API | GLM 5.3 Flash API — 1M Context, 3 Effort Levels

zai/glm-5.3-flash/chat

GLM 5.3 Flash is Z.ai's long-context chat model behind an OpenAI-compatible call. It reads up to 1,048,576 tokens, replies up to 131,072, and offers three reasoning-effort levels, 128 tool schemas per request and JSON output.

Input $0.1275Output $0.425per 1 million tokensCached input $0.0255

Run model View API

Send a request

Examples use the selected endpoint’s public parameter definitions. Replace the API key and example media, then send the request from your server.

SDKs & integrations

POSThttps://api.spicyapi.ai/v1/chat/completions

API authentication

Keep the API key in the server environment variable SPICY_API_KEY. Use Bearer authentication and Content-Type: application/json for JSON requests.

Authorization: Bearer $SPICY_API_KEY

curl --fail-with-body -sN https://api.spicyapi.ai/v1/chat/completions \
  -H "Authorization: Bearer $SPICY_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
  "model": "zai/glm-5.3-flash/chat",
  "messages": [
    {
      "role": "user",
      "content": "Summarise the following release notes into three bullet points."
    }
  ],
  "stream": true
}' \
  | jq --unbuffered -Rrj 'select(startswith("data: ")) | .[6:] | select(. != "[DONE]") | fromjson | if .error then "\n[error] \(.error.message)\n" else (.choices[0].delta.content? // empty) end'

Generated from this model’s input schema — the same one the API validates every request against.

Keep one Idempotency-Key for each logical request. After a network interruption, do not automatically resend with a new key; retain request_id to investigate the accepted request. Idempotency does not replay an earlier chat stream.

Input parameters

Place the model parameters directly in the JSON request body alongside model. This endpoint does not use an input wrapper.

messagesarray<object>Required

At most 256 ordered turns. Content is a string, or an array of text, image_url and video_url parts. Video is sent as an uploaded file, and the video in one request can total 14 MB. Put the corpus in one user message and the question plus output format in the system message.

Default: Not specified
Constraints: minItems:1
maxItems:256

messages[].rolestringRequired within object

Role of the message author.

Default: Not specified
Allowed values: "system""developer""user""assistant""tool"

messages[].namestringOptional

Optional name identifying the speaker within its role.

Default: Not specified

messages[].contentstring | array | nullOptional

Message content, either plain text or a list of content parts.

Default: Not specified

{
  "type": [
    "string",
    "array",
    "null"
  ],
  "items": {
    "oneOf": [
      {
        "type": "object",
        "required": [
          "type",
          "text"
        ],
        "properties": {
          "text": {
            "type": "string"
          },
          "type": {
            "const": "text"
          }
        }
      },
      {
        "type": "object",
        "required": [
          "type",
          "image_url"
        ],
        "properties": {
          "type": {
            "const": "image_url"
          },
          "image_url": {
            "type": "object",
            "required": [
              "url"
            ],
            "properties": {
              "url": {
                "type": "string"
              }
            }
          }
        }
      },
      {
        "type": "object",
        "required": [
          "type",
          "video_url"
        ],
        "properties": {
          "type": {
            "const": "video_url"
          },
          "video_url": {
            "type": "object",
            "required": [
              "url"
            ],
            "properties": {
              "url": {
                "type": "string"
              }
            }
          }
        }
      }
    ]
  },
  "description": "Message content, either plain text or a list of content parts."
}

messages[].tool_callsarray<object>Optional

Tool calls the assistant requested in this message.

Default: Not specified

messages[].tool_call_idstringOptional

Identifier of the tool call this message answers. Required on tool messages.

Default: Not specified

messages[].reasoning_contentstringOptional

Reasoning text from a previous assistant reply, preserved when continuing a tool conversation.

