What is the difference between GLM-4.7, GLM-4.7-Flash, and GLM-4.7-FlashX?

GLM-4.7 is the full-scale variant with maximum capability. GLM-4.7-Flash is optimized for faster inference with reduced capability. GLM-4.7-FlashX provides the fastest inference tier in the generation. All share the same API surface.

Is GLM 4.7 good for frontend development?

Yes. Z.AI cites improved frontend development results as a key change in this model generation.

How do I authenticate with GLM 4.7 through AI Gateway?

AI Gateway provides a unified API key. Configure it in your environment and use the model identifier to route requests. No separate Z.AI account is required, though BYOK is also supported.

How does GLM 4.7 handle multi-step agentic tasks?

Multi-step reasoning is a core improvement in this generation. The model maintains better coherence across extended tool-use sequences and planning steps compared to earlier GLM models.

What providers serve GLM 4.7 through AI Gateway?

GLM 4.7 is available through Z.AI, Novita AI, DeepInfra, Bedrock, Baseten. AI Gateway handles routing and automatic retries across providers.

Z.AI

GLM 4.7

GLM 4.7 is Z.AI's model released December 22, 2025 with major improvements in coding, tool usage, and multi-step reasoning. It uses a more natural conversational tone and shows improved frontend development results. Your use is subject to Z.AI's Terms & Privacy Policies.

View API reference

Input and output price: Prices from: Input $0.40, Output $1.75, Per 1M tokens
24h uptime: Loading AI Gateway uptime

Get API key Read the docs

import { streamText } from 'ai'

const result = streamText({
  model: 'zai/glm-4.7',
  prompt: 'Why is the sky blue?'
})

Read docs

Overview Playground Providers Uptime Status Throughput Latency API Similar About FAQ

Copy link to headingPlayground

Try out GLM 4.7 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 4.7

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.

Checking availability for your team

Provider

Context	Max Output	Latency	Throughput	Input	Output	Cache	Web Search	Capabilities	ZDR	No Training	Regional Inference	Free Tier	Release Date

Z.AI

Legal:Terms•Privacy

200K

120K

4.2 s

59 tps

$0.60/M

$2.20/M

Read$0.11/M

—

12/22/2025

Novita AI

Legal:Terms•Privacy

205K

131K

3.6 s

51 tps

$0.60/M

$2.20/M

Read$0.11/M

—

12/22/2025

DeepInfra

Legal:Terms•Privacy

203K

120K

1.0 s

14 tps

$0.40/M

$1.75/M

Read$0.08/M

—

12/22/2025

Bedrock

Legal:Terms•Privacy

200K

120K

0.1 s

113 tps

$0.60/M

$2.20/M

—

12/22/2025

Going away Sep 26, 2026

Baseten

Legal:Terms•Privacy

200K

120K

0.5 s

112 tps

$0.60/M

$2.20/M

Read$0.12/M

—

12/22/2025

Getting started

Call GLM 4.7 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.

index.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'zai/glm-4.7',
    prompt: 'Why is the sky blue?',
  });

  console.log(result.text);
}

main().catch(console.error);

Top-level parameters

The same GLM 4.7 request in each API format AI Gateway supports.

top-level-params.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'zai/glm-4.7',
    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-4.7`. AI Gateway routes the request to an available provider.
`maxOutputTokens`	`number`	No	Hard cap on generated tokens. GLM 4.7 supports up to `131,072` 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.

provider-options.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'zai/glm-4.7',
    prompt: 'Why is the sky blue?',
    providerOptions: {
      gateway: {
        only: ['zai', 'novita'],
      },
    },
  });

  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.

reasoning.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'zai/glm-4.7',
    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.

tool-calling.ts

import { generateText, tool } from 'ai';
import { z } from 'zod';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'zai/glm-4.7',
    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

Context	Latency	Throughput	Input	Output	Cache	Web Search	Capabilities	Providers	ZDR	No Training	Free Tier	Release Date

zai/glm-5.3-flashx

2.9 s

149 tps

$0.37/M

$1.25/M

Read$0.08/M

—

09/18/2026

zai/glm-5.3-flash

0.7 s

120 tps

$0.08/M

$0.25/M

Read$0.01/M

—

+17

08/26/2026

zai/glm-5.3

0.1 s

232 tps

$0.70/M+1 more

$2.20/M+1 more

Read$0.12/M

—

+17

08/18/2026

zai/glm-5.2-fast

0.3 s

481 tps

$2.10/M

$6.60/M

Read$0.21/M

—

06/23/2026

zai/glm-5.2

0.2 s

411 tps

$0.49/M+1 more

$1.56/M+1 more

Read$0.09/M

—

+14

06/16/2026

zai/glm-5.1

205K

1.5 s

54 tps

$1.05/M

$3.50/M

Read$0.21/M

—

04/07/2026

Copy link to headingAbout GLM 4.7

GLM 4.7 was released December 22, 2025 as a capability upgrade in Z.AI's model lineup. It brings major improvements in coding, tool usage, and multi-step reasoning, with added focus on complex agentic tasks that require sustained planning across multiple steps.

