models

GLM-4-Long

Markdown · JSON

GLM-4-Long

GLM-4-Long is Zhipu AI’s model for reading very long texts and maintaining document context across a conversation. Its documented 1M context and 4K maximum output support focused analyses of reports, papers, contracts and long-form fiction.

About the model

This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.

GLM-4-Long is Zhipu AI’s language model for very long texts and memory-oriented conversation tasks. The producer specifies text input and text output, a 1M context window and a maximum output of 4K tokens. Its emphasis is reading, translating and analysing extensive material, then producing a focused response based on the supplied content.

Prepare the material for a global analysis

Supply the document text together with the question it should answer. Keep section headings, page or chapter identifiers, dates and table units attached to their contents. A long input window is useful when an answer depends on relationships across many sections, such as a stated objective, the evidence supporting it and an exception elsewhere in the document.

The maker describes gradually extending context from 2K to 1M through continued pre-training, supervised fine-tuning and reinforcement learning from human feedback. For practical work, define the relationship to examine before asking for a broad summary. An illustrative instruction is: “Compare the proposed architecture with the implementation sections, and identify each difference with its source section.” The result can be a concise comparison that keeps the original evidence available for review.

Read financial reports and academic papers

The producer recommends analysing annual reports, extracting revenue structure, risk disclosures and management discussion, and comparing financial data across periods. Prepare reports with their reporting dates and consistent labels for units and currencies. Ask for a table of the selected figures, the passage behind each value and a separate explanation of the change. This preserves the distinction between a reported number and an interpretation of its movement.

For academic material, GLM-4-Long can organise research background, experimental methods and conclusions by topic. Provide the complete passages needed for the comparison, including definitions and qualifications that occur in another chapter. A useful output is a map of claims, methods and supporting sections, followed by questions that remain unresolved in the supplied text. Keep quotations and the model’s analysis in separate fields when preparing a research note.

Follow clauses, characters and events across a long text

The maker’s legal-document scenario covers statutes, cases and contracts, including rights, obligations and responsibility clauses. Name the parties and the issue to compare, then ask for the relevant clauses with their section references. A focused extraction can become a working document for later professional review, with the source wording beside the explanation.

The fiction scenario concerns character relationships, plot structure, targeted summaries and continuation based on a long narrative’s style. Specify the chapters and the point in the chronology that matter. For example, request a character relationship map with the events supporting each connection, or a continuation brief that retains established names and unresolved story threads.

Use the long input with a bounded answer

The documented 4K maximum output is much smaller than the input context. Select the desired deliverable: an executive summary, a clause comparison, a research outline or a chapter-specific analysis. For a large review, divide the requested output into clearly named tasks while keeping the relevant source material associated with each answer.

For a continuing document conversation, retain the earlier question, answer and the passages needed for the next question. The producer describes memory-oriented chat as a use of long context; organise that context so the follow-up refers to the same document, reporting period or chapter. Save the completed analysis with those source identifiers, then check extracted names, figures and quotations against the underlying text before incorporating them into the next report.

Practical task

Reconcile architecture and implementation notes

Technical example in English

Reconcile architecture and implementation notes

Compare labeled excerpts. Architecture §2: every export job is resumable and stores its cursor after each completed page. Implementation §7: the exporter stores its cursor only when the entire job completes. Operations §4: interrupted jobs restart from page one. Return a concise discrepancy map with source references and a focused requirement for the next code review.

Expected result

A source-linked discrepancy table and one review requirement tied to the resumability objective.

Check the result

The answer connects all three excerpts and does not invent additional implementation details.
Ailoot Ultra · OpenAI Chat POST /v1/chat/completions glm-4-long

glm-4-long

Z.ai /glm-4-long

Overview

GLM-4-Long is Zhipu AI’s model for reading very long texts and maintaining document context across a conversation. Its documented 1M context and 4K maximum output support focused analyses of reports, papers, contracts and long-form fiction.