Default: Not specified

{
  "type": "array",
  "x-ui": {
    "order": 100,
    "widget": "chat-messages",
    "primary": true
  },
  "items": {
    "type": "object",
    "allOf": [
      {
        "if": {
          "required": [
            "reasoning_content"
          ]
        },
        "then": {
          "properties": {
            "role": {
              "const": "assistant"
            }
          }
        }
      }
    ],
    "required": [
      "role"
    ],
    "properties": {
      "name": {
        "type": "string",
        "description": "Optional name identifying the speaker within its role."
      },
      "role": {
        "enum": [
          "system",
          "developer",
          "user",
          "assistant",
          "tool"
        ],
        "type": "string",
        "description": "Role of the message author."
      },
      "content": {
        "type": [
          "string",
          "array",
          "null"
        ],
        "items": {
          "oneOf": [
            {
              "type": "object",
              "required": [
                "type",
                "text"
              ],
              "properties": {
                "text": {
                  "type": "string"
                },
                "type": {
                  "const": "text"
                }
              }
            },
            {
              "type": "object",
              "required": [
                "type",
                "image_url"
              ],
              "properties": {
                "type": {
                  "const": "image_url"
                },
                "image_url": {
                  "type": "object",
                  "required": [
                    "url"
                  ],
                  "properties": {
                    "url": {
                      "type": "string"
                    }
                  }
                }
              }
            },
            {
              "type": "object",
              "required": [
                "type",
                "video_url"
              ],
              "properties": {
                "type": {
                  "const": "video_url"
                },
                "video_url": {
                  "type": "object",
                  "required": [
                    "url"
                  ],
                  "properties": {
                    "url": {
                      "type": "string"
                    }
                  }
                }
              }
            }
          ]
        },
        "description": "Message content, either plain text or a list of content parts."
      },
      "tool_calls": {
        "type": "array",
        "items": {
          "type": "object"
        },
        "description": "Tool calls the assistant requested in this message."
      },
      "tool_call_id": {
        "type": "string",
        "description": "Identifier of the tool call this message answers. Required on tool messages."
      },
      "reasoning_content": {
        "type": "string",
        "description": "Reasoning text from a previous assistant reply, preserved when continuing a tool conversation."
      }
    },
    "additionalProperties": false
  },
  "maxItems": 256,
  "minItems": 1,
  "description": "Conversation history in order, oldest message first."
}

response_formatobjectOptional

Ask for a JSON object and name every key in the system message.

Default: Not specified

tool_choicestring | objectOptional

auto, none, required, or an object naming one function.

Default: Not specified

toolsarray<object>Optional

Up to 128 function definitions per request.

Default: Not specified
Constraints: maxItems:128

top_pnumberOptional

0.01 to 1, default 0.95. Adjust this or temperature, never both in the same comparison.

Default: 0.95
Constraints: minimum:0.01
maximum:1

temperaturenumberOptional

0 to 1, default 1. Hold it at 0 whenever the reply is parsed by code.

Default: 1
Constraints: minimum:0
maximum:1

max_tokensintegerOptional

Caps the reply at 131,072 - an eighth of the read window. Default 32,768. Reasoning tokens are billed as output too, so leave headroom above the visible answer you expect.

Default: 32768
Constraints: minimum:1
maximum:131072

stopstring | arrayOptional

One sequence, as a string or a one-item array: Z.ai reads only one. The reply ends as soon as the model writes it, and the matched text is left out. It can also fire inside the reasoning pass and end the turn before any answer appears, so pick a string the reasoning is unlikely to contain. No default. It does not change the rate; a reply cut short is billed only for the tokens it produced.

Default: Not specified
Constraints: minLength:1
minItems:1
maxItems:1

reasoning_effortstringOptional

low, high or max. max is the default, as on Z.ai's own API, so a request that omits the field already gets the most careful setting; drop to low or high for bulk passes.

