a lightweight model balancing capability and efficiency. It accepts text and generates text. The producer specifically highlights software development, Chinese writing, translation, long-form text processing and role-based conversation. A useful brief can request a code proposal, a revised passage, an explanation or a structured result grounded in supplied material.
For development, Z.ai identifies both front-end and application-logic tasks for this Flash edition. Supply the behaviour to implement, the relevant source and the conditions that must remain intact. For a page or component, describe its states, layout and required interaction, then ask for editable code and an explanation of the important choices. For an existing function, include the observed failure and an example of the expected result. The model produces the proposed code; compiling it, running it or rendering the interface belongs to a connected application environment.
The producer-hosted GLM-4.7 series profile lists text input, text output, a 200K-token context and up to 128K output tokens for Flash. The open-model card and the hosted profile describe different aspects of the same named edition: checkpoint characteristics and a producer service configuration. Prepare long input with source headings, code identifiers and clear document boundaries, leaving room for reasoning and the requested answer. A text-only model can write code for an application that processes images or camera input, but that does not give this checkpoint a native visual-input mode.
Reasoning is enabled by default in the GLM-4.7 series. The producer documents a per-turn switch so a conversation can request reasoning for a difficult question and disable it for a straightforward rewrite or short answer. It also supports interleaved thinking between tool calls, allowing the model to interpret a returned observation before planning another step. Define the available tools and the required final artifact before starting such a task. A document assistant can ask for selected information, receive the actual retrieval result and then prepare an explanation supported by that result.
Preserved thinking is a distinct option for sustained coding or agent work. The maker’s guide uses clear_thinking=false and requires the complete, unmodified reasoning_content from earlier assistant turns to be returned in its original order. Changing or rearranging those blocks can degrade the result and affect cache behaviour. The default differs between the producer’s coding and standard interfaces, so the option is a configured workflow rather than an automatic property of every conversation. Keep the visible answer separate from retained reasoning, and preserve the evidence or tool output on which later steps depend.
The family’s documented interface includes streaming text, function calling, context caching and structured output such as JSON. For a structured result, provide the required fields and what each value represents; for a tool request, define the function’s purpose, arguments and completion condition. A generated call is a request for the application to act, rather than proof of execution. The final result can be a short report, a data object or a code artifact, with the information used to produce it still identifiable.
For writing or translation, specify the reader, language, tone and terms that should remain unchanged. The maker recommends trying Flash in Chinese writing and in narrative or role-based dialogue as well as technical work. An illustrative editing brief can provide a passage and ask for a concise revision that preserves its facts; a translation brief can supply a glossary and distinguish quoted text from instructions. In a longer conversation, retain the constraints and identify the next result needed, so the model’s response remains connected to the original task.
The exact open-model card publishes different generation settings for its evaluation tasks: a default temperature of 1.0 and top-p of 0.95, with separate software-task settings of 0.7 and 1.0. Its example generation lengths are part of those procedures, not additional universal limits. The checkpoint is distinct from GLM-4.7, GLM-4.7-FlashX and later GLM-5 models. Match the task and response mode to this edition’s documented text capabilities, then assess the delivered code, extracted values or revised prose against the input.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits z-ai/glm-4.7-flash | Default— |
Fieldmessages | Typemessage[] | RequirementRequired | Values & limits Minimum items: 1 | Default— |
Fieldmessages[].role | Typestring | RequirementRequired | Values & limits Examples: system, user, assistant, tool, function Conditions: These roles are explicitly represented by Source compatibility types; the exact model role set remains model-specific. Model-specific | Default— |
Fieldmessages[].content | Typestring|content_part[]|null | RequirementOptional | Values & limits | Default— |
Fieldmessages[].tool_calls | Typetool_call[] | RequirementOptional | Values & limits | Default— |
Fieldmessages[].tool_call_id | Typestring | RequirementOptional | Values & limits Applies when: role=tool; use actual returned ID | Default— |
Fieldmessages[].name | Typestring | RequirementOptional | Values & limits | Default— |