Accepted inputs
Text
Results
Text

Available in Ailoot · inputs & methods

Ailoot Ultra · OpenAI Chat POST /v1/chat/completions
Input types
text
Output types
text
Output format
json or SSE
FieldTypeRequirementValues & limitsDefault
FieldmodelTypestringRequirementRequiredValues & limits
glm-4-long
Default—
FieldmessagesTypemessage[]RequirementRequiredValues & limits
Minimum items: 1
Default—
Fieldmessages[].roleTypestringRequirementRequiredValues & 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[].contentTypestring|content_part[]|nullRequirementOptionalValues & limitsDefault—
Fieldmessages[].tool_callsTypetool_call[]RequirementOptionalValues & limitsDefault—
Fieldmessages[].tool_call_idTypestringRequirementOptionalValues & limits
Applies when: role=tool; use actual returned ID
Default—
Fieldmessages[].nameTypestringRequirementOptionalValues & limitsDefault—
Fieldmessages[].reasoning_contentTypestringRequirementOptionalValues & limits
Applies when: Round-trip actual returned reasoning where this model uses it
Default—
Fieldmessages[].reasoning_detailsTypeobject|arrayRequirementOptionalValues & limits
Model-specific
Default—
Fieldmax_tokensTypeintegerRequirementOptionalValues & limits
Minimum: 1
Model-specific
Default—
Fieldmax_completion_tokensTypeintegerRequirementOptionalValues & limits
Minimum: 1
Model-specific
Default—
FieldstreamTypebooleanRequirementOptionalValues & limitsDefaultfalse
Fieldstream_options.include_usageTypebooleanRequirementOptionalValues & limits
Model-specific
Default—
FieldtemperatureTypenumberRequirementOptionalValues & limits
Model-specific
Default—
Fieldtop_pTypenumberRequirementOptionalValues & limits
Model-specific
Default—
FieldstopTypestring|string[]RequirementOptionalValues & limits
Model-specific
Default—
FieldtoolsTypefunction_tool[]RequirementOptionalValues & limits
Model-specific
Default—
Fieldtools[].typeTypestringRequirementOptionalValues & limits
function
Model-specific
Default—
Fieldtools[].function.nameTypestringRequirementRequiredValues & limits
Applies when: function tool supplied
Default—
Fieldtools[].function.descriptionTypestringRequirementOptionalValues & limitsDefault—
Fieldtools[].function.parametersTypeJSON_schemaRequirementOptionalValues & limitsDefault—
Fieldtool_choiceTypestring|objectRequirementOptionalValues & limits
Model-specific
Default—
Fieldparallel_tool_callsTypebooleanRequirementOptionalValues & limits
Model-specific
Default—
Fieldresponse_formatTypeobjectRequirementOptionalValues & limits
Model-specific
Default—
Fieldreasoning_effortTypestringRequirementOptionalValues & limits
Model-specific
Default—
FieldreasoningTypeobjectRequirementOptionalValues & limits
Model-specific
Default—
Fieldservice_tierTypestringRequirementOptionalValues & limits
Model-specific
Default—
FieldinstructionsTypestringRequirementOptionalValues & limits
Compatibility field
Default—
FieldfunctionsTypefunction[]RequirementOptionalValues & limits
Model-specific
Default—
Fieldfunction_callTypestring|objectRequirementOptionalValues & limits
Model-specific
Default—
Fieldprompt_cache_optionsTypeobjectRequirementOptionalValues & limits
Model-specific
Default—
FieldmodalitiesTypestring[]RequirementOptionalValues & limits
text
Default—
FieldproviderTypeobjectRequirementOptionalValues & limits
Conditions: provider.options is rejected on this Ultra text route
Default—
Fieldcache_control.ttlTypestringRequirementOptionalValues & limits
Conditions: 1h is rejected in actual prompt-cache locations
Default—
Input material combinations

Text · UTF8 text

messages[].content

Method parameters and lifecycle
ParameterContract
Parametercontent_typeContractapplication/json
ParameterrequiredContractmodel, messages
Parametermaterial_typesContracttext
ParametermessagesContractmessage array with role/content shape
Parameterfile_materialContractactual UTF-8 document inserted as literal text; no file ID inferred
Parameteroptional_controlsContractstream, temperature, top_p, stop, max_tokens, max_completion_tokens, reasoning, response_format, tools, tool_choice
Parametercontrol_scopeContractmodel-specific; user function tools differ from hosted tools
Parameteroutput_modalitiesContracttext
Parameterhosted_operationsContractfalse
Parametermultimodal_input_bindingContractnull

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.

Pricing

Tariff references do not add request options. Supported parameters are listed for the selected method.

