--- title: 'GLM-5.3-Flash API: Model ID, 1M Context, OpenAI and Anthropic SDKs | RunAPI' description: Call glm-5.3-flash through RunAPI's OpenAI-compatible and Anthropic Messages APIs. 320B MoE with 18B active, 1M-token context, always-on thinking, text input. url: https://runapi.ai/models/glm/5.3-flash.md canonical: https://runapi.ai/models/glm/5.3-flash locale: en site: RunAPI image: https://runapi.ai/assets/opengraph-bfaaa0f0.png alternates: en: https://runapi.ai/models/glm/5.3-flash zh-CN: https://runapi.ai/zh-CN/models/glm/5.3-flash es: https://runapi.ai/es/models/glm/5.3-flash ja: https://runapi.ai/ja/models/glm/5.3-flash de: https://runapi.ai/de/models/glm/5.3-flash fr: https://runapi.ai/fr/models/glm/5.3-flash pt-BR: https://runapi.ai/pt-BR/models/glm/5.3-flash ko: https://runapi.ai/ko/models/glm/5.3-flash it: https://runapi.ai/it/models/glm/5.3-flash nl: https://runapi.ai/nl/models/glm/5.3-flash pl: https://runapi.ai/pl/models/glm/5.3-flash tr: https://runapi.ai/tr/models/glm/5.3-flash zh-TW: https://runapi.ai/zh-TW/models/glm/5.3-flash zh-HK: https://runapi.ai/zh-HK/models/glm/5.3-flash ar: https://runapi.ai/ar/models/glm/5.3-flash x-default: https://runapi.ai/models/glm/5.3-flash model: GLM provider: Z.ai variant_id: glm-5.3-flash sdk_model_id: glm-5.3-flash modality: text billing_unit: 1K tokens status: active --- > HTML version: https://runapi.ai/models/glm/5.3-flash > Site index for agents: https://runapi.ai/llms.txt # glm-5.3-flash API Call glm-5.3-flash from the GLM family through RunAPI. Billing is per token with no subscription, and a request that fails before its response starts is not charged. **Z.ai / [GLM](https://runapi.ai/models/glm.md)** **Operational · text · Commercial OK** ## What GLM-5.3-Flash is built for GLM-5.3-Flash is the lower-cost model of Z.ai's GLM-5.3 generation, released on August 26, 2026. It is a Mixture-of-Experts model with 320B total parameters and 18B active per token. Z.ai describes it as the first open-source frontier model to combine sparse and linear attention, and reports about 3x less attention compute and a 4.4x smaller KV cache than GLM-5.3. The context window is 1M tokens and output goes up to 128K tokens. Thinking is always on: Z.ai's API accepts only the enabled thinking mode, so every reply starts with a reasoning step. Z.ai aims the model at coding user interfaces from screenshots, office documents, financial research, and computer-use loops, and supports function calling and structured output. Z.ai's model also reads images, video, and files. On RunAPI, glm-5.3-flash accepts text input only. Call it through the OpenAI-compatible Chat Completions endpoint (/v1/chat/completions), the Anthropic Messages endpoint (/v1/messages), OpenAI Responses, or Gemini generateContent, all with the same RunAPI API key. **Model ID:** glm-5.3-flash **Released:** August 26, 2026 **Architecture:** MoE, 320B total / 18B active **Context window:** 1M tokens **Max output:** 128K tokens **Thinking:** Always on **Endpoint on RunAPI:** OpenAI Chat Completions and Anthropic Messages, text input ## Try GLM-5.3-Flash Pick any model and generate in seconds. **Model:** - **Chat completion** — `chat_completion` · `glm-5.3-flash` · Input $0.12 / 1M tokens | Output $0.40 / 1M tokens **Prompt:** Describe what you want to create... **Estimated:** Input $0.12 / 1M tokens | Output $0.40 / 1M tokens - [Generate](https://runapi.ai/login) Sign in to generate with RunAPI. ### Switch variant - [glm-4.5](https://runapi.ai/models/glm/4.5.md) - [glm-4.5-air](https://runapi.ai/models/glm/4.5-air.md) - [glm-4.6](https://runapi.ai/models/glm/4.6.md) - [glm-4.7](https://runapi.ai/models/glm/4.7.md) - [glm-5](https://runapi.ai/models/glm/5.md) - [glm-5-turbo](https://runapi.ai/models/glm/5-turbo.md) - [glm-5.1](https://runapi.ai/models/glm/5.1.md) - [glm-5.2](https://runapi.ai/models/glm/5.2.md) - [glm-5.3](https://runapi.ai/models/glm/5.3.md) - **glm-5.3-flash** (current) 10 versions available glm-5.3-flash is one of the GLM models on RunAPI. It uses the same API key as every other model, and you switch to it by changing the model ID in your request. Each call is synchronous and billed in USD by input, output, and cache tokens, with no subscription or minimum spend. A request that fails before the response starts is not charged; once a response is streaming, the tokens already generated are billed, even if the client disconnects. - Per-token billing in USD with no subscription - No charge when a request fails