Default: "max"
Allowed values: "low""high""max"

{
  "type": "object",
  "required": [
    "messages"
  ],
  "x-pricing": {
    "billingMode": "formula",
    "variantFields": []
  },
  "properties": {
    "stop": {
      "type": [
        "string",
        "array"
      ],
      "x-ui": {
        "order": 65,
        "widget": "text",
        "affects_price": false
      },
      "items": {
        "type": "string",
        "minLength": 1
      },
      "maxItems": 1,
      "minItems": 1,
      "minLength": 1,
      "description": "A sequence that ends the reply as soon as the model writes it; the matched text is not returned."
    },
    "tools": {
      "type": "array",
      "x-ui": {
        "order": 35,
        "widget": "json"
      },
      "items": {
        "type": "object"
      },
      "maxItems": 128,
      "description": "Tool definitions the model may call."
    },
    "top_p": {
      "type": "number",
      "x-ui": {
        "step": 0.01,
        "order": 40,
        "widget": "slider"
      },
      "default": 0.95,
      "maximum": 1,
      "minimum": 0.01,
      "description": "Nucleus sampling threshold. Lower values keep only the most likely tokens."
    },
    "messages": {
      "type": "array",
      "x-ui": {
        "order": 100,
        "widget": "chat-messages",
        "primary": true
      },
      "items": {
        "type": "object",
        "allOf": [
          {
            "if": {
              "required": [
                "reasoning_content"
              ]
            },
            "then": {
              "properties": {
                "role": {
                  "const": "assistant"
                }
              }
            }
          }
        ],
        "required": [
          "role"
        ],
        "properties": {
          "name": {
            "type": "string",
            "description": "Optional name identifying the speaker within its role."
          },
          "role": {
            "enum": [
              "system",
              "developer",
              "user",
              "assistant",
              "tool"
            ],
            "type": "string",
            "description": "Role of the message author."
          },
          "content": {
            "type": [
              "string",
              "array",
              "null"
            ],
            "items": {
              "oneOf": [
                {
                  "type": "object",
                  "required": [
                    "type",
                    "text"
                  ],
                  "properties": {
                    "text": {
                      "type": "string"
                    },
                    "type": {
                      "const": "text"
                    }
                  }
                },
                {
                  "type": "object",
                  "required": [
                    "type",
                    "image_url"
                  ],
                  "properties": {
                    "type": {
                      "const": "image_url"
                    },
                    "image_url": {
                      "type": "object",
                      "required": [
                        "url"
                      ],
                      "properties": {
                        "url": {
                          "type": "string"
                        }
                      }
                    }
                  }
                },
                {
                  "type": "object",
                  "required": [
                    "type",
                    "video_url"
                  ],
                  "properties": {
                    "type": {
                      "const": "video_url"
                    },
                    "video_url": {
                      "type": "object",
                      "required": [
                        "url"
                      ],
                      "properties": {
                        "url": {
                          "type": "string"
                        }
                      }
                    }
                  }
                }
              ]
            },
            "description": "Message content, either plain text or a list of content parts."
          },
          "tool_calls": {
            "type": "array",
            "items": {
              "type": "object"
            },
            "description": "Tool calls the assistant requested in this message."
          },
          "tool_call_id": {
            "type": "string",
            "description": "Identifier of the tool call this message answers. Required on tool messages."
          },
          "reasoning_content": {
            "type": "string",
            "description": "Reasoning text from a previous assistant reply, preserved when continuing a tool conversation."
          }
        },
        "additionalProperties": false
      },
      "maxItems": 256,
      "minItems": 1,
      "description": "Conversation history in order, oldest message first."
    },
    "max_tokens": {
      "type": "integer",
      "x-ui": {
        "unit": "tokens",
        "order": 60,
        "widget": "number",
        "advanced": false,
        "affects_price": false
      },
      "default": 32768,
      "maximum": 131072,
      "minimum": 1,
      "description": "Maximum number of tokens to generate in the reply."
    },
    "temperature": {
      "type": "number",
      "x-ui": {
        "order": 50,
        "widget": "slider"
      },
      "default": 1,
      "maximum": 1,
      "minimum": 0,
      "description": "Sampling temperature. Higher values make the output more varied."
    },
    "tool_choice": {
      "type": [
        "string",
        "object"
      ],
      "x-ui": {
        "order": 30,
        "widget": "json"
      },
      "description": "Controls whether and which tool the model may call."
    },
    "response_format": {
      "type": "object",
      "x-ui": {
        "order": 25,
        "widget": "json"
      },
      "description": "Requested reply format, such as plain text or a JSON object."
    },
    "reasoning_effort": {
      "enum": [
        "low",
        "high",
        "max"
      ],
      "type": "string",
      "x-ui": {
        "order": 70,
        "widget": "radio"
      },
      "default": "max",
      "description": "How much reasoning the model spends before answering."
    }
  },
  "x-input-token-limit": 1048576,
  "additionalProperties": false
}