The model introduces a more natural conversational tone compared to earlier GLM generations. This improves the experience in chat-based applications and interactive coding assistants. GLM 4.7 shows improved frontend development results for teams building UI components, web applications, and design-to-code workflows.

GLM 4.7 operates within a context window of 204.8K tokens and is available through AI Gateway with the standard unified API, built-in observability, and intelligent provider routing. It represents the full-scale offering in the 4.7 generation, complemented by GLM-4.7-Flash and GLM-4.7-FlashX for speed-optimized workloads.

Copy link to headingWhat To Consider When Choosing a Provider

Configuration: GLM 4.7 targets frontend tasks. If your workload involves generating React components, CSS, or converting designs to code, benchmark it against general-purpose alternatives you already use.
Configuration: The 4.7 generation includes three tiers. GLM 4.7 provides maximum capability, GLM-4.7-Flash offers speed optimization, and GLM-4.7-FlashX provides the fastest inference. Choose based on your latency-capability tradeoff.
Configuration: Multi-step reasoning updates make GLM 4.7 more reliable for agentic pipelines. Test it against your existing agent benchmarks to quantify the improvement over GLM-4.6.
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 4.7

Best for

Frontend development: HTML, CSS, React components, and design-to-code conversion benefit from the targeted improvements
Complex agentic tasks: Multi-step reasoning, tool usage, and sustained planning across extended interactions
Interactive coding assistants: The natural conversational tone improves developer experience
Full-stack code generation: Improvements in both coding capability and tool usage apply across the stack
Production applications: The highest capability tier in the GLM-4.7 generation, paired with AI Gateway observability

Consider alternatives when

Latency-driven workloads: GLM-4.7-Flash or GLM-4.7-FlashX provides faster inference at reduced capability
Vision capabilities needed: Evaluate GLM-4.6V or GLM-4.5V for multimodal visual input
Advanced reasoning beyond 4.7: GLM-5 introduces multiple thinking modes and improved long-range planning
Cost-efficiency priority: The flash variants in the 4.7 generation or GLM-4.5-Air may be more economical when peak capability is not essential

Copy link to headingConclusion

GLM 4.7 advances Z.AI's model lineup with targeted improvements in the areas that matter most for modern development workflows: coding, tool usage, multi-step reasoning, and frontend generation. As the full-scale 4.7 model, it sets the capability ceiling for the generation while GLM-4.7-Flash and FlashX variants serve speed-sensitive workloads.

Copy link to headingFrequently Asked Questions

What are the main improvements in GLM 4.7 over previous GLM models?
Coding, tool usage, and multi-step reasoning. It also uses a more natural conversational tone and shows improved frontend development results in this generation.
What is the difference between GLM-4.7, GLM-4.7-Flash, and GLM-4.7-FlashX?
GLM-4.7 is the full-scale variant with maximum capability. GLM-4.7-Flash is optimized for faster inference with reduced capability. GLM-4.7-FlashX provides the fastest inference tier in the generation. All share the same API surface.
Is GLM 4.7 good for frontend development?
Yes. Z.AI cites improved frontend development results as a key change in this model generation.
What is the context window for GLM 4.7?
204.8K tokens.
How do I authenticate with GLM 4.7 through AI Gateway?
AI Gateway provides a unified API key. Configure it in your environment and use the model identifier to route requests. No separate Z.AI account is required, though BYOK is also supported.
How does GLM 4.7 handle multi-step agentic tasks?
Multi-step reasoning is a core improvement in this generation. The model maintains better coherence across extended tool-use sequences and planning steps compared to earlier GLM models.
What providers serve GLM 4.7 through AI Gateway?
GLM 4.7 is available through Z.AI, Novita AI, DeepInfra, Bedrock, Baseten. AI Gateway handles routing and automatic retries across providers.

GLM 4.7

Copy link to headingPlayground

Copy link to headingProviders

Copy link to headingUptime24 hours

Copy link to headingThroughput24 hours

Copy link to headingLatency24 hours

Getting started

Top-level parameters

Input limits

Provider options

Routing across providers

Reasoning

Tool calling

Copy link to headingMore models by Z.AI

Copy link to headingAbout GLM 4.7

Copy link to headingWhat To Consider When Choosing a Provider

Copy link to headingWhen to Use GLM 4.7

Best for

Consider alternatives when

Copy link to headingConclusion

Copy link to headingFrequently Asked Questions