before its response starts - Token-by-token streaming - Switch models by changing one model ID - One API key and one bill for every model and provider ## Technical details | Field | Value | |---|---| | Provider | Z.ai | | Model ID | glm-5.3-flash | | Modality | Text | | Task types | Synchronous | | API endpoint | `/v1/chat/completions` | | | `/v1/responses` | | | `/v1/messages` | | | `/v1beta/models/glm-5.3-flash:generateContent` | | | `/v1beta/models/glm-5.3-flash:streamGenerateContent` | | Billing unit | 1K tokens | | Catalog status | Operational | **HOW IT WORKS** ## Use This Model in 3 Steps 1. **Get Your Key** - Sign up for free and create an API key for glm-5.3-flash from the dashboard. 2. **Send a Request** - POST to /v1/chat/completions with the glm-5.3-flash model slug and your parameters. 3. **Get Results** - Read the completed glm-5.3-flash response directly from the endpoint. ## What this model offers - **Endpoint coverage** — Exposes 1 public endpoint(s): chat_completion. - **Usage-based billing** — Metered by 1K tokens with no subscription requirement. ## GLM-5.3-Flash Pricing | Endpoint | Price | |---|---| | `chat_completion` | Input: $0.12 / 1M tokens
Output: $0.40 / 1M tokens
Cache read: $0.03 / 1M tokens
Cache write 5m: Free / 1M tokens
Cache write 1h: Free / 1M tokens | **API REFERENCE** ## Endpoint Specification | Field | Value | |---|---| | Endpoint | `POST /v1/chat/completions` | | Model ID | `glm-5.3-flash` | | Task Types | `chat_completion` | ## Request parameters No request parameters are published for this endpoint. **Request example** ```json { "model": "glm-5.3-flash", "messages": [ { "role": "user", "content": "Read this multi-file repository, find the failing integration test, and propose a patch with an explanation of the root cause." } ] } ``` ### Model skill — glm-5.3-flash Install the skill once, then use the variant ID from this page while building. Base URL: `https://runapi.ai` | Endpoint | Protocol | |---|---| | `POST /v1/chat/completions` | OpenAI compatible | | `POST /v1/responses` | OpenAI Responses | | `POST /v1/messages` | Anthropic compatible | | `POST /v1beta/models/glm-5.3-flash:generateContent` | Gemini generateContent | | `POST /v1beta/models/glm-5.3-flash:streamGenerateContent` | Gemini streamGenerateContent | Use the OpenAI / Anthropic / Google Gen AI SDK with your RunAPI API key and `model: "glm-5.3-flash"`. ### Use glm-5.3-flash with a model skill 1. **Install** — Install the model skill for the GLM line. It loads docs, request formats, and pricing notes into your coding workspace. 2. **Configure** — Point your SDK at https://runapi.ai and set your RunAPI API key. The same key works for every model and provider. 3. **Call** — Send a request in an API format this model supports, with the model field set to the model ID on this page. RunAPI forwards it to the provider. 4. **Receive** — Read the response from the same call, or stream it as it is generated. The usage field shows the tokens you are billed for. ### What's different about glm-5.3-flash - **VS GLM-4.5: Lower-cost GLM-5.3 tier; 1M context, always-on thinking; text requests through OpenAI and Anthropic SDKs** — 355B / 32B active; 128K context; flagship open-weight MoE baseline - **VS GLM-4.5-AIR: Lower-cost GLM-5.3 tier; 1M context, always-on thinking; text requests through OpenAI and Anthropic SDKs** — Lighter GLM-4.5 tier for fast, lower-cost everyday work - **VS GLM-4.6: Lower-cost GLM-5.3 tier; 1M context, always-on thinking; text requests through OpenAI and Anthropic SDKs** — 200K context; first GLM on Cambricon chips; sharper code generation ## USE CASES **Customer support** Answer customer questions from a private knowledge base, reducing ticket volume. **Document analysis** Draft contract summaries and flag key clauses for attorney review. **Code generation** Auto-generate unit tests, code reviews, and refactoring suggestions in CI. ## Frequently asked questions about GLM-5.3-Flash ### How is GLM-5.3-Flash different from GLM-5.3? GLM-5.3-Flash is the smaller, lower-cost model of the GLM-5.3 generation, with 320B total and 18B active parameters. Its hybrid sparse and linear attention cuts attention compute by about 3x against GLM-5.3, according to Z.ai. Both have a 1M-token context window. Choose glm-5.3 for the flagship model and glm-5.3-flash for high-volume or cost-sensitive work. ### Can I turn thinking off on GLM-5.3-Flash? No. Z.ai ships it with thinking always on, and the thinking setting accepts