Evaluación de agentes de texto de varios pasos
Planificación de ejercicios, argumentos de herramientas y recuperación de errores en una tarea controlada.
USD / 1 millón de tokens
Catálogo actualizado: 2026-10-29.
Acceda a GLM-5.3 a través de la API compatible con IteraCompute OpenAI con contexto de 1M, llamada de herramientas, razonamiento y transmisión.
https://api.iteracompute.com/v1Authorization: Bearer ITERACOMPUTE_API_KEYChoose request fields, response parsing and stream completion by endpoint. This table describes wire formats; see this model's capabilities and verification scope.
| Customer endpoint | Model status | Input / output budget | Result | SSE completion |
|---|---|---|---|---|
OpenAI Chat CompletionsPOST /v1/chat/completions | Declared for this model | messagesmax_tokens | choices[0].message.content | [DONE] |
OpenAI ResponsesPOST /v1/responses | Declared for this model | inputmax_output_tokens | output[] (SDK: output_text) | response.completed |
Anthropic MessagesPOST /v1/messages | Declared for this model | messages; system (top-level)max_tokens (required) | content[] | message_stop |
For the Messages SDK use https://api.iteracompute.com as base URL; max_tokens is required. Do not reuse another protocol's fields.
Includes this model's ID, wire formats and parameter constraints. Check this page's verification scope and current prices before use.
# IteraCompute · z-ai/glm-5.3
Model ID: z-ai/glm-5.3
Base URL (OpenAI SDK): https://api.iteracompute.com/v1
Authentication: Authorization: Bearer ITERACOMPUTE_API_KEY
Content-Type: application/json
Use only the customer endpoints below. Request and response formats differ by protocol. An endpoint declaration does not certify every capability.
## Chat Completions
POST https://api.iteracompute.com/v1/chat/completions
Input: messages
Output budget: max_tokens
Read result: choices[0].message.content
SSE completion: [DONE]
Docs: https://iteracompute.com/docs.html#api-reference
## Responses
POST https://api.iteracompute.com/v1/responses
Input: input
Output budget: max_output_tokens
Read result: output[] (SDK: output_text)
SSE completion: response.completed
Docs: https://iteracompute.com/docs.html#responses-api
## Messages
POST https://api.iteracompute.com/v1/messages
Input: messages; system (top-level)
Output budget: max_tokens (required)
Read result: content[]
SSE completion: message_stop
Docs: https://iteracompute.com/docs.html#anthropic-messages
## Parameters
Configuration and parameter acceptance do not establish semantic capability. Do not invent undisclosed defaults.
Current parameter configuration is unconfirmed. Check the model page and current catalog before calling.
## References
Model catalog: https://iteracompute.com/models/
Current prices and billing: https://iteracompute.com/pricing/
Documentation index: https://iteracompute.com/llms.txt
Unknown prices are not zero. Account and subscription limits also apply.
Never include a real API key in an LLM prompt or client-side code.
GLM-5.3 y Flash requieren razonamiento y admiten los niveles low/high/max. Los límites de muestreo dependen del modelo. La pasarela ofrece Chat Completions, Responses y Messages, y convierte los controles de razonamiento nativos de cada protocolo. Responses no conserva estado: store/background deben ser false.
Utilice los parámetros y las pruebas publicados para este modelo concreto. Revisar la documentación del proveedor no certifica todas las funciones en la pasarela.
These parameters and ranges come from the model’s existing default configuration, not live verification of the current route. Published configuration takes precedence.
Click a parameter to copy its name; scroll the table horizontally to see all columns. Usage notes identify protocol differences; identical names do not guarantee cross-endpoint support.