Fieldmessages[].reasoning_content | Typestring | RequirementOptional | Values & limits Applies when: Round-trip actual returned reasoning where this model uses it | Default— |
Fieldmessages[].reasoning_details | Typeobject|array | RequirementOptional | Values & limits Model-specific | Default— |
Fieldmax_tokens | Typeinteger | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
Fieldmax_completion_tokens | Typeinteger | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
Fieldstream_options.include_usage | Typeboolean | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtemperature | Typenumber | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtop_p | Typenumber | RequirementOptional | Values & limits Model-specific | Default— |
Fieldstop | Typestring|string[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtools | Typefunction_tool[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtools[].type | Typestring | RequirementOptional | Values & limits function Model-specific | Default— |
Fieldtools[].function.name | Typestring | RequirementRequired | Values & limits Applies when: function tool supplied | Default— |
Fieldtools[].function.description | Typestring | RequirementOptional | Values & limits | Default— |
Fieldtools[].function.parameters | TypeJSON_schema | RequirementOptional | Values & limits | Default— |
Fieldtool_choice | Typestring|object | RequirementOptional | Values & limits Model-specific | Default— |
Fieldparallel_tool_calls | Typeboolean | RequirementOptional | Values & limits Model-specific | Default— |
Fieldresponse_format | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldreasoning_effort | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
Fieldreasoning | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldservice_tier | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
Fieldinstructions | Typestring | RequirementOptional | Values & limits Compatibility field | Default— |
Fieldfunctions | Typefunction[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldfunction_call | Typestring|object | RequirementOptional | Values & limits Model-specific | Default— |
Fieldprompt_cache_options | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldmodalities | Typestring[] | RequirementOptional | Values & limits text | Default— |
Fieldprovider | Typeobject | RequirementOptional | Values & limits Conditions: provider.options is rejected on this Ultra text route | Default— |
Fieldcache_control.ttl | Typestring | RequirementOptional | Values & limits Conditions: 1h is rejected in actual prompt-cache locations | Default— |
Text · UTF8 text
messages[].content
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, messages |
Parametermaterial_types | Contracttext |
Parametermessages | Contractmessage array with role/content shape |
Parameterfile_material | Contractactual UTF-8 document inserted as literal text; no file ID inferred |
Parameteroptional_controls | Contractstream, temperature, top_p, stop, max_tokens, max_completion_tokens, reasoning, response_format, tools, tool_choice |
Parametercontrol_scope | Contractmodel-specific; user function tools differ from hosted tools |
Parameteroutput_modalities | Contracttext |
Parameterhosted_operations | Contractfalse |
Parametermultimodal_input_binding | Contractnull |
Lifecycle: synchronous_or_streamed
Send exact model ID with messages.
Context length is not an output cap.
A text file may supply literal text; image/audio/file-object inputs need exact binding.
Tariff references do not add request options. Supported parameters are listed for the selected method.
Match each charge to the conditions shown. Use one rate for each set of alternative configurations.
| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
|---|---|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.000144 / 1K tokens Output · Output tokens $0.000858 / 1K tokens Input · Cache read $0.00002 / 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 $0.000144 / 1K tokens Output · Output tokens $0.000858 / 1K tokens Input · Cache read $0.00002 / 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": "z-ai/glm-4.7-flash", "messages": [{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}]}')\n\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path("result.json").read_text())\nfor x in r.get("choices",[]):\n if x.get("message",{}).get("content"): print(x["message"]["content"])\nPY_RESULT\nfrom openai import OpenAI\nimport os\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nresult=client.chat.completions.create(model='z-ai/glm-4.7-flash',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}])\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(result.to_dict(mode="json"))\nfrom openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nwith client.chat.completions.stream(model='z-ai/glm-4.7-flash',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:\n with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:\n for event in stream:\n payload=event.to_dict(mode="json")\n log.write(json.dumps(payload,ensure_ascii=False)+"\\n"); log.flush()\n print(json.dumps(payload,ensure_ascii=False))\n final=stream.get_final_completion()\n save_result(final.to_dict(mode="json"),"stream-result")\njson or SSE
Keep every complete returned response, file and content part.
Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.
