{ "openapi": "3.1.0", "info": { "title": "Runware API - GLM-5.1", "summary": "Flagship agentic coding model with 200K context, deep thinking, and long-horizon task execution", "description": "GLM-5.1 is Z.ai’s flagship language model for agentic engineering, coding, reasoning, and tool-driven workflows. It supports a 200K token context window with up to 128K output tokens, deep thinking, function calling, structured output, and streaming tool calls, and is designed to stay effective over long multi-step sessions rather than only short-horizon tasks.", "version": "1.0.0", "x-model-id": "zai-glm-5-1", "x-air-id": "zai:glm@5.1", "x-status": "coming-soon", "x-creator": { "id": "zai", "name": "Z.ai", "logo": "https://assets.runware.ai/fa229a51-5cf8-4d1b-be22-a89f9645573c.png" }, "x-capabilities": [ "text-to-text" ], "x-released-at": "2026-04-07T00:00:00Z", "x-cover-image": "https://assets.runware.ai/014ae69a-a188-4879-abf4-d80d9d0ec68c.jpeg" }, "servers": [ { "url": "https://api.runware.ai/v1", "description": "Runware REST API" } ], "components": { "securitySchemes": { "apiKeyAuth": { "type": "http", "scheme": "bearer", "description": "Runware API Key (e.g., Bearer )" } }, "schemas": { "AuthenticationTask": { "title": "Authentication", "description": "Authenticates a connection using an API key. Can be sent as the first element of the request array as an alternative to using the Authorization header.", "type": "object", "x-response-schema": "https://schemas.runware.ai/responses/utilities/authentication.json", "properties": { "taskType": { "const": "authentication", "title": "Task Type", "description": "The type of task to perform." }, "apiKey": { "title": "API Key", "description": "Your Runware API key.", "type": "string" }, "connectionSessionUUID": { "title": "Connection Session UUID", "description": "Optional session UUID to resume a previous connection and receive any buffered results.", "type": "string", "format": "uuid" } }, "required": [ "taskType", "apiKey" ], "additionalProperties": false }, "RequestBody": { "type": "array", "items": { "type": "object", "properties": { "model": { "title": "Model", "description": "Identifier of the model to use for generation.", "type": "string", "const": "zai:glm@5.1" }, "seed": { "title": "Seed", "description": "Random seed for reproducible generation. When not provided, a random seed is generated in the unsigned 32-bit range.", "type": "integer", "minimum": 0, "maximum": 9223372036854776000 }, "settings": { "title": "Settings", "description": "Global inference settings.", "type": "object", "properties": { "systemPrompt": { "title": "System Prompt", "description": "System-level instruction that guides the model's behavior and output style across the entire generation.", "type": "string", "minLength": 1, "maxLength": 200000 }, "temperature": { "title": "Temperature", "description": "Controls randomness in generation. Lower values produce more deterministic outputs, higher values increase variation and creativity.", "type": "number", "multipleOf": 0.01, "minimum": 0, "maximum": 1, "default": 1 }, "topP": { "title": "Top-P", "description": "Nucleus sampling parameter that controls diversity by limiting the probability mass. Lower values make outputs more focused, higher values increase diversity.", "type": "number", "multipleOf": 0.01, "minimum": 0.01, "maximum": 1 }, "frequencyPenalty": { "title": "Frequency Penalty", "description": "Penalizes tokens based on their frequency in the output so far. A value of 0.0 disables the penalty.", "type": "number", "multipleOf": 0.01, "minimum": -2, "maximum": 2 }, "maxTokens": { "title": "Max Tokens", "description": "Maximum number of tokens to generate in the response.", "type": "integer", "minimum": 1, "default": 4096, "maximum": 131072 }, "presencePenalty": { "title": "Presence Penalty", "description": "Encourages the model to introduce new topics. A value of 0.0 disables the penalty.", "type": "number", "multipleOf": 0.01, "minimum": -2, "maximum": 2 }, "stopSequences": { "title": "Stop Sequences", "description": "Array of sequences that will cause the model to stop generating further tokens when encountered.", "type": "array", "items": { "type": "string", "minLength": 1, "maxLength": 50 }, "maxItems": 5 }, "thinkingLevel": { "title": "Thinking Level", "description": "Controls the depth of internal reasoning the model performs before generating a response.", "type": "string", "enum": [ "none", "low", "medium", "high" ], "default": "none" }, "toolChoice": { "title": "Tool Choice", "description": "Controls how the model selects which tool to call.", "type": "object", "properties": { "type": { "title": "Type", "description": "Tool selection strategy.", "type": "string", "oneOf": [ { "const": "auto", "description": "Model decides whether to call a tool." }, { "const": "any", "description": "Model must call at least one tool." }, { "const": "tool", "description": "Model must call the specified tool." }, { "const": "none", "description": "Model must not call any tool." } ] }, "name": { "title": "Name", "description": "Name of the tool to call.", "type": "string" } }, "required": [ "type" ], "additionalProperties": false }, "tools": { "title": "Tools", "description": "Function definitions available for the model to call. Each tool is a JSON Schema object describing the function signature.", "type": "array", "items": { "type": "object", "additionalProperties": false } }, "topK": { "title": "Top-K", "description": "Top-K sampling parameter that limits the number of highest-probability tokens considered at each step.", "type": "integer", "minimum": 1, "maximum": 100647 } }, "additionalProperties": false }, "messages": { "title": "Messages", "description": "Array of chat messages forming the conversation context.", "type": "array", "minItems": 1, "items": { "title": "Message", "description": "A single chat message with a role and content.", "type": "object", "properties": { "role": { "title": "Role", "description": "The role of the message author.", "type": "string", "enum": [ "user", "assistant" ] }, "content": { "title": "Content", "description": "The text content of the message.", "type": "string", "minLength": 1 } }, "required": [ "role", "content" ], "additionalProperties": false } }, "taskType": { "title": "Task Type", "description": "Identifier for the type of task being performed", "type": "string", "const": "textInference" }, "taskUUID": { "title": "Task UUID", "description": "UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task.", "type": "string", "format": "uuid" }, "webhookURL": { "title": "Webhook URL", "description": "Specifies a webhook URL where JSON responses will be sent via HTTP POST when generation tasks complete. For batch requests with multiple results, each completed item triggers a separate webhook call as it becomes available.", "type": "string", "format": "uri" }, "includeCost": { "title": "Include Cost", "description": "Include task cost in the response.", "type": "boolean", "default": false }, "deliveryMethod": { "title": "Delivery Method", "description": "Determines how the API delivers task results.", "type": "string", "oneOf": [ { "const": "sync", "description": "Returns complete results directly in the API response." }, { "const": "async", "description": "Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse." }, { "const": "stream", "description": "Streams results token-by-token as they are generated." } ], "default": "sync" }, "numberResults": { "title": "Number of Results", "description": "Number of results to generate. Each result uses a different seed, producing variations of the same parameters.", "type": "integer", "minimum": 1, "default": 1, "maximum": 4 }, "includeUsage": { "title": "Include Usage", "description": "Include token usage statistics in the response.", "type": "boolean", "default": false } }, "additionalProperties": false, "required": [ "taskType", "taskUUID", "model", "messages" ] }, "description": "You must always POST an array of task objects." }, "ResponseBody": { "type": "object", "properties": { "data": { "type": "array", "items": { "type": "object", "description": "Unknown response structure" } } } }, "ErrorResponse": { "title": "Error Response", "description": "Standard error response returned by the Runware API.", "type": "object", "properties": { "errors": { "type": "array", "items": { "type": "object", "required": [ "code", "message" ], "additionalProperties": true, "properties": { "code": { "type": "string", "description": "A short identifier for the error (e.g., invalidApiKey, timeoutProvider)." }, "message": { "type": "string", "description": "A human-readable explanation of what went wrong." }, "parameter": { "type": "string", "description": "The request parameter related to the error, if applicable." }, "taskType": { "type": "string", "description": "The task type of the request that failed." }, "taskUUID": { "type": "string", "description": "The unique identifier of the failed request." }, "documentation": { "type": "string", "description": "A link to relevant documentation." } } } } }, "required": [ "errors" ], "additionalProperties": false } } }, "paths": { "/": { "post": { "summary": "Run GLM-5.1", "description": "GLM-5.1 is Z.ai’s flagship language model for agentic engineering, coding, reasoning, and tool-driven workflows. It supports a 200K token context window with up to 128K output tokens, deep thinking, function calling, structured output, and streaming tool calls, and is designed to stay effective over long multi-step sessions rather than only short-horizon tasks.", "operationId": "run_zai_glm_5_1", "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/RequestBody" } } } }, "responses": { "200": { "description": "Successful response", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ResponseBody" } } } }, "400": { "description": "Bad Request — Missing or invalid parameters.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } }, "401": { "description": "Unauthorized — No valid API key provided.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } }, "402": { "description": "Payment Required — Insufficient account balance.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } }, "403": { "description": "Forbidden — The API key lacks permissions for this request.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } }, "429": { "description": "Too Many Requests — Rate limit exceeded.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } }, "500": { "description": "Server Error — Something went wrong on Runware's end.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } }, "503": { "description": "Service Unavailable — Temporarily unavailable (maintenance or capacity).", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } } } } } }, "security": [ { "apiKeyAuth": [] } ] }