| Parameter | Type | Acceptance | Range | Usage / protocol |
|---|---|---|---|---|
| integer | Reference: supported | [1, 131072] | Output token budget; includes reasoning where applicable. Chat Completions / Messages. | |
| integer | Reference: supported | [1, 131072] | Alternative Chat output budget; use only when accepted by this model. | |
| integer | Reference: supported | [1, 131072] | Responses output budget. Chat acceptance must be checked separately. | |
| number | Reference: supported | [0, 1] | Sampling randomness. An accepted but ignored value does not control generation. | |
| number | Reference: supported | [0.01, 1] | Nucleus sampling probability threshold. | |
| number | Reference: supported | [-2, 2] | Penalize tokens already present in the generated text. | |
| number | Reference: supported | [-2, 2] | Penalize repeated tokens according to frequency. | |
| integer | Reference: supported | [1, 1] | Number of completions; many routes accept only 1. | |
| boolean | Reference: supported | — | Enable SSE streaming; completion markers depend on the protocol. | |
| array | Reference: supported | — | Tool definitions; the application executes tool calls and returns results. | |
| any | Reference: supported | — | Choose whether and which tool to call; allowed shapes vary by protocol. | |
| object | Reference: supported | — | Text: Chat output format. Images: b64_json only; not text JSON mode. | |
| any | Reference: supported | — | Reasoning control; object or boolean depends on the model and protocol. | |
| enum | Reference: supported | [false] | Responses storage control; acceptance does not establish retention guarantees. | |
| enum | Reference: supported | [false] | Responses: background execution (false on stateless routes). Images: auto, opaque or transparent. | |
| enum | Reference: supported | ["low","high","max"] | Chat reasoning effort; use the model's listed values, not another protocol's shape. |
POST /v1/chat/completions
{
"model": "z-ai/glm-5.3",
"messages": [
{
"role": "user",
"content": "Reply OK"
}
],
"max_tokens": 256,
"reasoning_effort": "low"
}Parameter revision:9933293f7aba
Haz clic en un parámetro para copiar su nombre.
| Parámetros | Uso |
|---|---|
| Utilice el ID de modelo exacto y la lista de mensajes de chat | |
| Utilice herramientas para definir funciones y role=tool para devolver sus resultados. | |
| Utilice la transmisión SSE con uso final | |
| Establecer un presupuesto de producción dentro de los límites del modelo y de la cuenta. |
Los parámetros varían según el modelo.Mantenga los controles específicos del modelo separados de los campos compartidos compatibles con OpenAI.
Referencia de interfaz verificada: 2026-10-23
| Parámetros | Uso |
|---|---|
| Chat usa max_tokens o max_completion_tokens; Responses usa max_output_tokens. Usa enteros positivos dentro de los límites del Gateway. | |
| temperature: 0–1; top_p: 0.01–1. GLM-5.3 y Flash requieren razonamiento con low/high/max (max por defecto). |
2026-10-26
Current parameter configuration is unconfirmed; the historical example below has not been verified against the current configuration.
import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.iteracompute.com/v1",
api_key=os.environ["ITERACOMPUTE_API_KEY"],
)
response = client.chat.completions.create(
model='z-ai/glm-5.3',
messages=[{'role': 'user', 'content': 'Reply OK'}],
max_tokens=256,
reasoning_effort='low',
)
print(response.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.iteracompute.com/v1",
apiKey: process.env.ITERACOMPUTE_API_KEY,
});
const response = await client.chat.completions.create({
"model": "z-ai/glm-5.3",
"messages": [
{
"role": "user",
"content": "Reply OK"
}
],
"max_tokens": 256,
"reasoning_effort": "low"
});
console.log(response.choices[0].message.content);curl https://api.iteracompute.com/v1/chat/completions \
-H "Authorization: Bearer ITERACOMPUTE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "z-ai/glm-5.3",
"messages": [
{
"role": "user",
"content": "Reply OK"
}
],
"max_tokens": 256,
"reasoning_effort": "low"
}'import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.iteracompute.com/v1",
api_key=os.environ["ITERACOMPUTE_API_KEY"],
)
response = client.responses.create(
model='z-ai/glm-5.3',
