GLM 4.6
GLM 4.6 is Z.AI's coding-focused model released September 30, 2025, with enhanced performance on both benchmarks and real-world programming tasks. It features an expanded context window of 204.8K tokens for handling large codebases and complex agent workflows.
View API reference- Input and output price
- Prices from: Input $0.50, Output $2, Per 1M tokens
- 24h uptime
- Loading AI Gateway uptime
import { streamText } from 'ai'
const result = streamText({ model: 'zai/glm-4.6', prompt: 'Why is the sky blue?'})Copy link to headingPlayground
Try out GLM 4.6 by Z.AI. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days.
GLM 4.6
GLM 4.6
Copy link to headingProviders
Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.
Copy link to headingUptime24 hours
Direct request success rate on AI Gateway and per-provider. Visit the docs for more info.
Copy link to headingThroughput24 hours
P50 throughput on live AI Gateway traffic, in tokens per second (TPS). Visit the docs for more info.
Copy link to headingLatency24 hours
P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds. View the docs for more info.
Getting started
Call GLM 4.6 through AI Gateway with the AI SDK generateText and streamText functions, or through the OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages APIs by changing the base URL. AI Gateway authenticates the request and routes it to an available provider.
Install the AI SDK (pnpm add ai dotenv), create an API key from the API Keys page, and set it as AI_GATEWAY_API_KEY in your environment. Full setup is covered in the text generation quickstart.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'zai/glm-4.6', prompt: 'Why is the sky blue?', });
console.log(result.text);}
main().catch(console.error);Top-level parameters
The same GLM 4.6 request in each API format AI Gateway supports.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'zai/glm-4.6', system: 'You are a concise technical assistant.', prompt: 'Summarize the tradeoffs between static generation and SSR.', maxOutputTokens: 1024, });
console.log(result.text);}
main().catch(console.error);Standard parameters like prompt, messages, temperature, and tools work as documented in the AI SDK docs. These are the parameters with model-specific behavior.
| Parameter | Type | Required | Description |
|---|---|---|---|
model | string | Yes | Model ID in the form creator/model, e.g. zai/glm-4.6. AI Gateway routes the request to an available provider. |
maxOutputTokens | number | No | Hard cap on generated tokens. GLM 4.6 supports up to 202,752 output tokens. Reasoning tokens count toward this limit. |
reasoning | 'provider-default' | 'none' | 'minimal' | 'low' | 'medium' | 'high' | 'xhigh' | No | Provider-agnostic reasoning effort, available in AI SDK 7 or later. Maps to the provider’s native reasoning configuration; reasoning settings under providerOptions take precedence when both are set. See the Reasoning section below. |
providerOptions | Record<string, JSONValue> | No | AI Gateway routing options under gateway, plus any provider-native options under the provider’s own namespace — see the table below. |
Input limits
| Input | Formats | Sources | Max count | Max size | Limits |
|---|---|---|---|---|---|
| Text | — | — | — | — | Prompt and response share the 205K-token context window |
Provider options
Set AI Gateway routing options under providerOptions.gateway. For provider-specific options, pass them under the provider’s namespace as documented by the AI SDK.
Learn more in the AI SDK provider docs.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'zai/glm-4.6', prompt: 'Why is the sky blue?', providerOptions: { gateway: { only: ['zai', 'deepinfra'], }, }, });
console.log(result.text);}
main().catch(console.error);These AI Gateway routing options apply to every model. Provider-specific options pass through under the provider’s own namespace (for example providerOptions.anthropic) exactly as documented by the AI SDK.
| Parameter | Type | Required | Description |
|---|---|---|---|
providerOptions.gateway.only | string[] | No | Restrict routing to these provider slugs. Requests fail over only within the listed providers. |
providerOptions.gateway.order | string[] | No | Preferred provider order. Listed providers are tried first; unlisted providers remain available as fallbacks. |
providerOptions.gateway.sort | 'cost' | 'ttft' | 'tps' | No | Rank candidate providers by price, time to first token, or tokens per second instead of the default routing order. |
providerOptions.gateway.zeroDataRetention | boolean | No | Route only to providers with a zero-data-retention policy for this model. |
Routing across providers
AI Gateway serves the same model through multiple providers and fails over automatically. order expresses a preference while keeping every provider eligible; only is a hard allowlist — if none of the listed providers are available the request fails instead of falling back.
Options under a provider's own namespace (for example providerOptions.anthropic) are forwarded to that provider with the request. Providers ignore option namespaces that don't apply to them, so it is safe to set provider options alongside gateway routing options.
Reasoning
AI Gateway bridges reasoning across every API format. The AI SDK exposes a provider-agnostic top-level reasoning level (none, minimal, low, medium, high, or xhigh); the Chat Completions and Responses formats take the same effort under reasoning.effort; and the Anthropic Messages format uses a native thinking token budget. Whichever you send, the gateway maps it to the target model’s native configuration, converting between effort levels and token budgets as needed. Reasoning-related settings under providerOptions take full precedence over the top-level reasoning value and are never merged. Reasoning tokens typically count toward your output-token usage, though how they’re reported and billed varies by provider.
