---
title: GLM API — Variants, pricing & model skill | RunAPI
description: Compare GLM API variants, pricing, and the GLM skill for app development. One API key, skills-first workflow.
url: https://runapi.ai/models/glm.md
canonical: https://runapi.ai/models/glm
locale: en
site: RunAPI
image: https://runapi.ai/assets/opengraph-bfaaa0f0.png
alternates:
  en: https://runapi.ai/models/glm
  zh-CN: https://runapi.ai/zh-CN/models/glm
  es: https://runapi.ai/es/models/glm
  ja: https://runapi.ai/ja/models/glm
  de: https://runapi.ai/de/models/glm
  fr: https://runapi.ai/fr/models/glm
  pt-BR: https://runapi.ai/pt-BR/models/glm
  ko: https://runapi.ai/ko/models/glm
  it: https://runapi.ai/it/models/glm
  nl: https://runapi.ai/nl/models/glm
  pl: https://runapi.ai/pl/models/glm
  tr: https://runapi.ai/tr/models/glm
  zh-TW: https://runapi.ai/zh-TW/models/glm
  zh-HK: https://runapi.ai/zh-HK/models/glm
  ar: https://runapi.ai/ar/models/glm
  x-default: https://runapi.ai/models/glm
model: GLM
provider: Z.ai
modality: text
variant_count: 10
---

> HTML version: https://runapi.ai/models/glm
> Site index for agents: https://runapi.ai/llms.txt

[Home](https://runapi.ai/.md) / [Models](https://runapi.ai/models.md) / GLM


# GLM API

Z.ai GLM API access via RunAPI — MIT-licensed MoE models with up to 200K context, leading open-weight coding benchmarks.

- [Try in playground](https://runapi.ai/login)
- [API reference →](https://runapi.ai/docs/api/openai/chat-completions)

**Provider:** Z.ai
**Modality:** Text
**Catalog:** 10 variants

## About GLM

GLM is Z.ai's family of MIT-licensed Mixture-of-Experts language models. GLM-4.5 (355B total / 32B active, 128K context) introduced the open-weight MoE line with a flagship and a lighter Air tier. GLM-4.6 and 4.7 extend to 200K context with stronger code generation — 4.7 reaches 73.8% on SWE-bench. The GLM-5 series (744B / 40B active, 200K context) pushes further to 77.8% SWE-bench Verified, and GLM-5.1 holds the top open-weight score on SWE-bench Pro at 58.4%. All are available through RunAPI with one key and per-token billing.

**Provider:** Z.ai
**Modality:** Text

## GLM API endpoints

| Endpoint | Protocol |
|---|---|
| `POST /v1/chat/completions` | OpenAI compatible |
| `POST /v1/responses` | OpenAI Responses |
| `POST /v1/messages` | Anthropic compatible |
| `POST /v1beta/models/{model}:generateContent` | Gemini generateContent |
| `POST /v1beta/models/{model}:streamGenerateContent` | Gemini streamGenerateContent |


## Available Versions

| Version | Variant | Pricing | Billing | URL |
|---|---|---|---|---|
| glm-4.5 | `glm-4.5` | Input $0.48 / 1M tokens | Output $1.76 / 1M tokens | 1M tokens | [View →](https://runapi.ai/models/glm/4.5.md) |
| glm-4.5-air | `glm-4.5-air` | Input $0.16 / 1M tokens | Output $0.88 / 1M tokens | 1M tokens | [View →](https://runapi.ai/models/glm/4.5-air.md) |
| glm-4.6 | `glm-4.6` | Input $0.48 / 1M tokens | Output $1.76 / 1M tokens | 1M tokens | [View →](https://runapi.ai/models/glm/4.6.md) |
| glm-4.7 | `glm-4.7` | Input $0.48 / 1M tokens | Output $1.76 / 1M tokens | 1M tokens | [View →](https://runapi.ai/models/glm/4.7.md) |
| glm-5 | `glm-5` | Input $0.80 / 1M tokens | Output $2.56 / 1M tokens | 1M tokens | [View →](https://runapi.ai/models/glm/5.md) |
| glm-5-turbo | `glm-5-turbo` | Input $0.96 / 1M tokens | Output $3.20 / 1M tokens | 1M tokens | [View →](https://runapi.ai/models/glm/5-turbo.md) |
| glm-5.1 | `glm-5.1` | Input $1.12 / 1M tokens | Output $3.52 / 1M tokens | 1M tokens | [View →](https://runapi.ai/models/glm/5.1.md) |
| glm-5.2 | `glm-5.2` | Input $1.12 / 1M tokens | Output $3.52 / 1M tokens | 1M tokens | [View →](https://runapi.ai/models/glm/5.2.md) |
| glm-5.3 | `glm-5.3` | Input $1.12 / 1M tokens | Output $3.52 / 1M tokens | 1M tokens | [View →](https://runapi.ai/models/glm/5.3.md) |
| glm-5.3-flash | `glm-5.3-flash` | Input $0.12 / 1M tokens | Output $0.40 / 1M tokens | 1M tokens | [View →](https://runapi.ai/models/glm/5.3-flash.md) |