Fast mode
Not specified When fast mode is selected
Flex mode
Not specified When flex mode is selected
Maximum reasoning effort
Not specified When maximum reasoning effort uses the default adjustment

Ailoot rates

Prices by configuration

ConfigurationRate scheduleCharge
ConfigurationBase token ratesRate scheduleBase rateCharge
Input · Input tokens $0.00028 / 1K tokens
Output · Output tokens $0.00028 / 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 →

Example requests

Ailoot Ultra · OpenAI Chat

curlPython SDKPython stream
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "glm-4-long", "messages": [{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}]}')

Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
r=json.loads(Path("result.json").read_text())
for x in r.get("choices",[]):
    if x.get("message",{}).get("content"): print(x["message"]["content"])
PY_RESULT
from openai import OpenAI
import os

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
result=client.chat.completions.create(model='glm-4-long',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}])
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        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
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(result.to_dict(mode="json"))
from openai import OpenAI
import os
from pathlib import Path

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        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
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

with client.chat.completions.stream(model='glm-4-long',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:
    with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:
        for event in stream:
            payload=event.to_dict(mode="json")
            log.write(json.dumps(payload,ensure_ascii=False)+"\n"); log.flush()
            print(json.dumps(payload,ensure_ascii=False))
    final=stream.get_final_completion()
    save_result(final.to_dict(mode="json"),"stream-result")

Receive and save results

Ailoot Ultra · OpenAI Chat

json or SSE

Keep all completed results

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.

If the original response needs checking

Keep request/response IDs and headers. No generic text job retrieval URL is supplied.

Response fields
FieldType
Fieldchoices[].indexTypeinteger
Fieldchoices[].message.contentTypestring|null
Fieldchoices[].message.tool_callsTypetool_call[]
Fieldchoices[].message.reasoning_contentTypestring
Fieldchoices[].message.reasoning_detailsTypeobject|array
Fieldchoices[].finish_reasonTypestring|null
FieldusageTypeobject
Errors and next steps
ResponseConditionNext step
Response400 · invalid_request_errorConditionInvalid required fields, material representation or parameter valueNext stepCorrect the indicated fields before a new creation request.

Aliases

Model aliases

Ailoot Ultra glm-4-long

Method path aliases

Use the method paths shown above.

Related caller IDs

glm-4-long

Ailoot Ultra · Anthropic Messages POST /v1/messages glm-4-long

glm-4-long

Z.ai /glm-4-long

Overview

GLM-4-Long is Zhipu AI’s model for reading very long texts and maintaining document context across a conversation. Its documented 1M context and 4K maximum output support focused analyses of reports, papers, contracts and long-form fiction.

Accepted inputs
Text
Results
json · sse

Available in Ailoot · inputs & methods

Ailoot Ultra · Anthropic Messages POST /v1/messages
Input types
text
Output types
json, sse
Output format
JSON or SSE
FieldTypeRequirementValues & limitsDefault
FieldmodelTypestringRequirementRequiredValues & limits
glm-4-long
Default—
FieldmessagesTypemessage[]RequirementRequiredValues & limitsDefault—
Fieldmessages[].roleTypestringRequirementRequiredValues & limits
user, assistant
Default—
Fieldmessages[].contentTypestringRequirementRequiredValues & limitsDefault—
Fieldmax_tokensTypeintegerRequirementRequiredValues & limitsDefault—
FieldstreamTypebooleanRequirementOptionalValues & limitsDefaultfalse
Input material combinations

Text · UTF-8 text

messages[].content string

Method parameters and lifecycle
ParameterContract
Parametercontent_typeContractapplication/json
ParameterrequiredContractmodel, messages, max_tokens
Parameteroptional_controlsContractstream
Parametermaterial_typesContracttext
Parametertext_file_materialContractRead the actual UTF-8 document and put its text in the indicated input or message content string.

Lifecycle: synchronous_or_streamed

Pricing

Tariff references do not add request options. Supported parameters are listed for the selected method.

