GLM 4.7 FlashX
GLM 4.7 FlashX is the ultra-fast inference variant in Z.AI's GLM-4.7 generation, released January 19, 2026. Designed for the lowest latency workloads, it provides the fastest response times in the GLM-4.7 family while retaining core coding and reasoning capabilities.
View API reference- Input and output price
- Input $0.06, Output $0.40, Per 1M tokens
- 24h uptime
- Loading AI Gateway uptime
import { streamText } from 'ai'
const result = streamText({ model: 'zai/glm-4.7-flashx', prompt: 'Why is the sky blue?'})Copy link to headingPlayground
Try out GLM 4.7 FlashX 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 FlashX
GLM 4.7 FlashX
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 4.7 FlashX 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-4.7-flashx', prompt: 'Why is the sky blue?', });
console.log(result.text);}
main().catch(console.error);Top-level parameters
The same GLM 4.7 FlashX 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-4.7-flashx', 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-flashx. AI Gateway routes the request to an available provider. |
maxOutputTokens | number | No | Hard cap on generated tokens. GLM 4.7 FlashX supports up to 128,000 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 200K-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-4.7-flashx', prompt: 'Why is the sky blue?', providerOptions: { gateway: { only: ['zai'], }, }, });
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-4.7-flashx', 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-4.7-flashx', 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 | 213 tps | $0.70/M | $2.20/M | Read$0.13/M | — |  | 09/02/2026 | ||||||
| 1M | 0.3 s | 116 tps | $0.07/M | $0.24/M | Read$0.01/M | — | +1 |   +15 | 08/26/2026 | |||||
| 1M | 0.2 s | 421 tps | $0.70/M+1 more | $2.20/M+1 more | Read$0.12/M | — |   +15 | 08/18/2026 | ||||||
| 1M | 0.5 s | 233 tps | $2.10/M | $6.60/M | Read$0.21/M | — |   | 06/23/2026 | ||||||
| 1M | 0.2 s | 553 tps | $0.70/M+1 more | $2.20/M+1 more | Read$0.11/M | — | +15 | 06/16/2026 | ||||||
| 203K | 1.1 s | 180 tps | $1/M | $3.20/M | Read$0.20/M | — |   | 02/12/2026 |
Copy link to headingAbout GLM 4.7 FlashX
GLM 4.7 FlashX was released January 19, 2026 as the fastest inference tier in Z.AI's GLM-4.7 generation. It targets workloads where response latency is the dominant constraint: real-time user-facing applications, high-frequency API calls, and pipeline steps that block downstream processing.
As the most aggressively speed-optimized variant in the 4.7 family, GLM 4.7 FlashX makes the largest capability tradeoff compared to the full GLM-4.7. It retains the generation's core improvements in coding, reasoning, and conversational tone, but peak performance on the most complex tasks will be lower. The tradeoff is intentional: for the majority of production requests that don't require maximum reasoning depth, GLM 4.7 FlashX delivers adequate quality at the lowest possible latency.
The model shares the same API surface as GLM-4.7 and GLM-4.7-Flash, enabling seamless tier switching. Teams can route simple requests to GLM 4.7 FlashX and complex ones to GLM-4.7, optimizing both cost and quality across their request distribution.
Copy link to headingWhat To Consider When Choosing a Provider
- Configuration: GLM 4.7 FlashX is the right choice when response time is the binding constraint. If quality on complex tasks matters more, step up to GLM-4.7-Flash or GLM-4.7.
- Configuration: Use AI Gateway to route requests by complexity. Simple extraction, classification, and short generation tasks perform well on GLM 4.7 FlashX. Route complex reasoning to higher-tier models.
- Configuration: At the lowest per-token cost in the 4.7 generation, GLM 4.7 FlashX is the most economical option for workloads measured in millions of daily requests.
- Zero Data Retention: Zero Data Retention 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 FlashX
Best for
- Real-time user-facing applications: Sub-second response times are required for acceptable user experience
- High-frequency API endpoints: Thousands of requests per minute where latency compounds into throughput bottlenecks
- Simple extraction and classification: Tasks that need language understanding without deep reasoning
- Pipeline preprocessing steps: Steps that block downstream processing benefit from the fastest possible completion
- Cost-optimized batch processing: Extreme volume where per-token cost is the primary economic driver
Consider alternatives when
- Complex reasoning quality: GLM-4.7 or GLM-4.7-Flash provides deeper capability for multi-step planning
- Balanced speed and capability: GLM-4.7-Flash offers a middle ground in the 4.7 generation
- Speed-optimized vision: Evaluate GLM-4.6V-Flash for multimodal processing when vision is needed
- Advanced thinking modes: GLM-5 provides multiple thinking modes and an expanded reasoning architecture
Copy link to headingConclusion
GLM 4.7 FlashX occupies the speed extreme of Z.AI's GLM-4.7 generation. For teams that measure success in milliseconds and process requests at massive scale, it provides the lowest-latency entry point to the 4.7 generation's improvements in coding, reasoning, and conversational quality.
Copy link to headingFrequently Asked Questions
How fast is GLM 4.7 FlashX compared to other GLM-4.7 variants?
GLM 4.7 FlashX is the fastest inference tier in the GLM-4.7 generation. It provides the lowest latency, followed by GLM-4.7-Flash, then the full GLM-4.7.
What capability tradeoffs does GLM 4.7 FlashX make?
It trades peak reasoning and coding depth for speed. Core capabilities are retained, but the most complex multi-step reasoning and code generation tasks will produce better results on GLM-4.7 or GLM-4.7-Flash.
Can I mix GLM 4.7 FlashX with other GLM-4.7 models?
Yes. All GLM-4.7 variants share the same API surface. Route simple requests to GLM 4.7 FlashX for speed and complex ones to GLM-4.7 for quality.
What is the context window for GLM 4.7 FlashX?
200K tokens.
How do I authenticate with GLM 4.7 FlashX through AI Gateway?
AI Gateway provides a unified API key. No separate Z.AI account is needed. Use the model identifier to route requests. BYOK is also supported.
What workloads is GLM 4.7 FlashX best for?
Real-time user-facing applications, high-frequency API calls, simple classification and extraction, and any workload where response latency is the primary constraint.
How does pricing compare to other GLM-4.7 variants?
Check the pricing panel on this page for today's numbers. AI Gateway tracks rates across every provider that serves GLM 4.7 FlashX.