Learn more in the AI Gateway reasoning guide.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'zai/glm-4.6', prompt: 'Explain the Monty Hall problem step by step.', reasoning: 'high', });
console.log(result.text);}
main().catch(console.error);Tool calling
Expose tools the model can call. Define each tool’s inputs with a Zod schema.
import { generateText, tool } from 'ai';import { z } from 'zod';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'zai/glm-4.6', prompt: 'What is the weather in San Francisco?', tools: { getWeather: tool({ description: 'Get the current weather for a location', inputSchema: z.object({ location: z.string() }), execute: async ({ location }) => ({ location, temperatureC: 18 }), }), }, });
console.log(result.text);}
main().catch(console.error);Copy link to headingMore models by Z.AI
| Model |
|---|
| 1M | 0.4 s | 159 tps | $0.07/M | $0.24/M | Read$0.01/M | — | +1 |    +15 | 08/26/2026 | |||||
| 1M | 0.2 s | 315 tps | $0.70/M+1 more | $2.20/M+1 more | Read$0.12/M | — |   +15 | 08/18/2026 | ||||||
| 1M | 0.5 s | 172 tps | $2.10/M | $6.60/M | Read$0.21/M | — |   | 06/23/2026 | ||||||
| 1M | 0.2 s | 412 tps | $0.70/M+1 more | $2.20/M+1 more | Read$0.11/M | — | +15 | 06/16/2026 | ||||||
| 205K | 1.4 s | 69 tps | $1.40/M | $4.40/M | Read$0.26/M | — |  | 04/07/2026 | ||||||
| 203K | 0.6 s | 124 tps | $1/M | $3.20/M | Read$0.20/M | — |  | 02/12/2026 |
Copy link to headingAbout GLM 4.6
GLM 4.6 was released September 30, 2025 as Z.AI's dedicated coding model. It builds on the GLM-4.5 foundation with targeted improvements for software engineering workflows, benchmark performance, and real-world programming tasks.
The key architectural change is an expanded context window of 204.8K tokens. You can process entire codebases, long specification documents, and multi-file analysis in a single request. This benefits code generation tasks that require understanding cross-file relationships, and agentic coding workflows that maintain state across extended interactions.
GLM 4.6 shows enhanced performance on both public benchmarks and real-world programming tasks. Benchmark scores predict capability, but real-world coding involves ambiguous requirements, legacy code patterns, and iterative refinement. GLM 4.6 targets both dimensions.
Copy link to headingWhat To Consider When Choosing a Provider
- Configuration: The context window of 204.8K tokens handles large codebases in a single pass. Structure your prompts to include relevant file context rather than relying on the model to infer missing dependencies.
- Configuration: GLM 4.6 is optimized for code generation and understanding. For general reasoning or conversational tasks, GLM-4.5 may provide a more balanced profile.
- Configuration: Coding tasks with large context inputs consume many tokens. Monitor usage through AI Gateway's built-in observability to track actual costs against estimates.
- Zero Data Retention: Zero Data Retention is available for this model. It is offered on a per-provider and model basis. See the documentation for details.
- Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.
Copy link to headingWhen to Use GLM 4.6
Best for
- Software engineering workflows: Code generation, debugging, refactoring, and code review across large repositories
- Agentic coding tasks: Extended context and multi-step planning improve the quality of generated solutions
- Large codebase analysis: The context window of 204.8K tokens fits cross-file dependencies and architectural patterns
- Code migration and modernization: Understanding legacy patterns and generating updated code requires broad context
- Technical documentation generation: Codebases where the model must read and synthesize large amounts of source code
Consider alternatives when
- General-purpose workloads: GLM-4.5 provides broader capability without the coding specialization for reasoning or conversation
- Vision-enabled coding: GLM-4.6V combines vision input with coding capability for code-from-screenshot workflows
- Faster inference priority: GLM-4.6V-Flash offers vision and coding at reduced latency when speed matters more than depth
- Advanced coding improvements: GLM-4.7 includes further advancements in tool usage and multi-step reasoning for complex agentic tasks
Copy link to headingConclusion
GLM 4.6 targets the coding workload specifically, combining an expanded context window of 204.8K tokens with improvements in both benchmark and real-world programming performance. For teams building coding assistants, automated code review pipelines, or agentic development tools, it provides a focused alternative to general-purpose models.
Copy link to headingFrequently Asked Questions
What makes GLM 4.6 different from GLM-4.5?
GLM 4.6 is specifically optimized for coding tasks with an expanded context window of 204.8K tokens and targeted improvements in programming benchmark and real-world coding performance. GLM-4.5 is the general-purpose model.
What is the context window for GLM 4.6?
204.8K tokens, designed to handle large codebases, long specification documents, and multi-file analysis in a single request.
Can GLM 4.6 handle multi-file code analysis?
Yes. The expanded context window lets you include multiple files in a single request, enabling the model to understand cross-file dependencies, imports, and architectural patterns.
How do I authenticate with GLM 4.6 through AI Gateway?
AI Gateway provides a unified API key. Configure it in your environment and specify the model identifier. No separate Z.AI account is required, though BYOK is supported.
How does GLM 4.6 compare to GLM-4.7 for coding?
GLM 4.6 introduced the coding-focused improvements in the GLM lineup. GLM-4.7 adds further gains in tool usage, multi-step reasoning, and frontend development, per Z.AI's release notes.
Is GLM 4.6 suitable for non-coding tasks?
GLM 4.6 retains general language capability but is optimized for code. For conversational, reasoning, or general-purpose tasks, GLM-4.5 or GLM-5 may be more appropriate.
What is the pricing for GLM 4.6?
Pricing appears on this page and updates as providers adjust their rates. AI Gateway routes traffic through the configured provider.