only enabled. Reasoning tokens count toward the output, so leave room for them in max_tokens. ### Can I send images to glm-5.3-flash on RunAPI? Not yet. Z.ai's model reads images, video, and files, but RunAPI accepts text input only for glm-5.3-flash, and requests with image parts are rejected. ### Which SDKs can call glm-5.3-flash? Point the OpenAI SDK at https://runapi.ai/v1 for Chat Completions or Responses, or use the Anthropic SDK for Messages, and set the model to glm-5.3-flash. One RunAPI API key works for every protocol. ### How do I select glm-5.3-flash? Pass the model ID shown in the quickstart. ### What's the rate limit on this variant? Per-key rate limits scale with your usage tier. The pricing page shows current limits. If you need higher throughput, contact support to discuss tier upgrades. ### Can I switch variants later? Yes. Variant is a parameter in the request. Switch by changing the model ID — no code changes, no re-authentication, no separate billing setup. All variants share the same API key and request shape. ### Does it stream? Where streaming is available, RunAPI streams end-to-end. LLM models support token-level streaming. Media models use async task polling or webhook callbacks for result delivery. ### Where do I report quality issues? Open an issue on the public GitHub repo or email support at contact@runapi.ai. Include the task ID and model ID so the team can investigate the specific generation. ### Do I need a separate provider account? No. Your RunAPI API key is enough to access this variant and every other model in the catalog. You do not need accounts with the underlying provider. ### RELATED - [glm-4.5-air](https://runapi.ai/models/glm/4.5-air.md) — by Z.ai · Input $0.16 / 1M tokens | Output $0.88 / 1M tokens - [glm-4.5](https://runapi.ai/models/glm/4.5.md) — by Z.ai · Input $0.48 / 1M tokens | Output $1.76 / 1M tokens - [glm-4.6](https://runapi.ai/models/glm/4.6.md) — by Z.ai · Input $0.48 / 1M tokens | Output $1.76 / 1M tokens - [glm-4.7](https://runapi.ai/models/glm/4.7.md) — by Z.ai · Input $0.48 / 1M tokens | Output $1.76 / 1M tokens ### Start building with GLM. - [Create free account](https://runapi.ai/login) - [Read the quickstart →](https://runapi.ai/docs/api/openai/chat-completions) ## Building with a team? We're here to help with enterprise setup, integrations, and technical questions. [Contact Us](https://runapi.ai/contact.md) --- ## More from RunAPI - [Home](https://runapi.ai/.md) ### Product - [Model Catalog](https://runapi.ai/models.md) - [Pricing](https://runapi.ai/pricing.md) - [Providers](https://runapi.ai/models#all-models) ### Developers - [Documentation](https://runapi.ai/docs/guides) - [SDKs](https://runapi.ai/sdk.md) - [CLI](https://runapi.ai/cli.md) - [MCP Server](https://runapi.ai/mcp.md) - [x402](https://runapi.ai/x402.md) ### Guides - [Claude Code vs Cursor](https://runapi.ai/claude-code-vs-cursor.md) - [Cursor API Setup](https://runapi.ai/cursor-api-setup.md) - [RunAPI vs OpenRouter](https://runapi.ai/openrouter-alternative.md) ### Company - [Enterprise](https://runapi.ai/contact.md) - [Contact](https://runapi.ai/contact.md) ### Legal - [Terms](https://runapi.ai/terms.md) - [Privacy](https://runapi.ai/privacy.md) - [Site index for agents](https://runapi.ai/llms.txt) Contact: contact@runapi.ai ## Structured data ```json [ { "@context": "https://schema.org", "inLanguage": "en", "@type": "WebSite", "name": "RunAPI", "url": "https://runapi.ai/", "potentialAction": { "@type": "SearchAction", "target": { "@type": "EntryPoint", "urlTemplate": "https://runapi.ai/models?q={search_term_string}" }, "query-input": "required name=search_term_string" } }, { "@context": "https://schema.org", "inLanguage": "en", "@type": "Organization", "name": "RunAPI", "url": "https://runapi.ai/", "logo": { "@type": "ImageObject", "url": "https://runapi.ai/icon.svg" }, "sameAs": [ "https://github.com/runapi-ai" ] }, { "@context": "https://schema.org", "inLanguage": "en", "@type": "SoftwareApplication", "name": "GLM glm-5.3-flash", "applicationCategory": "DeveloperApplication" }, { "@context": "https://schema.org", "inLanguage": "en", "@type": "BreadcrumbList", "itemListElement": [ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://runapi.ai/" }, { "@type": "ListItem", "position": 2, "name": "Models", "item": "https://runapi.ai/models" }, { "@type": "ListItem", "position": 3, "name": "GLM", "item": "https://runapi.ai/models/glm" }, { "@type": "ListItem", "position": 