## GLM Pricing

| Endpoint | Resolution | Duration | Price |  |
|---|---|---|---|---|
| `chat_completion` | — | — | Input $0.48 / 1M tokens | Output $1.76 / 1M tokens |  |

Prices shown for glm-4.5. Other variants retain their own endpoint pricing.




## Run GLM From an Agent

- [OpenClaw](https://runapi.ai/openclaw-glm.md) — Use GLM with OpenClaw agent — the RunAPI tool exposes callable actions with automatic task polling.
- [Hermes Agent](https://runapi.ai/hermes-glm.md) — Use GLM with Hermes agent — describe what you need in natural language and Hermes picks the right settings.


## Get Started with GLM

1. **Create an API key** — Sign up and generate an API key from the dashboard.
2. **Pick a version** — Choose the version that best matches your quality and cost requirements.
3. **Send a request** — Submit your prompt and parameters to the model's documented endpoint.
4. **Get your result** — Poll the task or set a webhook, then download the completed output.



## About GLM on RunAPI

GLM models from Z.ai are MIT-licensed MoE LLMs spanning 128K–200K context. GLM-5.1 leads open-weight models on SWE-bench Pro. Through RunAPI they share a single API key with pay-as-you-go token billing, callable from the OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages surfaces.

**Provider:** [Z.ai](https://runapi.ai/providers/z-ai.md) — See all →
**Modality:** [Text](https://runapi.ai/models#all-models) — Browse models →



## Why Use GLM Through RunAPI

- **One auth, every provider** — A single RunAPI API key unlocks the whole model catalog across all providers. No separate accounts to create, no API keys to rotate per integration, and no credential management overhead. Add a new model to your app by changing one parameter.
- **Unified pricing & billing** — Per-call pricing in USD, billed monthly into a single invoice. No subscription tiers, no minimum spend, and failed generations are never charged. The pricing page and check_pricing API show exact costs before you commit to a model.
- **Schema-first SDK** — Typed schemas, parameter constraints, and setup notes are packaged in the model skill so your implementation starts from the right contract. The skill loads into Claude Code, Codex, Gemini CLI, Cursor, and VS Code — your agent knows the correct request shape before you write a line of code.


## GLM Questions

### What are the GLM models good at?

Coding and agentic tool use. GLM-5.1 leads open-weight models on SWE-bench Pro (58.4%) and scores 95.3% on AIME 2026. The full line is strong at multi-step tool calling, code generation across large codebases, and mathematical reasoning.

### What is the difference between glm-4.5 and glm-4.5-air?

glm-4.5 is the 355B flagship (32B active parameters) with 128K context; glm-4.5-air is a lighter 106B MoE (12B active) for faster, lower-cost everyday work.

### How does GLM-5 compare to GLM-4.7?

GLM-5 scales to 744B total / 40B active with 256 experts, versus GLM-4.7's 358B / 32B. SWE-bench Verified jumps from 73.8% to 77.8%. Both share 200K context.

### Which SDKs can call GLM through RunAPI?

Point the OpenAI SDK (Chat Completions or Responses) or the Anthropic Messages SDK at RunAPI and pass the GLM model id; the proxy adapts the protocol for you.