input='Reply OK',
max_output_tokens=256,
reasoning={'effort': 'low'},
)
print(response.output_text)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.iteracompute.com/v1",
apiKey: process.env.ITERACOMPUTE_API_KEY,
});
const response = await client.responses.create({
"model": "z-ai/glm-5.3",
"input": "Reply OK",
"max_output_tokens": 256,
"reasoning": {
"effort": "low"
}
});
console.log(response.output_text);curl https://api.iteracompute.com/v1/responses \
-H "Authorization: Bearer ITERACOMPUTE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "z-ai/glm-5.3",
"input": "Reply OK",
"max_output_tokens": 256,
"reasoning": {
"effort": "low"
}
}'import os
from anthropic import Anthropic
client = Anthropic(
base_url="https://api.iteracompute.com",
api_key=os.environ["ITERACOMPUTE_API_KEY"],
)
response = client.messages.create(
model='z-ai/glm-5.3',
max_tokens=256,
messages=[{'role': 'user', 'content': 'Reply OK'}],
output_config={'effort': 'low'},
)
print("".join(block.text for block in response.content if block.type == "text"))import Anthropic from "@anthropic-ai/sdk";
const client = new Anthropic({
baseURL: "https://api.iteracompute.com",
apiKey: process.env.ITERACOMPUTE_API_KEY,
});
const response = await client.messages.create({
"model": "z-ai/glm-5.3",
"max_tokens": 256,
"messages": [
{
"role": "user",
"content": "Reply OK"
}
],
"output_config": {
"effort": "low"
}
});
console.log(response.content.filter(block => block.type === "text").map(block => block.text).join(""));curl https://api.iteracompute.com/v1/messages \
-H "x-api-key: ITERACOMPUTE_API_KEY" \
-H "anthropic-version: 2023-06-01" \
-H "Content-Type: application/json" \
-d '{
"model": "z-ai/glm-5.3",
"max_tokens": 256,
"messages": [
{
"role": "user",
"content": "Reply OK"
}
],
"output_config": {
"effort": "low"
}
}'Precios en USD por 1 millón de tokens, verificados el 2026-11-20: $0.82 de entrada, $0.20 de entrada en caché y $2.88 de salida. El precio oficial de Z.ai para el mismo modelo es $1.40 / $0.26 / $4.40.
z-ai/glm-5.3Revisión del backend: no publicadaUtilice los parámetros y las pruebas publicados para este modelo concreto. Revisar la documentación del proveedor no certifica todas las funciones en la pasarela.
Fuente del precio: API pública de modelos · Los precios y la precisión se verifican por separado.
Las tarifas de lectura de caché se aplican a aciertos reales. Una tarifa ausente (—) es desconocida, no cero. Consulte los límites de uso para las restricciones de contexto de la cuenta y del Gateway.
La entrada incluye lecturas y escrituras de caché sin solaparse. La salida ya incluye razonamiento; indícalo como subconjunto, sin sumarlo dos veces. Cuenta pasos del agente y reintentos como solicitudes.
Coste mensual
—USDGLM-5.3
Sin garantía de caché ni capacidad.
Planificación de ejercicios, argumentos de herramientas y recuperación de errores en una tarea controlada.
Compare los requisitos y la implementación con una lista de verificación explícita.
Sugerencias de tareas basadas en las características y el precio del catálogo, no en puntos de referencia de calidad del modelo.
Establezca base_url en https://api.iteracompute.com/v1 y modelo en z-ai/glm-5.3.Autentíquese con su clave API de IteraCompute.
Consulte la sección de precios para conocer las tasas actuales de entrada, entrada en caché y salida en USD por 1 millón de tokens.Verifique el tiempo de actualización antes de su uso.
Consulte el resumen anterior para ver el contexto y la salida máxima de esta API. La entrada y la salida solicitada comparten el presupuesto de contexto.
Cree su clave, elija una herramienta y obtenga una primera respuesta que no esté vacía.
Explora los modelos seleccionados como novedades, con precios de API, funciones compatibles y guías de integración.
gemini/gemini-4-hydrogen
Google Cloud lists Gemini 4 Hydrogen for fast coding assistance, multimodal input and high-volume text generation.
Disponible en IteraCompute desde
USD / 1 millón de tokens
openai/gpt-6.2-astra
OpenAI lists GPT-6.2 Astra for complex engineering and long-horizon reasoning.
Disponible en IteraCompute desde
USD / 1 millón de tokens
openai/gpt-6.2-sol
OpenAI lists GPT-6.2 Sol for everyday coding and agent workflows.
Disponible en IteraCompute desde
USD / 1 millón de tokens