Keep request/response IDs and headers. No generic text job retrieval URL is supplied.
| Field | Type |
|---|---|
Fieldchoices[].index | Typeinteger |
Fieldchoices[].message.content | Typestring|null |
Fieldchoices[].message.tool_calls | Typetool_call[] |
Fieldchoices[].message.reasoning_content | Typestring |
Fieldchoices[].message.reasoning_details | Typeobject|array |
Fieldchoices[].finish_reason | Typestring|null |
Fieldusage | Typeobject |
| Response | Condition | Next step |
|---|---|---|
Response400 · invalid_request_error | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |
Ailoot Ultra z-ai/glm-4.7-flash
Use the method paths shown above.
z-ai/glm-4.7-flashGLM-4.7-Flash is Z.ai’s 30B-A3B mixture-of-experts text model for coding, long-form text, Chinese writing and translation. It supports reasoning and tool-directed workflows, with a producer-hosted profile of 200K context tokens and up to 128K output.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
GLM-4.7-Flash is the 30B-A3B mixture-of-experts edition of Z.ai’s GLM-4.7 family. Its sparse design has approximately 30 billion total parameters and three billion activated, and the maker presents it as a lightweight model balancing capability and efficiency. It accepts text and generates text. The producer specifically highlights software development, Chinese writing, translation, long-form text processing and role-based conversation. A useful brief can request a code proposal, a revised passage, an explanation or a structured result grounded in supplied material.
For development, Z.ai identifies both front-end and application-logic tasks for this Flash edition. Supply the behaviour to implement, the relevant source and the conditions that must remain intact. For a page or component, describe its states, layout and required interaction, then ask for editable code and an explanation of the important choices. For an existing function, include the observed failure and an example of the expected result. The model produces the proposed code; compiling it, running it or rendering the interface belongs to a connected application environment.
The producer-hosted GLM-4.7 series profile lists text input, text output, a 200K-token context and up to 128K output tokens for Flash. The open-model card and the hosted profile describe different aspects of the same named edition: checkpoint characteristics and a producer service configuration. Prepare long input with source headings, code identifiers and clear document boundaries, leaving room for reasoning and the requested answer. A text-only model can write code for an application that processes images or camera input, but that does not give this checkpoint a native visual-input mode.
Reasoning is enabled by default in the GLM-4.7 series. The producer documents a per-turn switch so a conversation can request reasoning for a difficult question and disable it for a straightforward rewrite or short answer. It also supports interleaved thinking between tool calls, allowing the model to interpret a returned observation before planning another step. Define the available tools and the required final artifact before starting such a task. A document assistant can ask for selected information, receive the actual retrieval result and then prepare an explanation supported by that result.
Preserved thinking is a distinct option for sustained coding or agent work. The maker’s guide uses clear_thinking=false and requires the complete, unmodified reasoning_content from earlier assistant turns to be returned in its original order. Changing or rearranging those blocks can degrade the result and affect cache behaviour. The default differs between the producer’s coding and standard interfaces, so the option is a configured workflow rather than an automatic property of every conversation. Keep the visible answer separate from retained reasoning, and preserve the evidence or tool output on which later steps depend.
The family’s documented interface includes streaming text, function calling, context caching and structured output such as JSON. For a structured result, provide the required fields and what each value represents; for a tool request, define the function’s purpose, arguments and completion condition. A generated call is a request for the application to act, rather than proof of execution. The final result can be a short report, a data object or a code artifact, with the information used to produce it still identifiable.
For writing or translation, specify the reader, language, tone and terms that should remain unchanged. The maker recommends trying Flash in Chinese writing and in narrative or role-based dialogue as well as technical work. An illustrative editing brief can provide a passage and ask for a concise revision that preserves its facts; a translation brief can supply a glossary and distinguish quoted text from instructions. In a longer conversation, retain the constraints and identify the next result needed, so the model’s response remains connected to the original task.