Read the result

With stream set to false, the request returns the completed chat response directly. Read choices[].message; no task polling is needed. Set stream to true when your client supports Server-Sent Events.

Completed response example

{
  "id": "chatcmpl_example",
  "object": "chat.completion",
  "created": 1788652800,
  "model": "zai/glm-5.3-flash/chat",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Here is a concise summary of the release notes."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 32,
    "completion_tokens": 14,
    "total_tokens": 46
  }
}

The response example is illustrative. usage reports token counts; token counts and charges depend on your actual request.

SDKs & integrations

Use SpicyAPI in your app, terminal, AI assistant or visual workflow. Choose a setup guide below.

SDKs

TypeScript · Python · Go · PHP · Java

CLI

Terminal commands and automation scripts.

MCP

Claude Code · Cursor · Codex

Agent Skill

Reusable instructions for your AI assistant.

n8n

Self-hosted community nodes and importable HTTP Request templates for n8n Cloud.

ComfyUI

Image, video and audio workflows on a node canvas.

More integrations

SillyTavern Telegram / Discord App proxy OpenAI SDK LangChain Vercel AI SDK

Browse ready-to-use workflows

This is a chat model, so it works wherever the OpenAI chat API works: keep your client, change the base URL, and select this model by its ID.

Point any OpenAI-compatible client here

export OPENAI_BASE_URL="https://api.spicyapi.ai/v1"
export OPENAI_API_KEY="$SPICY_API_KEY"

aider --model openai/zai/glm-5.3-flash/chat

Anything that speaks the OpenAI chat API works the same way — SDKs, the Vercel AI SDK, LangChain, aider, Cline. The MCP server and the spicyapi CLI cover asynchronous media tasks. Per-tool setup is in the developer hub.

Use it in SillyTavern and roleplay apps

In SillyTavern, RisuAI, Agnai or any app with an OpenAI-compatible setting, paste the base URL below and your API key, then pick zai/glm-5.3-flash/chat as the model. Browser calls are allowed, and sliders this model does not take are ignored instead of rejected.

Base URL: https://api.spicyapi.ai/v1
Model: zai/glm-5.3-flash/chat

SillyTavern guide RisuAI, Agnai and more SillyTavern extension

Use it in ComfyUI

Install the SpicyAPI nodes from ComfyUI Manager or with the command below, then pick zai/glm-5.3-flash/chat in the SpicyAPI Chat node to use this model inside a ComfyUI graph.

cd ComfyUI/custom_nodes
git clone https://github.com/spicyapi-ai/comfyui-spicyapi

Workflow examples Setup guide Source on GitHub

The embedded panel reads the same schema as this page, so it cannot drift from the API. If your docs need the content to be searchable, read the JSON under /api/embed/models/ and render it yourself.

<iframe src="https://spicyapi.ai/embed/en/models/glm-5-3-flash/api?model=zai%2Fglm-5.3-flash%2Fchat" width="100%" height="560" loading="lazy" title="Request example" style="border:1px solid rgba(0,0,0,.12)"></iframe>

Open the panel

Workbench

Send a request

API authentication

Input parameters

Read the result

SDKs & integrations

Use it in SillyTavern and roleplay apps

Use it in ComfyUI