---
title: "GLM API — variantes, tarifs et model skill | RunAPI"
url: "https://runapi.ai/fr/models/glm.md"
canonical: "https://runapi.ai/fr/models/glm.md"
locale: "fr"
model: "GLM"
provider: "Z.ai"
modality: "text"
variant_count: 7
price_from_cents: 1
---

# GLM API

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

**Provider:** Z.ai
**Modality:** Text
**Catalog:** 7 variants

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.

## Variants

| Version | Variant | Pricing | Billing | URL |
|---|---|---|---|---|
| glm-4.5 | `4.5` | $0.020 | 1K tokens | https://runapi.ai/fr/models/glm/4.5.md |
| glm-4.5-air | `4.5-air` | $0.010 | 1K tokens | https://runapi.ai/fr/models/glm/4.5-air.md |
| glm-4.6 | `4.6` | $0.020 | 1K tokens | https://runapi.ai/fr/models/glm/4.6.md |
| glm-4.7 | `4.7` | $0.020 | 1K tokens | https://runapi.ai/fr/models/glm/4.7.md |
| glm-5 | `5` | $0.020 | 1K tokens | https://runapi.ai/fr/models/glm/5.md |
| glm-5-turbo | `5-turbo` | $0.020 | 1K tokens | https://runapi.ai/fr/models/glm/5-turbo.md |
| glm-5.1 | `5.1` | $0.030 | 1K tokens | https://runapi.ai/fr/models/glm/5.1.md |


## API endpoints

Base URL: `https://runapi.ai`

- `POST /v1/chat/completions`

Use the OpenAI or Anthropic SDK with your RunAPI API key. No extra SDK required.

## Context

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.

## FAQ

### Comment appeler ce modèle ?

Installez le model skill et suivez ses notes de setup avec votre clé RunAPI.

### Les générations échouées coûtent-elles quelque chose ?

Les générations échouées ne sont pas facturées

### Puis-je l'appeler depuis mon application ?

Oui. Installez le model skill dans votre workspace de code et utilisez-le pendant l'ajout de la fonctionnalité.