The exact open-model card publishes different generation settings for its evaluation tasks: a default temperature of 1.0 and top-p of 0.95, with separate software-task settings of 0.7 and 1.0. Its example generation lengths are part of those procedures, not additional universal limits. The checkpoint is distinct from GLM-4.7, GLM-4.7-FlashX and later GLM-5 models. Match the task and response mode to this edition’s documented text capabilities, then assess the delivered code, extracted values or revised prose against the input.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits z-ai/glm-4.7-flash | Default— |
Fieldmessages | Typemessage[] | RequirementRequired | Values & limits | Default— |
Fieldmessages[].role | Typestring | RequirementRequired | Values & limits user, assistant | Default— |
Fieldmessages[].content | Typestring | RequirementRequired | Values & limits | Default— |
Fieldmax_tokens | Typeinteger | RequirementRequired | Values & limits | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
Text · UTF-8 text
messages[].content string
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, messages, max_tokens |
Parameteroptional_controls | Contractstream |
Parametermaterial_types | Contracttext |
Parametertext_file_material | ContractRead the actual UTF-8 document and put its text in the indicated input or message content string. |
Lifecycle: synchronous_or_streamed
Tariff references do not add request options. Supported parameters are listed for the selected method.
Match each charge to the conditions shown. Use one rate for each set of alternative configurations.
| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
|---|---|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.000144 / 1K tokens Output · Output tokens $0.000858 / 1K tokens Input · Cache read $0.00002 / 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 $0.000144 / 1K tokens Output · Output tokens $0.000858 / 1K tokens Input · Cache read $0.00002 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "z-ai/glm-4.7-flash",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 document}"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ['AILOOT_TEXT_FILE'])\nif not source_file.is_file():\n raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')\ntext = source_file.read_text(encoding='utf-8')\nif not text.strip():\n raise SystemExit('Choose a document containing text')\npayload = {'model': 'z-ai/glm-4.7-flash', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}\npayload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\\n\\n' + text\nPath('request.json').write_text(json.dumps(payload, ensure_ascii=False), encoding='utf-8')\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path('result.json').read_text(encoding='utf-8'))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\nPY_RESULT\nimport json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ['AILOOT_TEXT_FILE'])\nif not source_file.is_file():\n raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')\ntext = source_file.read_text(encoding='utf-8')\nif not text.strip():\n raise SystemExit('Choose a document containing text')\npayload = {'model': 'z-ai/glm-4.7-flash', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}\npayload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\\n\\n' + text\nfrom urllib.request import Request, urlopen\nfrom urllib.error import HTTPError\n\napi_key = os.environ['AILOOT_API_KEY']\nif not api_key.strip():\n raise SystemExit('Set AILOOT_API_KEY before making a request')\nheaders = {'x-api-key': 'PLACEHOLDER_KEY', 'anthropic-version': '2023-06-01', 'Content-Type': 'application/json'}\nheaders['x-api-key'] = api_key\nrequest = Request('https://api.ailoot.ai/v1/messages', data=json.dumps(payload, ensure_ascii=False).encode('utf-8'), headers=headers, method='POST')\ntry:\n with urlopen(request, timeout=120) as response:\n raw = response.read()\n Path('response-headers.txt').write_text(str(response.headers), encoding='utf-8')\nexcept HTTPError as error:\n Path('result.json').write_bytes(error.read())\n Path('response-headers.txt').write_text(str(error.headers), encoding='utf-8')\n raise\nPath('result.json').write_bytes(raw)\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path('result.json').read_text(encoding='utf-8'))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\nJSON or SSE
Keep every complete returned response, file and content part.
Keep all content blocks, thinking signatures and actual tool-use IDs. Assemble all SSE block deltas; a first text block is not the complete output.
Keep request/response IDs and headers. No generic text job retrieval URL is supplied.
| Field | Type |
|---|---|
Fieldid | Typestring |
Fieldmodel | Typestring |
Fieldcontent[] | Typetext|thinking|tool_use|other content block |
Fieldstop_reason | Typestring|null |
Fieldusage | Typeobject |
| Response | Condition | Next step |
|---|---|---|
Response400 · invalid_request_error | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |
Ailoot Ultra z-ai/glm-4.7-flash
Use the method paths shown above.
Technical example in English
Translate a notice with a fixed glossary\n\nTranslate this Chinese notice into English: '订单已审核，但尚未发货。更改收货地址需要重新审核。' Use this glossary consistently: 审核 = review; 发货 = dispatch; 收货地址 = delivery address. Write a clear customer-facing notice and preserve the distinction between completed review and pending dispatch. Do not add a dispatch date or an approval guarantee.A concise English notice applying the glossary and preserving the two different order states.The translation retains the requirement for another review after an address change and does not state that dispatch occurred.