4, "name": "glm-5.3-flash", "item": "https://runapi.ai/models/glm/5.3-flash" } ] }, { "@context": "https://schema.org", "inLanguage": "en", "@type": "HowTo", "name": "Use glm-5.3-flash with a model skill", "description": "Call glm-5.3-flash from the GLM family through RunAPI: per-token pricing, model ID, supported API formats, and setup guide.", "totalTime": "PT5M", "step": [ { "@type": "HowToStep", "position": 1, "name": "Install", "text": "Install the model skill for the GLM line. It loads docs, request formats, and pricing notes into your coding workspace.", "url": "https://runapi.ai/models/glm/5.3-flash#how-step-1" }, { "@type": "HowToStep", "position": 2, "name": "Configure", "text": "Point your SDK at https://runapi.ai and set your RunAPI API key. The same key works for every model and provider.", "url": "https://runapi.ai/models/glm/5.3-flash#how-step-2" }, { "@type": "HowToStep", "position": 3, "name": "Call", "text": "Send a request in an API format this model supports, with the model field set to the model ID on this page. RunAPI forwards it to the provider.", "url": "https://runapi.ai/models/glm/5.3-flash#how-step-3" }, { "@type": "HowToStep", "position": 4, "name": "Receive", "text": "Read the response from the same call, or stream it as it is generated. The usage field shows the tokens you are billed for.", "url": "https://runapi.ai/models/glm/5.3-flash#how-step-4" } ] }, { "@context": "https://schema.org", "inLanguage": "en", "@type": "FAQPage", "mainEntity": [ { "@type": "Question", "name": "How is GLM-5.3-Flash different from GLM-5.3?", "acceptedAnswer": { "@type": "Answer", "text": "GLM-5.3-Flash is the smaller, lower-cost model of the GLM-5.3 generation, with 320B total and 18B active parameters. Its hybrid sparse and linear attention cuts attention compute by about 3x against GLM-5.3, according to Z.ai. Both have a 1M-token context window. Choose glm-5.3 for the flagship model and glm-5.3-flash for high-volume or cost-sensitive work." } }, { "@type": "Question", "name": "Can I turn thinking off on GLM-5.3-Flash?", "acceptedAnswer": { "@type": "Answer", "text": "No. Z.ai ships it with thinking always on, and the thinking setting accepts only enabled. Reasoning tokens count toward the output, so leave room for them in max_tokens." } }, { "@type": "Question", "name": "Can I send images to glm-5.3-flash on RunAPI?", "acceptedAnswer": { "@type": "Answer", "text": "Not yet. Z.ai's model reads images, video, and files, but RunAPI accepts text input only for glm-5.3-flash, and requests with image parts are rejected." } }, { "@type": "Question", "name": "Which SDKs can call glm-5.3-flash?", "acceptedAnswer": { "@type": "Answer", "text": "Point the OpenAI SDK at https://runapi.ai/v1 for Chat Completions or Responses, or use the Anthropic SDK for Messages, and set the model to glm-5.3-flash. One RunAPI API key works for every protocol." } }, { "@type": "Question", "name": "How do I select glm-5.3-flash?", "acceptedAnswer": { "@type": "Answer", "text": "Pass the model ID shown in the quickstart." } }, { "@type": "Question", "name": "What's the rate limit on this variant?", "acceptedAnswer": { "@type": "Answer", "text": "Per-key rate limits scale with your usage tier. The pricing page shows current limits. If you need higher throughput, contact support to discuss tier upgrades." } }, { "@type": "Question", "name": "Can I switch variants later?", "acceptedAnswer": { "@type": "Answer", "text": "Yes. Variant is a parameter in the request. Switch by changing the model ID — no code changes, no re-authentication, no separate billing setup. All variants share the same API key and request shape." } }, { "@type": "Question", "name": "Does it stream?", "acceptedAnswer": { "@type": "Answer", "text": "Where streaming is available, RunAPI streams end-to-end. LLM models support token-level streaming. Media models use async task polling or webhook callbacks for result delivery." } }, { "@type": "Question", "name": "Where do I report quality issues?", "acceptedAnswer": { "@type": "Answer", "text": "Open an issue on the public GitHub repo or email support at contact@runapi.ai. Include the task ID and model ID so the team can investigate the specific generation." } }, { "@type": "Question", "name": "Do I need a separate provider account?", "acceptedAnswer": { "@type": "Answer", "text": "No. Your RunAPI API key is enough to access this variant and every other model in the catalog. You do not need accounts with the underlying provider." } } ] } ] ```