Fast mode
Not specified When fast mode is selected
Flex mode
Not specified When flex mode is selected
Maximum reasoning effort
Not specified When maximum reasoning effort uses the default adjustment

Ailoot rates

Prices by configuration

ConfigurationRate scheduleCharge
ConfigurationBase token ratesRate scheduleBase rateCharge
Input · Input tokens $0.00028 / 1K tokens
Output · Output tokens $0.00028 / 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 →

Example requests

Ailoot Ultra · Anthropic Messages

Complete minimal JSON bodycurl · use your UTF-8 documentPython · save the complete result
{
  "model": "glm-4-long",
  "max_tokens": 128,
  "messages": [
    {
      "role": "user",
      "content": "Summarize the incident report."
    }
  ],
  "stream": false
}
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 document}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json, os
from pathlib import Path

source_file = Path(os.environ['AILOOT_TEXT_FILE'])
if not source_file.is_file():
    raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')
text = source_file.read_text(encoding='utf-8')
if not text.strip():
    raise SystemExit('Choose a document containing text')
payload = {'model': 'glm-4-long', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}
payload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\n\n' + text
Path('request.json').write_text(json.dumps(payload, ensure_ascii=False), encoding='utf-8')
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \
  -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path

result = json.loads(Path('result.json').read_text(encoding='utf-8'))
print(json.dumps(result, ensure_ascii=False, indent=2))
PY_RESULT
import json, os
from pathlib import Path

source_file = Path(os.environ['AILOOT_TEXT_FILE'])
if not source_file.is_file():
    raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')
text = source_file.read_text(encoding='utf-8')
if not text.strip():
    raise SystemExit('Choose a document containing text')
payload = {'model': 'glm-4-long', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}
payload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\n\n' + text
from urllib.request import Request, urlopen
from urllib.error import HTTPError

api_key = os.environ['AILOOT_API_KEY']
if not api_key.strip():
    raise SystemExit('Set AILOOT_API_KEY before making a request')
headers = {'x-api-key': 'PLACEHOLDER_KEY', 'anthropic-version': '2023-06-01', 'Content-Type': 'application/json'}
headers['x-api-key'] = api_key
request = Request('https://api.ailoot.ai/v1/messages', data=json.dumps(payload, ensure_ascii=False).encode('utf-8'), headers=headers, method='POST')
try:
    with urlopen(request, timeout=120) as response:
        raw = response.read()
        Path('response-headers.txt').write_text(str(response.headers), encoding='utf-8')
except HTTPError as error:
    Path('result.json').write_bytes(error.read())
    Path('response-headers.txt').write_text(str(error.headers), encoding='utf-8')
    raise
Path('result.json').write_bytes(raw)
import json
from pathlib import Path

result = json.loads(Path('result.json').read_text(encoding='utf-8'))
print(json.dumps(result, ensure_ascii=False, indent=2))

Receive and save results

Ailoot Ultra · Anthropic Messages

JSON or SSE

Keep all completed results

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.

If the original response needs checking

Keep request/response IDs and headers. No generic text job retrieval URL is supplied.

Response fields
FieldType
FieldidTypestring
FieldmodelTypestring
Fieldcontent[]Typetext|thinking|tool_use|other content block
Fieldstop_reasonTypestring|null
FieldusageTypeobject
Errors and next steps
ResponseConditionNext step
Response400 · invalid_request_errorConditionInvalid required fields, material representation or parameter valueNext stepCorrect the indicated fields before a new creation request.

Aliases

Model aliases

Ailoot Ultra glm-4-long

Method path aliases

Use the method paths shown above.

Related caller IDs

glm-4-long

FAQ · GLM-4-Long
What inputs and results are available?

POST /v1/chat/completions · glm-4-long: text → text

POST /v1/messages · glm-4-long: text → json, sse

Which fields does the request use?

POST /v1/chat/completions · glm-4-long: model, messages, stream, modalities, provider

POST /v1/messages · glm-4-long: model, messages, max_tokens, stream

What limits apply?

POST /v1/chat/completions · glm-4-long: messages.min_items: 1

More details

Connect Ailoot to Claude Code, OpenCode, Hermes or your own app.

The company and its project portfolio

The company and its project portfolio: millions of customers; monthly sales in the billions.

Buy tokens at a discount.

Subscription discounts for regular use. Promo codes offer up to 50% off token purchases.

Subscription
Choose a discounted plan for your regular requests.
Promo code: up to 50% off
Enter your code at checkout. The price updates to reflect the current promotion.
Spending in your history
The model, tokens and amount are recorded for each request.

Choose a subscription · View model prices

Connect the API to a product you sell.

Use Ailoot in SaaS, apps and bots under its official service offer and licence agreement. Request a reseller licence for resale.

Commercial application
Add text, image, video and audio generation to paid features in your service.
Reseller licence
Send a description of your project and how you provide access. Request written terms for use and resale.
Documents on the website
The service offer, licence agreement and data processing policy are available before you connect.

Request a reseller licence · Service offer and licence agreement