### How is GLM billed?

Per token, pay-as-you-go, at RunAPI's published input and output rates for each GLM model — no subscription.

### Which variant should I start with?

Pick the cheapest variant that meets your quality bar. Most teams start on the fast variant and graduate to pro for production.



## Similar Text Models

- [Claude](https://runapi.ai/models/claude.md) - Anthropic - from $0.08 / 1M tokens
- [DeepSeek](https://runapi.ai/models/deepseek.md) - DeepSeek - from $0.30 / 1M tokens
- [Embedding](https://runapi.ai/models/embedding.md) - OpenAI - from $0.02 / 1M tokens
- [Gemini](https://runapi.ai/models/gemini.md) - Google - from $0.10 / 1M tokens


## Start generating with GLM

- [Create free account](https://runapi.ai/login)
- [Read the quickstart →](https://runapi.ai/docs/api/openai/chat-completions)

## Variants

- [GLM glm-4.5](https://runapi.ai/models/glm/4.5.md)
- [GLM glm-4.5-air](https://runapi.ai/models/glm/4.5-air.md)
- [GLM glm-4.6](https://runapi.ai/models/glm/4.6.md)
- [GLM glm-4.7](https://runapi.ai/models/glm/4.7.md)
- [GLM glm-5](https://runapi.ai/models/glm/5.md)
- [GLM glm-5-turbo](https://runapi.ai/models/glm/5-turbo.md)
- [GLM glm-5.1](https://runapi.ai/models/glm/5.1.md)
- [GLM glm-5.2](https://runapi.ai/models/glm/5.2.md)
- [GLM glm-5.3](https://runapi.ai/models/glm/5.3.md)
- [GLM glm-5.3-flash](https://runapi.ai/models/glm/5.3-flash.md)

## Category

- [Claude](https://runapi.ai/models/claude.md)
- [DeepSeek](https://runapi.ai/models/deepseek.md)
- [Embedding](https://runapi.ai/models/embedding.md)
- [Gemini](https://runapi.ai/models/gemini.md)

## Provider


## Docs

- [Quickstart](https://runapi.ai/docs/api/openai/chat-completions)
- [API reference](https://runapi.ai/docs/api/openai/chat-completions)
- [SDK README](https://github.com/runapi-ai)


---

## 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",
    "applicationCategory": "DeveloperApplication",
    "operatingSystem": "Cross-platform",
    "hasVariant": [
      {
        "@type": "SoftwareApplication",
        "name": "GLM glm-4.5"
      },
      {
        "@type": "SoftwareApplication",
        "name": "GLM glm-4.5-air"
      },
      {
        "@type": "SoftwareApplication",
        "name": "GLM glm-4.6"
      },
      {
        "@type": "SoftwareApplication",
        "name": "GLM glm-4.7"
      },
      {
        "@type": "SoftwareApplication",
        "name": "GLM glm-5"
      },
      {
        "@type": "SoftwareApplication",
        "name": "GLM glm-5-turbo"
      },
      {
        "@type": "SoftwareApplication",
        "name": "GLM glm-5.1"
      },
      {
        "@type": "SoftwareApplication",
        "name": "GLM glm-5.2"
      },
      {
        "@type": "SoftwareApplication",
        "name": "GLM glm-5.3"
      },
      {
        "@type": "SoftwareApplication",
        "name": "GLM glm-5.3-flash"
      }
    ]
  },
  {
    "@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"
      }
    ]
  },
  {
    "@context": "https://schema.org",
    "inLanguage": "en",
    "@type": "HowTo",
    "name": "From model skill to first result in four steps",
    "description": "Compare GLM API variants, pricing, and the GLM skill for app development. One API key, skills-first workflow.",
    "totalTime": "PT5M",
    "step": [
      {
        "@type": "HowToStep",
        "position": 1,
        "name": "Create an API key",
        "text": "Sign up and generate an API key from the dashboard.",
        "url": "https://runapi.ai/models/glm#how-step-1"
      },
      {
        "@type": "HowToStep",
        "position": 2,
        "name": "Pick a version",
        "text": "Choose the version that best matches your quality and cost requirements.",
        "url": "https://runapi.ai/models/glm#how-step-2"
      },
      {
        "@type": "HowToStep",
        "position": 3,
        "name": "Send a request",
        "text": "Submit your prompt and parameters to the model's documented endpoint.",
        "url": "https://runapi.ai/models/glm#how-step-3"
      },
      {
        "@type": "HowToStep",
        "position": 4,
        "name": "Get your result",
        "text": "Poll the task or set a webhook, then download the completed output.",
        "url": "https://runapi.ai/models/glm#how-step-4"
      }
    ]
  },
  {
    "@context": "https://schema.org",
    "inLanguage": "en",
    "@type": "FAQPage",
    "mainEntity": [
      {
        "@type": "Question",
        "name": "What are the GLM models good at?",
        "acceptedAnswer": {
          "@type": "Answer",
          "text": "Coding and agentic tool use. GLM-5.1 leads open-weight models on SWE-bench Pro (58.4%) and scores 95.3% on AIME 2026. The full line is strong at multi-step tool calling, code generation across large codebases, and mathematical reasoning."
        }
      },
      {
        "@type": "Question",
        "name": "What is the difference between glm-4.5 and glm-4.5-air?",
        "acceptedAnswer": {
          "@type": "Answer",
          "text": "glm-4.5 is the 355B flagship (32B active parameters) with 128K context; glm-4.5-air is a lighter 106B MoE (12B active) for faster, lower-cost everyday work."
        }
      },
      {
        "@type": "Question",
        "name": "How does GLM-5 compare to GLM-4.7?",
        "acceptedAnswer": {
          "@type": "Answer",
          "text": "GLM-5 scales to 744B total / 40B active with 256 experts, versus GLM-4.7's 358B / 32B. SWE-bench Verified jumps from 73.8% to 77.8%. Both share 200K context."
        }
      },
      {
        "@type": "Question",
        "name": "Which SDKs can call GLM through RunAPI?",
        "acceptedAnswer": {
          "@type": "Answer",
          "text": "Point the OpenAI SDK (Chat Completions or Responses) or the Anthropic Messages SDK at RunAPI and pass the GLM model id; the proxy adapts the protocol for you."
        }
      },
      {
        "@type": "Question",
        "name": "How is GLM billed?",
        "acceptedAnswer": {
          "@type": "Answer",
          "text": "Per token, pay-as-you-go, at RunAPI's published input and output rates for each GLM model — no subscription."
        }
      },
      {
        "@type": "Question",
        "name": "Which variant should I start with?",
        "acceptedAnswer": {
          "@type": "Answer",
          "text": "Pick the cheapest variant that meets your quality bar. Most teams start on the fast variant and graduate to pro for production."
        }
      },
      {
        "@type": "Question",
        "name": "Is there a free tier?",
        "acceptedAnswer": {
          "@type": "Answer",
          "text": "Creating an account and API key is free. API calls use prepaid, pay-as-you-go billing; add funds before making requests."
        }
      },
      {
        "@type": "Question",
        "name": "Do you stream results?",
        "acceptedAnswer": {
          "@type": "Answer",
          "text": "Where streaming is available, RunAPI streams end-to-end."
        }
      },
      {
        "@type": "Question",
        "name": "How are failures billed?",
        "acceptedAnswer": {
          "@type": "Answer",
          "text": "Failed generations are not charged."
        }
      },
      {
        "@type": "Question",
        "name": "Are outputs cached?",
        "acceptedAnswer": {
          "@type": "Answer",
          "text": "Generated outputs are stored and retrievable by task ID. Inputs are not cached."
        }
      },
      {
        "@type": "Question",
        "name": "Can I use commercially?",
        "acceptedAnswer": {
          "@type": "Answer",
          "text": "Yes — commercial use is included for every variant unless a model license explicitly restricts it, which is called out on the variant page."
        }
      },
      {
        "@type": "Question",
        "name": "What about rate limits?",
        "acceptedAnswer": {
          "@type": "Answer",
          "text": "Per-key rate limits scale with usage tier. See pricing page for current limits."
        }
      },
      {
        "@type": "Question",
        "name": "Where can I report issues?",
        "acceptedAnswer": {
          "@type": "Answer",
          "text": "Open an issue on the public GitHub repo or email support."
        }
      }
    ]
  }
]
```
